To see the other types of publications on this topic, follow the link: Knee segmentation in MRI.
Dissertations / Theses on the topic 'Knee segmentation in MRI'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Knee segmentation in MRI.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Lind, Marcus. "Automatic Segmentation of Knee Cartilage Using Quantitative MRI Data." Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-138403.
Full textAbstract:
This thesis investigates if support vector machine classification is a suitable approach when performing automatic segmentation of knee cartilage using quantitative magnetic resonance imaging data. The data sets used are part of a clinical project that investigates if patients that have suffered recent knee damage will develop cartilage damage. Therefore the thesis also investigates if the segmentation results can be used to predict the clinical outcome of the patients. Two methods that perform the segmentation using support vector machine classification are implemented and evaluated. The evaluation indicates that it is a good approach for the task, but the implemented methods needs to be further improved and tested on more data sets before clinical use. It was not possible to relate the cartilage properties to clinical outcome using the segmentation results. However, the investigation demonstrated good promise of how the segmentation results, if they are improved, can be used in combination with quantitative magnetic resonance imaging data to analyze how the cartilage properties change over time or vary between knees.
2
Kashyap, Satyananda. "Quantitative analysis and segmentation of knee MRI using layered optimal graph segmentation of multiple objects and surfaces." Diss., University of Iowa, 2016. https://ir.uiowa.edu/etd/2228.
Full textAbstract:
Knee osteoarthritis is one of the most debilitating aging diseases as it causes loss of cartilage of the knee joint. Knee osteoarthritis affects the quality of life and increases the burden on health care costs. With no disease-modifying osteoarthritis drug currently available there is an immediate need to understand the factors triggering the onset and progression of the disease. Developing robust segmentation techniques and quantitative analysis helps identify potential imaging-based biomarkers that indicate the onset and progression of osteoarthritis. This thesis work developed layered optimal graph image segmentation of multiple objects and surfaces (LOGISMOS) framework based knee MRI segmentation algorithms in 3D and longitudinal 3D (4D). A hierarchical random forest classifier algorithm was developed to improve cartilage costs functions for the LOGISMOS framework. The new cost function design significantly improved the segmentation accuracy over the existing state of the art methods. Disease progression results in more artifacts appearing similar to cartilage in MRI. 4D LOGISMOS segmentation was developed to simultaneously segment multiple time-points of a single patient by incorporating information from earlier time points with a relatively healthier knee in the early stage of the disease. Our experiments showed consistently higher segmentation accuracy across all the time-points over 3D LOGISMOS segmentation of each time-point. Fully automated segmentation algorithms proposed are not 100% accurate especially for patient MRI's having severe osteoarthritis and require interactive correction. An interactive technique called just-enough interaction (JEI) was developed which added a fast correction step to the automated LOGISMOS, speeding up the interactions substantially over the current slice-by-slice manual editing while maintaining high accuracy. JEI editing modifies the graph nodes instead of the boundary surfaces of the bones and cartilages providing globally optimally corrected results. 3D JEI was extended to 4D JEI allowing for simultaneous visualization and interaction of multiple time points of the same patients.
Further quantitative analysis tools were developed to study the thickness losses. Nomenclature compliant sub-plate detection algorithm was developed to quantify thickness in the smaller load bearing regions of the knee to help understand the varying rates of thickness losses in the different regions. Regression models were developed to predict the thickness accuracy on a patient MRI at a later follow-up using the available thickness information from the LOGISMOS segmentation of the current set of MRI scans of the patient. Further non-cartilage based imaging biomarker quantification was developed to analyze bone shape changes between progressing and non-progressing osteoarthritic populations. The algorithm quantified statistically significant local shape changes between the two populations. Overall this work improved the state of the art in the segmentation of the bones and cartilage of the femur and tibia. Interactive 3D and 4D JEI were developed allowing for fast corrections of the segmentations and thus significantly improving the accuracy while performing many times faster. Further, the quantitative analysis tools developed robustly analyzed the segmentation providing measurable metrics of osteoarthritis progression.
3
Dib, Zoheir. "Chirurgie orthopédique assistée par ordinateur : application au traitement de l'arthrose du genou." Thesis, Brest, 2017. http://www.theses.fr/2017BRES0070/document.
Full textAbstract:
L’arthrose est un véritable problème de santé publique. Plus de dix millions de personnes sont atteintes en France et 35 millions aux États-Unis. L’arthrose du genou représente 35% du nombre total d’arthrose avec plus de 1,3 million de patients en Europe. Il existe de nos jours plusieurs solutions permettant de traiter l’arthrose du genou, suivant le caractère dégénératif de la maladie, allant du traitement chirurgical conservateur, tel que l’ostéotomie supérieure du tibia, jusqu’au traitement chirurgical prothétique, tel que l’arthroplastie totale du genou. Le succès à long terme de ces interventions repose (1) sur le contrôle de l’alignement du membre inférieur au cours de l’intervention, réalisé par l’intermédiaire de l’angle HKA entre les centres hanche, genou et cheville, et (2) sur une planification chirurgicale permettant de préparer l’intervention, et notamment, définir la position optimale des coupes osseuses pour la mise en place d’une prothèse à partir de modèles 3D de l’os du patient issus d’images tomodensitométriques (TDM) ou IRM. Nous nous sommes intéressés, dans un premier temps, à l’étude et l’évaluation, dans un contexte clinique, de la précision et la robustesse des techniques utilisées en chirurgie assistée par ordinateur pour la localisation du centre hanche, nécessaire au calcul de l’angle HKA. Nous avons ainsi proposé une nouvelle méthode, mini-invasive, et particulièrement adaptée pour l’ostéotomie supérieure du tibia. Nous nous sommes ensuite intéressés aux méthodes de segmentation permettant d’extraire la surface osseuse du genou à partir d’IRM pour la phase de planification. Nous avons également proposé une nouvelle approche, automatique, qui se base sur des modèles actifs de forme ou Active Shape Model (ASM). Compte tenu des résultats très encourageants, l’intégration de nos contributions en routine clinique pourrait, potentiellement, améliorer le service médical rendu pour le traitement de l’arthrose du genouOsteoarthritis is a real public health problem. More than ten million people are affected by osteoarthritis in France and 35 million in the United States. Knee Osteoarthritis represents 35% of the total number of osteoarthritis with more than 1.3 million patients in Europe. Today, there are several solutions to treat knee osteoarthritis depending on the degenerative nature of the disease : from conservative surgical treatment, such as High tibia Osteotomy (HTO), to prosthetic surgical treatment, such as Total Knee arthroplasty (TKA). The long-term success of these interventions is (1) the control of the lower limb alignment, during the intervention, which can be obtained by measuring the HKA angle between the hip, the knee and the ankle centers, and (2) the surgical planning allowing the preparation of the intervention, and for instance, the definition of the optimal cuts for the placement of a knee prosthesis based on the 3D model of the patient bone obtained from computerized tomography (CT) or MRI. We were interested, first, in the study and evaluation, in a clinical context, of the accuracy and precision of the methods used in computer-assisted orthopedic surgery for the localization of the hip center. We have thus proposed a new minimally invasive method especially adapted to HTO. We were interested, then, to the segmentation methods allowing the extraction of the knee bony surface from MRI for the surgical planning. We have also proposed a new automatic approach based on active shape models (ASM). Given the very encouraging results, the integration of our contributions in the clinical routine could, potentially, improve the medical benefits for the treatment of knee osteoarthritis
4
Morra, Jonathan Harold. "Learning methods for brain MRI segmentation." Diss., Restricted to subscribing institutions, 2009. http://proquest.umi.com/pqdweb?did=1905693471&sid=1&Fmt=2&clientId=1564&RQT=309&VName=PQD.
Full text
5
Krishnan, Nitya. "Multispectral segmentation of whole brain MRI." Morgantown, W. Va. : [West Virginia University Libraries], 2004. https://etd.wvu.edu/etd/controller.jsp?moduleName=documentdata&jsp%5FetdId=3753.
Full textAbstract:
Thesis (M.S.)--West Virginia University, 2004.Title from document title page. Document formatted into pages; contains vii, 89 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 56-59).
6
Ezzadeen, Hani. "Extraction and segmentation of MRI brain images." Thesis, McGill University, 2006. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=97949.
Full textAbstract:
Brain image segmentation is an active research in computer image analysis. The challenge lies in the fact that the brain anatomy is not identical for all normal subjects let alone subjects with abnormal tissue.In this thesis, we explain the research we have implemented to extract the brain from T1-weighted MRI images, and then segment the brain into the three prominent compartments (i.e. the cerebellum and the two hemispheres of the cerebrum). The brain extraction is implemented using morphological operations after thresholding. The brain segmentation, however, is implemented in two separate steps. The first step segments the two hemispheres by approximating the midsagittal surface using mainly Radon transform. The second step segments the cerebellum using an atlas-based contour as an initial contour for the gradient vector flow active contour algorithm.
Validation tests have been performed for the brain extraction and cerebellum segmentation methods.
7
Cederberg, Erik. "Adipose tissue segmentation in whole-body MRI." Thesis, Linköping University, Linköping University, Medical Informatics, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-57465.
Full text
8
Dreijer, Janto Frederick. "Cardiac MRI segmentation with conditional random fields." Thesis, Stellenbosch : Stellenbosch University, 2013. http://hdl.handle.net/10019.1/85847.
Full textAbstract:
Thesis (PhD)-- Stellenbosch University, 2013.ENGLISH ABSTRACT: This dissertation considers automatic segmentation of the left cardiac ventricle in short axis magnetic resonance images. The presence of papillary muscles near the endocardium border makes simple threshold based segmentation difficult. The endo- and epicardium are modelled as two series of radii which are inter-related using features describing shape and motion. Image features are derived from edge information from human annotated images. The features are combined within a Conditional Random Field (CRF) – a discriminatively trained probabilistic model. Loopy belief propagation is used to infer segmentations when an unsegmented video sequence is given. Powell’s method is applied to find CRF parameters by minimising the difference between ground truth annotations and the inferred contours. We also describe how the endocardium centre points are calculated from a single human-provided centre point in the first frame, through minimisation of frame alignment error. We present and analyse the results of segmentation. The algorithm exhibits robustness against inclusion of the papillary muscles by integrating shape and motion information. Possible future improvements are identified.
AFRIKAANSE OPSOMMING: Hierdie proefskrif bespreek die outomatiese segmentasie van die linkerhartkamer in kortas snit magnetiese resonansie beelde. Die teenwoordigheid van die papillêre spiere naby die endokardium grens maak eenvoudige drumpel gebaseerde segmentering moeilik. Die endo- en epikardium word gemodelleer as twee reekse van die radiusse wat beperk word deur eienskappe wat vorm en beweging beskryf. Beeld eienskappe word afgelei van die rand inligting van mens-geannoteerde beelde. Die funksies word gekombineer binne ’n CRF (Conditional Random Field) – ’n diskriminatief afgerigte waarskynlikheidsverdeling. “Loopy belief propagation” word gebruik om segmentasies af te lei wanneer ’n ongesegmenteerde video verskaf word. Powell se metode word toegepas om CRF parameters te vind deur die minimering van die verskil tussen mens geannoteerde segmentasies en die afgeleide kontoere. Ons beskryf ook hoe die endokardium se middelpunte bereken word vanaf ’n enkele mens-verskafte middelpunt in die eerste raam, deur die minimering van ’n raambelyningsfout. Ons analiseer die resultate van segmentering. Die algoritme vertoon robuustheid teen die insluiting van die papillêre spiere deur die integrasie van inligting oor die vorm en die beweging. Moontlike toekomstige verbeterings word geïdentifiseer.
9
Murgasova, Maria. "Segmentation of brain MRI during early childhood." Thesis, Imperial College London, 2008. http://hdl.handle.net/10044/1/4354.
Full textAbstract:
The objective of this thesis is the development of automatic methods to measure the changes in volume and growth of brain structures in prematurely born infants. Automatic tools for accurate tissue quantification from magnetic resonance images can provide means for understanding how the neurodevelopmental effects of the premature birth, such as cognitive, neurological or behavioural impairment, are related to underlying changes in brain anatomy. Understanding these changes forms a basis for development of suitable treatments to improve the outcomes of premature birth. In this thesis we focus on the segmentation of brain structures from magnetic resonance images during early childhood. Most of the current brain segmentation techniques have been focused on the segmentation of adult or neonatal brains. As a result of rapid development, the brain anatomy during early childhood differs from anatomy of both adult and neonatal brains and therefore requires adaptations of available techniques to produce good results. To address the issue of anatomical differences of the brain during early childhood compared to other age-groups, population-specific deformable and probabilistic atlases are introduced. A method for generation of population-specific prior information in the form of a probabilistic atlas is proposed and used to enhance existing segmentation algorithms. The evaluation of registration-based and intensity-based approaches shows the techniques to be complementary in the quality of automatic segmentation in different parts of the brain. We propose a novel robust segmentation method combining the advantages of both approaches. The method is based on multiple label propagation using B-spline non-rigid registration followed by EM segmentation. Intensity in homogeneity is a shading artefact resulting from the acquisition process, which significantly affects modern high resolution MR data acquired at higher magnetic field strengths. A novel template based method focused on correcting the intensity inhomogeneity in data acquired at higher magnetic field strengths is therefore proposed. The proposed segmentation method combined with proposed intensity in homogeneity correction method offers a robust tool for quantification of volumes and growth of brain structures during early childhood. The tool has been applied to 67 T1-weigted images of subject at one and two years of age.
10
Donoghue, Claire. "Analysis of MRI for knee osteoarthritis using machine learning." Thesis, Imperial College London, 2013. http://hdl.handle.net/10044/1/24684.
Full textAbstract:
Approximately 8.5 million people in the UK (13.5% of the population) have osteoarthritis (OA) in one or both knees, with more than 6 million people in the UK suffering with painful osteoarthritis of the knee. In addition, an ageing population implies that an estimated 17 million people (twice as many as in 2012) are likely to be living with OA by 2030. Despite this, there exists no disease modifying drugs for OA and structural OA in MRI is poorly characterised. This motivates research to develop biomarkers and tools to aid osteoarthritis diagnosis from MRI of the knee. Previously many solutions for learning biomarkers have relied upon hand-crafted features to characterise and diagnose osteoarthritis from MRI. The methods proposed in this thesis are scalable and use machine learning to characterise large populations of the OAI dataset, with one experiment applying an algorithm to over 10,000 images. Studies of this size enable subtle characteristics of the dataset to be learnt and model many variations within a population. We present data-driven algorithms to learn features to predict OA from the appearance of the articular cartilage. An unsupervised manifold learning algorithm is used to compute a low dimensional representation of knee MR data which we propose as an imaging marker of OA. Previous metrics introduced for OA diagnosis are loosely based on the research communities intuition of the structural causes of OA progression, including morphological measures of the articular cartilage such as the thickness and volume. We demonstrate that there is a strong correlation between traditional morphological measures of the articular cartilage and the biomarkers identified using the manifold learning algorithm that we propose (R 2 = 0.75). The algorithm is extended to create biomarkers for different regions and sequences. A combination of these markers is proposed to yield a diagnostic imaging biomarker with superior performance. The diagnostic biomarkers presented are shown to improve upon hand-crafted morphological measure of disease status presented in the literature, a linear discriminant analysis (LDA) classification for early stage diagnosis of knee osteoarthritis results with an AUC of 0.9. From the biomarker discovery experiments we identified that intensity based affine registration of knee MRIs is not sufficiently robust for large scale image analysis, approximately 5% of these registrations fail. We have developed fast algorithms to compute robust affine transformations of knee MRI, which enables accurate pairwise registrations in large datasets. We model the population of images as a non-linear manifold, a registration is defined by the shortest geodesic path over the manifold representation. We identify sources of error in our manifold representation and propose fast mitigation strategies by checking for consistency across the manifold and by utilising multiple paths. These mitigation strategies are shown to improve registration accuracy and can be computed in less than 2 seconds with current architecture.
11
Abdullah, Bassem A. "Segmentation of Multiple Sclerosis Lesions in Brain MRI." Scholarly Repository, 2012. http://scholarlyrepository.miami.edu/oa_dissertations/711.
Full textAbstract:
Multiple Sclerosis (MS) is an autoimmune disease of central nervous system. It may result in a variety of symptoms from blurred vision to severe muscle weakness and degradation, depending on the affected regions in brain. To better understand this disease and to quantify its evolution, magnetic resonance imaging (MRI) is increasingly used nowadays. Manual delineation of MS lesions in MR images by human expert is time-consuming, subjective, and prone to inter-expert variability. Therefore, automatic segmentation is needed as an alternative to manual segmentation. However, the progression of the MS lesions shows considerable variability and MS lesions present temporal changes in shape, location, and area between patients and even for the same patient, which renders the automatic segmentation of MS lesions a challenging problem. In this dissertation, a set of segmentation pipelines are proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. These techniques use a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The main contribution of this set of frameworks is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional views segmentation to produce verified segmentation. The multi-sectional views pipeline is customized to provide better segmentation performance and to benefit from the properties and the nature of MS lesion in MRI. These customization and enhancement leads to development of the customized MV-T-SVM. The MRI datasets that were used in the evaluation of the proposed pipelines are simulated MRI datasets (3 subjects) generated using the McGill University BrainWeb MRI Simulator, real datasets (51 subjects) publicly available at the workshop of MS Lesion Segmentation Challenge 2008 and real MRI datasets (10 subjects) for MS subjects acquired at the University of Miami. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.
12
McGraw, Tim E. "Denoising, segmentation and visualization of diffusion weighted MRI." [Gainesville, Fla.] : University of Florida, 2005. http://purl.fcla.edu/fcla/etd/UFE0011618.
Full text
13
Kai, Li. "Neuroanatomical segmentation in MRI exploiting a priori knowledge /." view abstract or download file of text, 2007. http://proquest.umi.com/pqdweb?did=1400964181&sid=1&Fmt=2&clientId=11238&RQT=309&VName=PQD.
Full textAbstract:
Thesis (Ph. D.)--University of Oregon, 2007.Typescript. Includes vita and abstract. Includes bibliographical references (leaves 148-158). Also available for download via the World Wide Web; free to University of Oregon users.
14
Zhu, Yanong. "Automatic prostate segmentation and cancer staging using MRI." Thesis, University of East Anglia, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.426684.
Full text
15
Liu, Warren Hsiao-T. "Segmentation of Subcortical Structures from Nonhuman Primate MRI." Thesis, Virginia Tech, 2006. http://hdl.handle.net/10919/34737.
Full textAbstract:
Segmented analysis of subcortical structures within the nonhuman primate can potentially have a profound impact on studying the relationship between volumetric characteristics and alcohol dependencies. Image segmentations have been widely used in quantifying structural information. There are a variety of methods in which users can extract desired structures from a medical image; ranging from manual segmentations to fully-automated segmentations and 2-D to 3-D. The implications of this possibility can have tremendous applicability to medical research and diagnosis.
The primary goal of my thesis is to investigate different implementation methodologies for segmenting subcortical structures such as the hippocampus and striatum and then apply that knowledge towards the development of an approach to segment these two structures from a group of alcohol-dependent Rhesus Macaque monkeys. Using the Level Set Deformable Model (LSDM) with a priori structural information, a series of T1-weighted MR images of Rhesus Macaque hippocampi and striatum were segmented in an effort to compare the structural hippocampal and striatal volumes between early and late stages of alcohol dependency. The results suggest that the volumes of both subcortical structures are affected negatively by alcoholism. Volume deficits of as much as 5% for the hippocampus and 8% for the caudate were found.Master of Science
16
Ibrahim, Haidi. "Segmentation of the liver from 3D MRI data." Thesis, University of Surrey, 2005. http://epubs.surrey.ac.uk/842968/.
Full textAbstract:
Three dimensional (3D) visualisation has the potential to significantly ease the decision making in presurgical planning. The first stage of creating a 3D model for this purpose is to segment the liver from magnetic resonance (MRI) images. However, MRI images often contain data corrupted by intensity variations in held strength due to the sensitivity of the radio frequency (rf) coils used in the A/IRI scanner. In this thesis, we investigate several approaches to arrive at a solution to overcome this inhomogeneity problem, and at the same time, improve the image quality. These experiments show that the use of local enhancement, followed by median filtering, and toboggan contrast enhancement, is a good solution to achieve this aim. We then automate a segmentation technique known as intelligent scissors to segment the liver. The user only needs to select an initial slice, and the method is executed automatically. From the initial slice, the contour propagates inside the volume and segments the liver in every slice using a dynamic programming algorithm.
17
Stacke, Karin. "Automatic Brain Segmentation into Substructures Using Quantitative MRI." Thesis, Linköpings universitet, Datorseende, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-128900.
Full textAbstract:
Segmentation of the brain into sub-volumes has many clinical applications. Manyneurological diseases are connected with brain atrophy (tissue loss). By dividingthe brain into smaller compartments, volume comparison between the compartmentscan be made, as well as monitoring local volume changes over time. Theformer is especially interesting for the left and right cerebral hemispheres, dueto their symmetric appearance. By using automatic segmentation, the time consumingstep of manually labelling the brain is removed, allowing for larger scaleresearch.In this thesis, three automatic methods for segmenting the brain from magneticresonance (MR) images are implemented and evaluated. Since neither ofthe evaluated methods resulted in sufficiently good segmentations to be clinicallyrelevant, a novel segmentation method, called SB-GC (shape bottleneck detectionincorporated in graph cuts), is also presented. SB-GC utilizes quantitative MRIdata as input data, together with shape bottleneck detection and graph cuts tosegment the brain into the left and right cerebral hemispheres, the cerebellumand the brain stem. SB-GC shows promises of highly accurate and repeatable resultsfor both healthy, adult brains and more challenging cases such as childrenand brains containing pathologies.
18
Mahbod, Amirreza. "Structural Brain MRI Segmentation Using Machine Learning Technique." Thesis, KTH, Skolan för teknik och hälsa (STH), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-189985.
Full textAbstract:
Segmenting brain MR scans could be highly benecial for diagnosing, treating and evaluating the progress of specic diseases. Up to this point, manual segmentation,performed by experts, is the conventional method in hospitals and clinical environments. Although manual segmentation is accurate, it is time consuming, expensive and might not be reliable. Many non-automatic and semi automatic methods have been proposed in the literature in order to segment MR brain images, but the levelof accuracy is not comparable with manual segmentation. The aim of this project is to implement and make a preliminary evaluation of a method based on machine learning technique for segmenting gray matter (GM),white matter (WM) and cerebrospinal uid (CSF) of brain MR scans using images available within the open MICCAI grand challenge (MRBrainS13).The proposed method employs supervised articial neural network based autocontext algorithm, exploiting intensity-based, spatial-based and shape model-basedlevel set segmentation results as features of the network. The obtained average results based on Dice similarity index were 97.73%, 95.37%, 82.76%, 88.47% and 84.78% for intracranial volume, brain (WM + GM), CSF, WM and GM respectively. This method achieved competitive results with considerably shorter required training time in MRBrainsS13 challenge.
19
Makropoulos, Antonios. "Automatic MRI segmentation of the developing neonatal brain." Thesis, Imperial College London, 2014. http://hdl.handle.net/10044/1/23953.
Full textAbstract:
Detailed morphometric analysis of the neonatal brain is required to characterise normal brain development and investigate the neuroanatomical correlates of cognitive impairments. The segmentation of the brain in Magnetic Resonance Imaging (MRI) is a prerequisite to obtain quantitative measurements of regional brain structures. These measurements obtained at term-equivalent or early preterm age may lead to improved understanding of brain growth and may help evaluate long-term neurodevelopmental performance at an early stage. This thesis focuses on the development of an accurate segmentation algorithm for the neonatal brain MR images and its application in large cohorts of subjects. Neonatal brain segmentation is challenging due to the large anatomical variability as a result of the rapid brain development in the neonatal period. The lack of training data in the neonatal period, encoded in brain atlases, further hinders the development of automatic segmentation tools. A novel algorithm for the tissue segmentation of the neonatal brain is proposed. The algorithm is extended for the regional brain segmentation. This is the first segmentation method for the parcellation of the developing neonatal brain into multiple structures. A novel method is further proposed for the group-wise segmentation of the data that utilizes unlabelled data to complement the labelling information of brain atlases. Previous studies in the literature tended to overestimate the extent of the cortical region. A method based on the morphology of the cortex is introduced to correct for this over-segmentation. The segmentation method is applied on an extensive database of neonatal MR images. Regional volumetric, surface and diffusion tensor imaging measurements are derived from the early preterm period to term-equivalent age. These measurements allow characterisation of the regional brain development and the investigation of correlations with clinical factors. Finally, a spatio-temporal structural atlas is constructed for multiple regions of the neonatal brain.
20
Al-Riyami, Masoud. "Traumatic Chondral Lesions of the Knee in Athletes with Emphasis on Arthroscopy, MRI, and Knee Function." Thesis, University of Sheffield, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.486789.
Full textAbstract:
Background: Traumatic chondral lesions of the knee are common in football and rugby players, The diagnosis is often confirmed by arthroscopy, considered appropriate because of persistent pain and effusion. The natural course of these injuries is not well known. Clinical diagnosis is difficult and MRI is not always reliable. Aims: 1. To introduce a simplified arthroscopic mapping system of the weight-bearing surfaces of the knee which can be used to describe the location of these chondral lesions. 2. To correlate the location and severity of these lesions with a novel knee function score designe~ to reflect the demands of football and rugby. 3. To assess the accuracy of different MRI sequences in diagnosing chondral lesions using the arthroscopic mapping system as a standard. 4. To evaluate the short-term functional outcome of microfractured lesions using MRI and function scores. Methods: Forty two consecutive football and rugby players with traumatic isolated chondral lesions observed at arthroscopy were included after appropriate consent. Lesion size and grade were recorded with the mapping system. All subjects were scanned two to three weeks after surgery using a 3-Tesla MRI. At eight to 12 weeks from surgery they were tested with the functional knee score. Twenty four out of 42 subjects with grade III IV lesions underwent microfracture at the time of arthroscopy. They were assessed at 3, 6, 12 and 18 months by functional knee score and MRI. A second look arthroscopy was carried out in 10 players five to seven months after surgery to evaluate lesion healing because there was discrepancy between. a 'normal' MRI and persistent clinical symptoms. Results: Fifty five lesions on weight-bearing surfaces were found in the 42 subjects. The average size of the lesion was 197 square mm. Pain, effusion, tenderness on palpation and positive compression rotation test were the predominant symptoms and signs. The medial femoral condyle (MFC) was affected most with 36 (65 %) of the lesions. the lesions were concentrated in the B areas (p < 0.05). Grade IV lesions were the most common with 26 lesions (47.3 %). These lesions were concentrated in the B areas (p < 0.05). Cartilage specific sequences (CSS) showed a sensitivity of 89 percent and specificity of 98 percent to identify the chondral lesions. Lesion location and grade determined by MRI were comparable to arthroscopy, but size was underestimated by MRI (p < 0.05). Both the functional knee score and MRI showed good correlation in assessing healing after microfracture at six, 12 and 18 months (r2 =0.993,0.986 and 0.993, respectively). Conclusion: The distribution of the traumatic chondral lesions over the weight-bearing surfaces of the knee is unequal, and neither location nor grade predict functional outcome. Cartilage specific sequences have relatively high sensitivity but are not reliable enough to replace arthroscopy in diagnosing cases with typical symptoms and signs. Microfracture shows excellent short term out-comes. Both the functional knee score and MRI are reliable enough on average to confirm healing at the defect site, and a second look arthroscopy may be required in some cases.
21
Rezaeitabar, Yousef. "Facial Soft Tissue Segmentation In Mri Using Unlabeled Atlas." Master's thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613546/index.pdf.
Full textAbstract:
Segmentation of individual facial soft tissues has received relatively little attention in the literature due to the complicated structures of these tissues. There is a need to incorporate the prior information, which is usually in the form of atlases, in the segmentation process. In this thesis we performed several segmentation methods that take advantage of prior knowledge for facial soft tissue segmentation. An atlas based method and three expectation maximization &ndashMarkov random field (EM-MRF) based methods are tested for two dimensional (2D) segmentation of masseter muscle in the face. Atlas based method uses the manually labeled atlases as prior information. We implemented EM-MRF based method in different manners
without prior information, with prior information for initialization and with using labeled atlas as prior information. The differences between these methods and the influence of the prior information are discussed by comparing the results. Finally a new method based on EM-MRF is proposed in this study. In this method we aim to use prior information without performing manual segmentation, which is a very complicated and time consuming task. 10 MRI sets are used as experimental data in this study and leave-one-out technique is used to perform segmentation for all sets. The test data is modeled as a Markov Random Field where unlabeled training data, i.e., other 9 sets, are used as prior information. The model parameters are estimated by the Maximum Likelihood approach when the Expectation Maximization iterations are used to handle hidden labels. The performance of all segmentation methods are computed and compared to the manual segmented ground truth. Then we used the new 2D segmentation method for three dimensional (3D) segmentation of two masseter and two temporalis tissues in each data set and visualize the segmented tissue volumes.
22
Prastawa, Marcelinus Gerig Guido. "An MRI segmentation framework for brains with anatomical deviations." Chapel Hill, N.C. : University of North Carolina at Chapel Hill, 2007. http://dc.lib.unc.edu/u?/etd,768.
Full textAbstract:
Thesis (Ph. D.)--University of North Carolina at Chapel Hill, 2007.Title from electronic title page (viewed Dec. 18, 2007). "... in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Department of Computer Science." Discipline: Computer Science; Department/School: Computer Science.
23
Sångberg, Dennis. "Automated Glioma Segmentation in MRI using Deep Convolutional Networks." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-171046.
Full textAbstract:
Manual segmentation of brain tumours is a time consuming process, results often show high variability, and there is a call for automation in clinical practice. In this thesis the use of deep convolutional networks for automatic glioma segmentation in MRI is investigated. The implemented networks are evaluated on data used in the brain tumor segmentation challenge (BraTS). It is found that 3D convolutional networks generally outperform 2D convolutional networks, and that the best networks can produce segmentations that closely resemble human segmentations. Convolutional networks are also evaluated as feature extractors with linear SVM classifiers on top, and although the sensitivity is improved considerably, the segmentations are heavily oversegmented. The importance of the amount of data available is investigated as well by comparing results from networks trained on both 2013 and the greatly extended 2014 data set, but it is found that the method of producing ground-truth was also a contributing factor. The networks does not beat the previous high-scores on the BraTS data, but several simple improvement areas are identified to take the networks further.Manuell segmentering av hjärntumörer är en tidskrävande process, segmenteringarna är ofta varierade mellan experter, och automatisk segmentering skulle vara användbart för kliniskt bruk. Den här rapporten undersöker användningen av deep convolutional networks (ConvNets) för automatisk segmentering av gliom i MR-bilder. De implementerade nätverken utvärderas med hjälp av data från brain tumor segmentation challenge (BraTS). Studien finner att 3D-nätverk har generellt bättre resultat än 2D-nätverk, och att de bästa nätverken har förmågan att ge segmenteringar som liknar mänskliga segmenteringar. ConvNets utvärderas också som feature extractors, med linjära SVM som klassificerare. Den här metoden ger segmenteringar med hög känslighet, men är också till hög grad översegmenterade. Vikten av att ha mer träningsdata undersöks också genom att träna på två olika stora dataset, men metoden för att få fram de riktiga segmenteringarna har troligen också stor påverkan på resultatet. Nätverken slår inte de tidigare rekorden på BraTS, men flera viktiga men enkla förbättringsområden är identifierade som potentiellt skulle förbättra resultaten.
24
Alshuft, Hamza. "MRI-based brain morphometry correlates of chronic pain in knee osteoarthritis." Thesis, University of Nottingham, 2015. http://eprints.nottingham.ac.uk/29746/.
Full textAbstract:
Chronic pain is a complex experience that involves sensory, emotional, and cognitive aspects. The neurobiological mechanisms are therefore expected to be complex, widespread and largely maladaptive. Recent research of neuroimaging in chronic pain suggests cerebral re-organization on a structural level as a consequence of chronic pain. However, a combined and large-scale brain morphological profile in chronic pain to investigate its neural substrates has not been elucidated. The research presented aims to investigate morphological brain correlates and putatively related behavioural and cognitive aspects of chronic pain due to primary nociceptive knee osteoarthritic disorder using advanced imaging techniques for manual, voxel-based, and surface-based analysis, and questionnaire-based participants’ characterization. 31 participants with chronic painful knee osteoarthritis (age= 64.6± 8.4 years, 15 females, mean duration of pain=9.6 years) and 22 healthy controls (age= 61.3± 7.5, 13 females) underwent high-resolution anatomical MRI at 3 Tesla, and detailed pain characterization and psychometric assessment. Findings from this thesis challenge the common belief that chronic pain leads to hippocampal volume reduction and allegedly cognitive dysfunction. Indeed, general cognitive function and delayed recall memory were normally preserved in the studied cohort, and moreover the hippocampal volume was significantly enlarged. The volume of the rostral part (emotional) of anterior cingulate showed significant positive correlation with pain catastrophizing behaviour suggesting that it may underlie the pain catastrophizing tendency in patients with chronic knee pain. Higher scores of mechanical pain sensitivity correlated with reduced cortical thickness in the anterior cingulate indicating its potential key role in the process of central pain sensitization. Sufferers of chronic knee OA pain exhibited less grey matter volume in the left dorsolateral prefrontal cortex, which has a modulatory role in nociceptive transmission namely, pain perception inhibitory effect. Although the mechanism of this reduction is unknown, such a change may suggest functional disturbance with subsequent aberrant contribution to pain sustainability and chronification. Whole brain cortical thickness was investigated in patients and results revealed wide spread cortical thinning progresses with pain duration, preferentially in females, and in areas largely outside the known pain matrix, but including the posterior default mode network. Finally, preliminary results from investigating the potential mechanism of chronic pain related neocortical plasticity will be presented that may provide framework for future studies.
25
Kobold, Jonathan. "Deep Learning for lesion and thrombus segmentation from cerebral MRI." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLE044.
Full textAbstract:
L'apprentissage profond est le meilleur ensemble de méthodes aumonde pour identifier des objets sur des images. L'accident vascu-laire cérébral est une maladie mortelle dont le traitement nécessitel'identification d'objets par imagerie médicale. Cela semble être unecombinaison évidente, mais il n'est pas anodin de joindre les deux.La segmentation de la lésion de l'IRM cérébrale a retenu l'attentiondes chercheurs, mais la segmentation du thrombus est encore inex-plorée. Ce travail montre que les architectures de réseau de neur-ones convolutionnels contemporaines ne peuvent pas identifier demanière fiable le thrombus sur l'IRM. En outre, il est démontrépourquoi ces modèles ne fonctionnent pas sur ce problème. Fort decette connaissance, une architecture de réseau neuronal récurrente aété développée, appelée logic-LSTM, capable de prendre en comptela manière dont les médecins identifient le thrombus. Cette ar-chitecture fournit non seulement la première identification fiablede thrombus, mais elle fournit également de nouvelles informationssur la conception des réseaux neuronaux. En particulier, les méthodesd'augmentation du champ récepteur sont enrichies d'une nouvelleoption sans paramètre. Enfin, le logic-LSTM améliore également lesrésultats de la segmentation des lésions en fournissant une segment-ation des lésions avec un niveau de performance humaineDeep learning, the world's best set of methods for identifying ob-jects on images. Stroke, a deadly disease whose treatment requiresidentifying objects on medical imaging. Sounds like an obvious com-bination yet it is not trivial to marry the two. Segmenting the lesionfrom stroke MRI has had some attention in literature but thrombussegmentation is still uncharted area. This work shows that contem-porary convolutional neural network architectures cannot reliablyidentify the thrombus on stroke MRI. Also it is demonstrated whythese models don't work on this problem. With this knowledge arecurrent neural network architecture, the logic LSTM, is developedthat takes into account the way medical doctors identify the throm-bus. Not only this architecture provides the first reliable thrombusidentification, it also provides new insights to neural network design.Especially the methods for increasing the receptive field are enrichedwith a new parameter free option. And last but not least the logicLSTM also improves the results of lesion segmentation by providinga lesion segmentation with human level performance
26
Auger, Daniel A. "3D cine DENSE MRI: ventricular segmentation and myocardial stratin analysis." Doctoral thesis, University of Cape Town, 2013. http://hdl.handle.net/11427/3218.
Full text
27
Mackenzie, Roderick. "Assessment of the clinical value of magnetic resonance imaging of the knee." Thesis, University of Cambridge, 1994. https://www.repository.cam.ac.uk/handle/1810/251824.
Full text
28
Johal, Parminder Singh. "Tibiofemoral movement : an in vivo study of knee kinematics using 'interventional' MRI." Thesis, Imperial College London, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.440541.
Full text
29
Basalamah, Saleh Mohammed. "Model based magnetic resonance image segmentation with application to the knee." Thesis, Imperial College London, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.424450.
Full text
30
Kim, Max. "Improving Knee Cartilage Segmentation using Deep Learning-based Super-Resolution Methods." Thesis, KTH, Medicinteknik och hälsosystem, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-297900.
Full textAbstract:
Segmentation of the knee cartilage is an important step for surgery planning and manufacturing patient-specific prostheses. What has been a promising technology in recent years is deep learning-based super-resolution methods that are composed of feed-forward models which have been successfully applied on natural and medical images. This thesis aims to test the feasibility to super-resolve thick slice 2D sequence acquisitions and acquire sufficient segmentation accuracy of the articular cartilage in the knee. The investigated approaches are single- and multi-contrast super-resolution, where the contrasts are either based on the 2D sequence, 3D sequence, or both. The deep learning models investigated are based on predicting the residual image between the high- and low-resolution image pairs, finding the hidden latent features connecting the image pairs, and approximating the end-to-end non-linear mapping between the low- and high-resolution image pairs. The results showed a slight improvement in segmentation accuracy with regards to the baseline bilinear interpolation for the single-contrast super-resolution, however, no notable improvements in segmentation accuracy were observed for the multi-contrast case. Although the multi-contrast approach did not result in any notable improvements, there are still unexplored areas not covered in this work that are promising and could potentially be covered as future work.Segmentering av knäbrosket är ett viktigt steg för planering inför operationer och tillverkning av patientspecifika proteser. Idag segmenterar man knäbrosk med hjälp av MR-bilder tagna med en 3D-sekvens som både tidskrävande och rörelsekänsligt, vilket kan vara obehagligt för patienten. I samband med 3D-bildtagningar brukar även thick slice 2D-sekvenser tas för diagnostiska skäl, däremot är de inte anpassade för segmentering på grund av för tjocka skivor. På senare tid har djupinlärningsbaserade superupplösningsmetoder uppbyggda av så kallade feed-forwardmodeller visat sig vara väldigt framgångsrikt när det applicerats på verkliga- och medicinska bilder. Syftet med den här rapporten är att testa hur väl superupplösta thick slice 2D-sekvensbildtagningar fungerar för segmentering av ledbrosket i knät. De undersökta tillvägagångssätten är superupplösning av enkel- och flerkontrastbilder, där kontrasten är antingen baserade på 2D-sekvensen, 3D-sekvensen eller både och. Resultaten påvisar en liten förbättring av segmenteringnoggrannhet vid segmentering av enkelkontrastbilderna över baslinjen linjär interpolering. Däremot var det inte någon märkvärdig förbättring i superupplösning av flerkontrastbilderna. Även om superupplösning av flerkontrastmetoden inte gav någon märkbar förbättring segmenteringsresultaten så finns det fortfarande outforskade områden som inte tagits upp i det här arbetet som potentiellt skulle kunna utforskas i framtida arbeten.
31
Zhang, Nan. "Feature selection based segmentation of multi-source images : application to brain tumor segmentation in multi-sequence MRI." Phd thesis, INSA de Lyon, 2011. http://tel.archives-ouvertes.fr/tel-00701545.
Full textAbstract:
Multi-spectral images have the advantage of providing complementary information to resolve some ambiguities. But, the challenge is how to make use of the multi-spectral images effectively. In this thesis, our study focuses on the fusion of multi-spectral images by extracting the most useful features to obtain the best segmentation with the least cost in time. The Support Vector Machine (SVM) classification integrated with a selection of the features in a kernel space is proposed. The selection criterion is defined by the kernel class separability. Based on this SVM classification, a framework to follow up brain tumor evolution is proposed, which consists of the following steps: to learn the brain tumors and select the features from the first magnetic resonance imaging (MRI) examination of the patients; to automatically segment the tumor in new data using a multi-kernel SVM based classification; to refine the tumor contour by a region growing technique; and to possibly carry out an adaptive training. The proposed system was tested on 13 patients with 24 examinations, including 72 MRI sequences and 1728 images. Compared with the manual traces of the doctors as the ground truth, the average classification accuracy reaches 98.9%. The system utilizes several novel feature selection methods to test the integration of feature selection and SVM classifiers. Also compared with the traditional SVM, Fuzzy C-means, the neural network and an improved level set method, the segmentation results and quantitative data analysis demonstrate the effectiveness of our proposed system.
32
Johansson, Adam. "Evaluation of Bone Contrast Enhanced MRI Sequences and Voxel Based Segmentation." Thesis, Umeå universitet, Radiofysik, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-37560.
Full textAbstract:
An ultra-short echo time (UTE) magnetic resonance imaging (MRI) sequence was used together with other MRI sequences to evaluate the possibility of segmenting air, soft tissues and bone. Three patients were imaged with the UTE sequence and other sequences as well as with computed tomography (CT). An algorithm using Gaussian mixture models was developed and applied to the problem of segmenting the MR images. A similar algorithm was developed and used to generate an artificial CT image from the MR data. The images of the first patient were used as training data for the algorithms and the images of the other two patients were used for validation. It was found that less than 20 percent of the volume inside the head was misclassified and that the root mean square error of the artificial CT image was less than 420 Hounsfield units. Finally a volunteer was imaged in the same way but with an additional UTE sequence with a larger flip angle. The results suggested that the additional image may improve segmentation further.En sekevens för bildgivande magnetresonans (MRI) med ultrakort ekotid (UTE) användes tillsammans med andra MRI-sekvenser till att utvärdera möjligheten att segmentera luft, mjukvävnad och ben. Bilder togs av tre patienter med UTE-sekvensen och med övriga sekvenser samt med datortomografi (CT). En algoritm baserad på en blanding av normalfördelningar utvecklades och tillämpades på MR-segmenteringsproblemet.En likande algoritm utvecklades och användes till att skapa en konstgjord CT-bild utifrån MR-bilderna.Bilderna tagna av den första patienten användes till att träna algoritmerna medan bilderna av de två andra patienterna användes för validering. Mindre än 20 procent av volymen inuti huvudet felklassificerades och det kvadratiska medelvärdet av avvikelserna i den konstgjorda CT-bilden var mindre än 420 hounsfieldenheter. Slutligen togs bilder av en frivillig på samma sätt men med ytterligare en UTE-sekvens med en större flippvinkel. Resultatet antyder att den nya bilden kan bidra till en förbättrad segmentering.
33
Hansson, Olof. "Interactive segmentation of abdominal organs from 3D CT and MRI images." Thesis, Linköpings universitet, Institutionen för teknik och naturvetenskap, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-93510.
Full textAbstract:
Within the medical field, image segmentation is an important tool which can be used by radiologists and surgeons who want quantitative measurements of a lesion or organ. To be clinically useful, the tool has to be fast and easy to use. This work comprises implementation of the image foresting transform for segmentation using the Dijkstra algorithm and compares computation time between the implemented algorithm and a previous implemented algorithm, Bellman-Ford. These algorithms solve the shortest path with minimum cost problem. For a given cost function, similar results both in computation time and visual results were obtained with the two algorithms. Changing the cost functions, on the other hand, yielded very different segmentation results. The volume of liver and kidney was compared with manually delineated organs regarding seed planting and execution time. A graphical user interface has also been implemented.
34
Batista, Neto Joao Do Espirito Santo. "Techniques for computer-based anatomical segmentation of the brain using MRI." Thesis, Imperial College London, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.244197.
Full text
35
Kulaga-Yoskovitz, Jessie. "Hippocampal subfield segmentation on sub-millimetric MRI in temporal lobe epilepsy." Thesis, McGill University, 2013. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=119544.
Full textAbstract:
Background Temporal lobe epilepsy (TLE) is the most common drug-resistant epilepsy in adults. Hippocampal sclerosis, the hallmark epileptogenic lesion of TLE, is characterized by neuronal loss and gliosis. The hippocampus is composed of cytoarchitechtonically distinct subfields which are differentially affected in TLE. Indeed, neuronal loss is observed primarily in the CA1 and to a lesser degree in the subiculum, CA3, CA4 and dentate gyrus. Purpose. Our goal was to develop an anatomy-driven manual hippocampal subfield segmentation protocol on sub-millimetric MRI. We applied this protocol to TLE patients and controls to assess group-wise and individual differences in subfield volumes. Methods. We obtained T1-weighted (0.6 x 0.6 x 0.6 mm3) and T2-weighted (0.4 x 0.4 x 2 mm3) images in 30 consecutive patients with drug-resistant temporal lobe epilepsy (TLE) and 25 controls on a 3T-scanner with 32-channel head-coil. Images were registered into stereotaxic space to adjust for differences in brain volume and orientation. T1- and T2-weighted images were then co-registered and resampled into 0.4 mm isotropic voxels. The hippocampus was partitioned into subiculum, CA1-3, and CA4-dentate. Results. Compared to controls (2SD cut-off) in 14/30 (47%) TLE patients we found ipsilateral atrophy: 7/14 (50%) had atrophy in all three subfields, 4 (29%) in the CA1-3 and subiculum, whereas 3 (21%) had isolated CA1-3 atrophy. 10/30 (33%) of patients demonstrated hypertrophy in at least one subfield: in 4/10 changes were ipsilateral to the focus, either in the subiculum alone (1), or combined with CA1-CA3 (1), CA4-DG (1), or in CA1-CA3 and CA4-DG (1). In 6/10 patients, we observed bilateral hypertrophy in the subiculum (1), CA1-3 (1), CA4-DG (3), and combined CA1-3 and CA4-DG (1). Six patients demonstrate subfield volumes within the normal range. Significance. In our cohort of patients with drug-resistant TLE and unilateral hippocampal atrophy, subicular and hippocampal subfield atrophy, mainly CA1-3, co-occurred. Conversely, in 33% of patients, sub-millimetric MRI revealed hippocampal subfield hypertrophy, mainly affecting CA4-DG. Timing and interplay between structural pathology and remodelling of neuronal circuitry may favour astrogliotic response and neurogenesis, masking neuronal loss, thus resulting in MRI-apparent tissue hypertrophy.Introduction. L'épilepsie du lobe temporal (ELT) est la forme d'épilepsie pharmacorésistante la plus répandue dans la population adulte. La sclérose de l'hippocampe, la lésion épileptogène de l'ELT, est caractérisée par la perte de neurones et la gliose. L'hippocampe est composé des sous-structures qui sont cytoarchitectoniquement distinctes et sont affectées différemment par l'ELT. En effet, la perte de neurones est observée principalement dans la sous-structure CA1 et moins dans le subiculum, la CA3, la CA4 et le gyrus denté (GD). Objectif. Notre objectif était de développer un protocole pour la segmentation manuelle des sous-structures sur les images IRM sous-millimétriques. Nous avons appliqué ce protocole aux patients ayant l'ELT ainsi qu'à un groupe témoin sains pour évaluer les différences entre les groupes et les différences individuelles des volumes des sous-structures. Methodes. Nous avons obtenu des images pondérées en T1 (0.6 x 0.6 x 0.6 mm3) et en T2 (0.4 x 0.4 x 2 mm3) pour 30 patients consécutifs ayant l'ETL pharmacorésistante et pour 25 témoins sur un scanner 3T avec 32 antennes en réseau phasé. Les images ont été recalées dans l'espace stéréotaxique pour éliminer les différences de volume et d'orientation du cerveau. Les images pondérées en T1 et en T2 ont ensuite été co-recalées et ré-échantillonnées en voxels isotropes de 0.4 mm. L'hippocampe a été divisé en subiculum, CA1-3 et CA4-gyrus denté. Resultats. En comparaison avec le groupe témoin (seuil de 2 écarts-types), nous avons trouvé une atrophie ipsilaterale chez 14 patients sur 30 (47%). Sur ces 14 patients, 7 (50%) présentaient une atrophie des trois sous-structures, 4 (29%) de la CA1-3 et du subiculum, et 3 (21%) de la CA1-3 seulement. Dix des 30 (33%) patients ont montré une hypertrophie dans au moins une sous-structure. Parmi ces 10 patients, 4 ont montré des modifications ipsilateral, que ce soit dans le subiculum seul (1), ou combinées avec la CA1-3 (1), le CA4-GD (1) ou dans la CA1-CA3 et le CA4-GD (1). Pour les 6 autres patients, nous avons observé une hypertrophie bilatérale dans le subiculum (1), la CA1-3 (1), le CA4-GD (1), et à la fois dans le CA1-3 et le CA4-GD (1). Six patients présentaient des volumes de sous-structures équivalents à la distribution normale du groupe témoin. Conclusion. Dans notre cohorte de patients ayant l'ELT pharmacorésistante et l'atrophie de l'hippocampe unilatérale, l'atrophie du subiculum et des sous-structures de l'hippocampe, principalement le CA1-3, est survenue simultanément. D'autre part, l'IRM sous-millimétrique a révélé une hypertrophie des sous-régions pour 33% des patients, affectant principalement le CA4-GD. L'interaction entre la pathologie structurelle et le remodelage des circuits neuronaux peut favoriser une réponse astrogliotique avec une neurogenèse qui masque la perte de neurones, ce qui entraine une hypertrophie des tissus sur l'IRM.
36
Tejos, Cristián Andres. "Segmentation of articular cartilage from MRI using simplex mesh diffucsion snakes." Thesis, University of Cambridge, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.613688.
Full text
37
Enlund, Åström Isabelle. "Attention P-Net for Segmentation of Post-operative Glioblastoma in MRI." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-397009.
Full textAbstract:
Segmentation of post-operative glioblastoma is important for follow-up treatment. In this thesis, Fully Convolutional Networks (FCN) are utilised together with attention modules for segmentation of post-operative glioblastoma in MR images. Attention-based modules help the FCN to focus on relevant features to improve segmentation results. Channel and spatial attention combines both the spatial context as well as the semantic information in MR images. P-Net is used as a backbone for creating an architecture with existing bottleneck attention modules and was named attention P-Net. The proposed network and competing techniques were evaluated on a Uppsala University database containing T1-weighted MR images of brain from 12 subjects. The proposed framework shows substantial improvement over the existing techniques.
38
HOU, YU. "APPLICATION OF A 3D LEVEL SET METHOD IN MRI SURFACE SEGMENTATION." University of Cincinnati / OhioLINK, 2005. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1132170846.
Full text
39
Axberg, Elin, and Ida Klerstad. "Similarity models for atlas-based segmentation of whole-body MRI volumes." Thesis, Linköpings universitet, Institutionen för medicinsk teknik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-172792.
Full textAbstract:
In order to analyse body composition of MRI (Magnetic Resonance Imaging) volumes, atlas-based segmentation is often used to retrieve information from specific organs or anatomical regions. The method behind this technique is to use an already segmented image volume, an atlas, to segment a target image volume by registering the volumes to each other. During this registration a deformation field will be calculated, which is applied to a segmented part of the atlas, resulting in the same anatomical segmentation in the target. The drawback with this method is that the quality of the segmentation is highly dependent on the similarity between the target and the atlas, which means that many atlases are needed to obtain good segmentation results in large sets of MRI volumes. One potential solution to overcome this problem is to create the deformation field between a target and an atlas as a sequence of small deformations between more similar bodies. In this master thesis a new method for atlas-based segmentation has been developed, with the anticipation of obtaining good segmentation results regardless of the level of similarity between the target and the atlas. In order to do so, 4000 MRI volumes were used to create a manifold of human bodies, which represented a large variety of different body types. These MRI volumes were compared to each other and the calculated similarities were saved in matrices called similarity models. Three different similarity measures were used to create the models which resulted in three different versions of the model. In order to test the hypothesis of achieving good segmentation results when the deformation field was constructed as a sequence of small deformations, the similarity models were used to find the shortest path (the path with the least dissimilarity) between a target and an atlas in the manifold. In order to evaluate the constructed similarity models, three MRI volumes were chosen as atlases and 100 MRI volumes were randomly picked to be used as targets. The shortest paths between these volumes were used to create the deformation fields as a sequence of small deformations. The created fields were then used to segment the anatomical regions ASAT (abdominal subcutaneous adipose tissue), LPT (left posterior thigh) and VAT (visceral adipose tissue). The segmentation performance was measured with Dice Index, where segmentations constructed at AMRA Medical AB were used as ground truth. In order to put the results in relation to another segmentation method, direct deformation fields between the targets and the atlases were also created and the segmentation results were compared to the ground truth with the Dice Index. Two different types of transformation methods, one non-parametric and one affine transformation, were used to create the deformation fields in this master thesis. The evaluation showed that good segmentation results can be achieved for the segmentation of VAT for one of the constructed similarity models. These results were obtained when a non-parametric registration method was used to create the deformation fields. In order to achieve similar results for an affine registration and to improve the segmentation of other anatomical regions, further investigations are needed.
40
Kadir, Kushsairy Abdul. "Automatic edema segmentation and quantification from cardiac MRI with 3D visualization." Thesis, University of Strathclyde, 2012. http://oleg.lib.strath.ac.uk:80/R/?func=dbin-jump-full&object_id=25810.
Full textAbstract:
The extent of myocardial edema delineates the ischemic area-at-risk (AAR) after myocardial infarction (MI). Since AAR can be used to estimate the amount of salvageable myocardial post-MI, edema imaging has potential clinical utility in the management of acute MI patients. T2 weighted Cardiac Magnetic Resonance (CMR) imaging is widely used to investigate the extent of edema with recent acute MI patient. This thesis describes new approaches and methods of automatic edema segmentation and quantification with 3D visualization. An integrated approach has been developed, including the localization of Left Ventricle (LV) wall, segmentation of myocardial wall, segmentation and quantification of edema and 3D visualization and quantification. A novel automatic segmentation of LV wall is proposed. First a new LV wall localization algorithm is used to locate the centre of the blood pool region of the LV wall. Then a novel LV wall segmentation algorithm is used to segment the LV wall from the rest of anatomical structure. The advantage of the proposed method is in its ability to automatically localize the blood pool region of LV wall and the additional shape constraint which is adaptive to the data. A novel, Automatic Edema Segmentation and Quantification algorithm is presented which is developed based on a statistical mixture model. The technique takes advantage of the characteristic of the MRI signal where the signal is governed by a Rician distribution and using this information regions of edema are segmented over the rest of LV wall. A post-processing step in used to include microvascular obstruction as part of the edema region. The computational simplicity and good edema discrimination are described. Finally, a novel integrated approach to 3D visualization and quantification algorithm is presented. It extracts the information of the LV wall boundary and edema boundary. Then the information is used to generate an interactive 3D image which helps the clinician to visualize the extent of edema and its location. This edema quantification and 3D visualization method is evaluated by expert clinicians with favourable results.
41
Ali, Syed Farooq. "Comparative Studies of Contouring Algorithms for Cardiac Image Segmentation." The Ohio State University, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=osu1325183438.
Full text
42
García-Lorenzo, Daniel. "Robust Segmentation of Focal Lesions on Multi-Sequence MRI in Multiple Sclerosis." Phd thesis, Université Rennes 1, 2010. http://tel.archives-ouvertes.fr/tel-00485645.
Full textAbstract:
La sclérose en plaques (SEP) atteint autour de 80.000 personnes en France. L'imagerie par résonance magnétique (IRM) est un outil essentiel pour le diagnostic de la SEP. Plusieurs bio-marqueurs sont obtenus à partir des IRM, comme le volume des lésions, et sont utilisés comme mesure dans des études cliniques en SEP, notamment pour le développement des nouveaux traitements. La segmentation manuelle des lésions est une tâche encombrante et dont les variabilités intra- et inter-expert sont grandes. Nous avons développé une chaîne de traitement automatique pour la segmentation des lesions focales en SEP. La méthode de segmentation est basée sur l'estimation robuste d'un modèle paramétrique des intensités du cerveau qui permet de détecter les lésions comme des données aberrantes. Nous avons aussi proposé deux méthodes pour ajouter de l'information spatiale avec les algorithmes mean shift et graph cut. Nous avons validé quantitativement notre approche en utilisant des images synthétiques et cliniques, provenant de deux centres différents pour évaluer la précision et la robustesse.
43
Li, Ting. "Contributions to Mean Shift filtering and segmentation : Application to MRI ischemic data." Phd thesis, INSA de Lyon, 2012. http://tel.archives-ouvertes.fr/tel-00768315.
Full textAbstract:
Medical studies increasingly use multi-modality imaging, producing multidimensional data that bring additional information that are also challenging to process and interpret. As an example, for predicting salvageable tissue, ischemic studies in which combinations of different multiple MRI imaging modalities (DWI, PWI) are used produced more conclusive results than studies made using a single modality. However, the multi-modality approach necessitates the use of more advanced algorithms to perform otherwise regular image processing tasks such as filtering, segmentation and clustering. A robust method for addressing the problems associated with processing data obtained from multi-modality imaging is Mean Shift which is based on feature space analysis and on non-parametric kernel density estimation and can be used for multi-dimensional filtering, segmentation and clustering. In this thesis, we sought to optimize the mean shift process by analyzing the factors that influence it and optimizing its parameters. We examine the effect of noise in processing the feature space and how Mean Shift can be tuned for optimal de-noising and also to reduce blurring. The large success of Mean Shift is mainly due to the intuitive tuning of bandwidth parameters which describe the scale at which features are analyzed. Based on univariate Plug-In (PI) bandwidth selectors of kernel density estimation, we propose the bandwidth matrix estimation method based on multi-variate PI for Mean Shift filtering. We study the interest of using diagonal and full bandwidth matrix with experiment on synthesized and natural images. We propose a new and automatic volume-based segmentation framework which combines Mean Shift filtering and Region Growing segmentation as well as Probability Map optimization. The framework is developed using synthesized MRI images as test data and yielded a perfect segmentation with DICE similarity measurement values reaching the highest value of 1. Testing is then extended to real MRI data obtained from animals and patients with the aim of predicting the evolution of the ischemic penumbra several days following the onset of ischemia using only information obtained from the very first scan. The results obtained are an average DICE of 0.8 for the animal MRI image scans and 0.53 for the patients MRI image scans; the reference images for both cases are manually segmented by a team of expert medical staff. In addition, the most relevant combination of parameters for the MRI modalities is determined.
44
Dalca, Adrian Vasile. "Segmentation of nerve bundles and ganglia in spine MRI using particle filters." Thesis, Massachusetts Institute of Technology, 2012. http://hdl.handle.net/1721.1/75654.
Full textAbstract:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 41-44).
Automatic segmentation of spinal nerve bundles originating within the dural sac and exiting the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves seen in high resolution myelographic MR images makes segmentation a challenging task. In this thesis, we present an automatic tracking method for segmentation of nerve bundles based on particle filters. We develop a novel approach to flexible particle representation of tubular structures based on Bezier splines. We construct an appropriate dynamics to reflect the continuity and smoothness properties of real nerve bundles. Moreover, we introduce a robust image likelihood model that enables delineation of nerve bundles and ganglia from the surrounding anatomical structures. We evaluate the results by comparing them to expert manual segmentation, and we demonstrate accurate and fast nerve tracking.
by Adrian Vasile Dalca.
S.M.
45
García, Lorenzo Daniel. "Robust segmentation of focal lesions on multi-sequence MRI in multiple sclerosis." Rennes 1, 2010. http://www.theses.fr/2010REN1S018.
Full textAbstract:
La sclérose en plaques (SEP) atteint autour de 80. 000 personnes en France. L'imagerie par résonance magnétique (IRM) est un outil essentiel pour le diagnostic de la SEP. Plusieurs bio-marqueurs sont obtenus à partir des IRM, comme le volume des lésions, et sont utilisés comme mesure dans des études cliniques en SEP, notamment pour le développement des nouveaux traitements. La segmentation manuelle des lésions est une tâche encombrante et dont les variabilités intra- et inter-expert sont grandes. Nous avons développé une chaîne de traitement automatique pour la segmentation des lesions focales en SEP. La méthode de segmentation est basée sur l'estimation robuste d'un modèle paramétrique des intensités du cerveau qui permet de détecter les lésions comme des données aberrantes. Nous avons aussi proposé deux méthodes pour ajouter de l'information spatiale avec les algorithmes mean shift et graph cut. Nous avons validé quantitativement notre approche en utilisant des images synthétiques et cliniques, provenant de deux centres différents pour évaluer la précision et la robustesseMultiple sclerosis (MS) affects around 80. 000 people in France. Magnetic resonance imaging (MRI) is an essential tool for diagnosis of MS and MRI-derived surrogate markers such as MS lesion volumes are often used as measures in MS clinical trials for the development of new treatments. The manual segmentation of these MS lesions is a time-consuming task that shows high inter- and intra-rater variability. We developed an automatic workflow for the segmentation of focal MS lesions on MRI. The segmentation method is based on the robust estimation of a parametric model of the intensities of the brain; lesions are detected as outliers to the model. We proposed two methods to include spatial information in the segmentation using mean shift and graph cut. We performed a quantitative evaluation of our workflow using synthetic and clinical images of two different centers to verify its accuracy and robustness
46
Chen, Zhibin. "Segmentation of MRI images using non parametric deformable models integrating fuzzy technique." Reims, 2009. http://theses.univ-reims.fr/exl-doc/GED00001122.pdf.
Full textAbstract:
L'objectif de la thèse est de développer une méthode automatique pour segmenter les tissus cérébraux (la matière grise, la matière blanche et le liquide céphalo-rachidien) à partir des images IRM, fournissant ainsi des mesures quantitatives et précises du cerveau. Dans cette thèse, nous avons développé trois modèles déformables non-paramétriques en intégrant l'information statistique et l’information floue des images pour segmenter le cerveau en différents types de tissus. Nous présentons d'abord une méthode basée sur l’analyse de l'histogramme. La répartition de l'intensité des images est modélisée par le modèle de mélanges gaussiens (MMG). Les paramètres du MMG sont estimés par l’algorithme «Expectation Maximization». Ensuite, ils sont utilisés pour guider l'évolution des courbes pour atteindre la segmentation des tissus cérébraux. Nous proposons ensuite une amélioration d’un algorithme basé sur les contours actifs orientés région avec la contrainte géométrique. Grâce à la nouvelle expression proposée, il permet de résoudre le problème de stabilité sous-jacente associé à l'algorithme d’origine, et réalise une convergence rapide. Enfin, nous présentons une segmentation de multi-classes en intégrant une segmentation floue dans la méthode level sets. Elle utilise un ensemble d'équations différentielles ordinaires. Chacune d'elles représente une classe à segmenter. Cette approche réduit la complexité de calcul par rapport à l'algorithme multi-phase existant, permettant donc d’accélérer la vitesse de convergence. Toutes les méthodes ont été évaluées avec des images IRM simulées et réelles. Les analyses quantitatives sont données. Les résultats sont très encourageantsThe research goal of this thesis is to develop an automatic segmentation method to segment brain MRI images into different tissues (gray matter, white matter, and cerebrospinal fluid), providing quantitative and precise brain measurements. In this dissertation, we have developed three non-parametric deformable models integrating statistical information and fuzzy information of images to segment the brain into different tissue types from multi types of MRI images. We firstly present a histogram analysis based algorithm, where the intensity distribution of the MRI images is modeled via the mixture Gaussian model (MGM). The parameters of components in MGM are estimated via the Expectation Maximization (EM) algorithm. Then the estimated parameters are used to guide the evolution of the level set curves to achieve the brain tissue segmentation. We then propose an improved algorithm to region-based geometric active contour. Thanks to the new regional term, the new algorithm solves the underlying stability problem associated with the original algorithm, and achieves convergence with less iteration number compared with the original algorithm. Finally, we present a multiclass algorithm by integrating fuzzy segmentation with the level set methods. The algorithm uses a set of ordinary differential equations; each of them represents a class to be segmented. The multiclass algorithm reduces the computational complexity compared with the existing multiphase algorithm, so speeds up the convergence rate. All algorithms are evaluated with simulated and real MRI images, and quantitative analyses are provided. The results are very encouraging
47
Descoteaux, Maxime. "High angular resolution diffusion MRI : from local estimation to segmentation and tractography." Nice, 2008. http://www.theses.fr/2008NICE4000.
Full textAbstract:
La résolution actuelle des IRM pondérées en diffusion suggère qu'il y a entre un et deux tiers des voxels de la matière blanche qui contiennent plusieurs faisceaux de fibres qui se croisent. L'IRM par tenseur de diffusion (DTI) classique est intrinsèquement limitée à ces endroits par son hypothèse de base qu'un seul faisceau traverse chaque voxel de l'image. Le but de cette thèse est donc de développer des techniques d'IRM à haute résolution angulaire (HARDI) pour pouvoir retrouver une ou plusieurs fibres et surmonter aux limites DTI. L'imagerie par q-ball (QBI) est une technique récente qui permet d'estimer la distribution d'orientation des fibres (ODF). La technique de QBI ainsi que l'ODF de diffusion des fibres permettent de retrouver plusieurs directions de fibres en chaque voxel de l'image. Ceux-ci joueront donc un rôle important tout au long de ce document. Cette thèse propose plusieurs contributions originales. D'abord, nous développons l'estimation robuste du signal HARDI en utilisant une base modifiée d'harmoniques sphériques et un terme de régularisation. Ensuite, nous proposons la modélisation du coefficient de diffusion apparent (ADC) pour étudier les mesures d'anisotropie HARDI et faire la classification des voxels contenant une distribution isotrope, une distribution d'une seule population de fibres et une distribution de plusieurs faisceaux fibres. Nous proposons de plus, le développement d'une solution analytique pour estimer l'ODF de diffusion en QBI ainsi qu'un nouvel algorithme de segmentation de ces images d'ODF obtenues par le QBI. Nous présentons également le calcul de l'ODF de fibres avec une nouvelle méthode de déconvolution sphérique à partir des données QBI. Enfin, nous développons de nouveaux algorithmes de suivi de fibres (tracking) déterministes et probabilistes à partir de l'ODF du q-ball et l'ODF de fibres. Finalement, tous ces nouveaux algorithmes sont testés et appliqués sur des données HARDI simulées, sur un fantôme biologique et sur des données réelles de plusieurs sujets dans des régions complexes avec plusieurs faisceaux qui se croisent. Nos résultats illustrent clairement la valeur ajoutée de nos méthodes HARDI sur la plupart des méthodes courantes en DTI qui négligent ces faisceaux complexes, ce qui peut amener à une mauvaise analyse et interprétation de l'anatomie et des fonctions cérébralesAt the current resolution of diffusion-weighted (DW) magnetic resonance imaging (MRI), research groups agree that there are between one third to two thirds of imaging voxels in the human brain white matter that contain fiber crossing bundles. This thesis tackles the important problem of recovering fiber crossing bundles from DW-MRI measurements. The main goal is to overcome the limitations of diffusion tensor imaging (DTI). It is well-known that imaging voxels where there are multiple fiber crossings produce a non-Gaussian DW signal. This is precisely where DTI is limited due to the intrinsic Gaussian assumption of the technique. Hence, this thesis is dedicated to the development of local reconstruction methods, segmentation and tractography algorithms able to infer multiple fiber crossing from DW-MRI data. To do so, high angular resolution diffusion imaging (HARDI) is used to measure DW images along several directions. Q-ball imaging (QBI) is a recent such HARDI technique that reconstructs the diffusion orientation distribution function (ODF), a spherical function that has its maxima aligned with the underlying fiber directions at every voxel. QBI and the diffusion ODF will play a central role in this thesis. There are many original contributions in this thesis. First, we propose a robust estimation of the HARDI signal using a closed-form regularization algorithm based on the spherical harmonics. Then, we estimate the apparent coefficient coefficient (ADC) to study HARDI anisotropy measures and to discriminate voxels with underlying isotropic, single fiber and multiple fiber distributions. Next, we develop a linear, robust and analytical QBI solution using the spherical harmonic basis, which is used in a new statistical region-based active contour algorithm to segment important white matter fiber bundles. In addition, we develop a new spherical deconvolution sharpening method that transforms the diffusion q-ball ODF into a fiber ODF. Finally, we propose a new deterministic tractography algorithm and a new probabilistic tractography algorithm exploiting the full distribution of the fiber ODF. Overall, we show local reconstruction, segmentation and tracking results on complex fiber regions with known fiber crossing on simulated HARDI data, on a biological phantom and on multiple human brain datasets. Most current DTI based methods neglect these complex fibers, which might lead to wrong interpretations of the brain anatomy and functioning
48
Lin, Xiangbo. "Knowledge-based image segmentation using deformable registration: application to brain MRI images." Reims, 2009. http://theses.univ-reims.fr/exl-doc/GED00001121.pdf.
Full textAbstract:
L'objectif de la thèse est de contribuer au recalage élastique d'images médicales intersujet-intramodalité, ainsi qu’à la segmentation d'images 3D IRM du cerveau dans le cas normal. L’algorithme des démons qui utilise les intensités des images pour le recalage est d’abord étudié. Une version améliorée est proposée en introduisant une nouvelle équation de calcul des forces pour résoudre des problèmes de recalages dans certaines régions difficiles. L'efficacité de la méthode est montrée sur plusieurs évaluations à partir de données simulées et réelles. Pour le recalage intersujet, une méthode originale de normalisation unifiant les informations spatiales et des intensités est proposée. Des contraintes topologiques sont introduites dans le modèle de déformation, visant à obtenir un recalage homéomorphique. La proposition est de corriger les points de déplacements ayant des déterminants jacobiens négatifs. Basée sur le recalage, une segmentation des structures internes est étudiée. Le principe est de construire une ontologie modélisant le connaissance a-priori de la forme des structures internes. Les formes sont représentées par une carte de distance unifiée calculée à partir de l'atlas de référence et celui déformé. Cette connaissance est injectée dans la mesure de similarité de la fonction de coût de l'algorithme. Un paramètre permet de balancer les contributions des mesures d'intensités et de formes. L'influence des différents paramètres de la méthode et des comparaisons avec d'autres méthodes de recalage ont été effectuées. De très bon résultats sont obtenus sur la segmentation des différentes structures internes du cerveau telles que les noyaux centraux et hippocampeThe research goal of this thesis is a contribution to the intra-modality inter-subject non-rigid medical image registration and the segmentation of 3D brain MRI images in normal case. The well-known Demons non-rigid algorithm is studied, where the image intensities are used as matching features. A new force computation equation is proposed to solve the mismatch problem in some regions. The efficiency is shown through numerous evaluations on simulated and real data. For intensity based inter-subject registration, normalizing the image intensities is important for satisfying the intensity correspondence requirements. A non-rigid registration method combining both intensity and spatial normalizations is proposed. Topology constraints are introduced in the deformable model to preserve an expected property in homeomorphic targets registration. The solution comes from the correction of displacement points with negative Jacobian determinants. Based on the registration, a segmentation method of the internal brain structures is studied. The basic principle is represented by ontology of prior shape knowledge of target internal structure. The shapes are represented by a unified distance map computed from the atlas and the deformed atlas, and then integrated into the similarity metric of the cost function. A balance parameter is used to adjust the contributions of the intensity and shape measures. The influence of different parameters of the method and comparisons with other registration methods were performed. Very good results are obtained on the segmentation of different internal structures of the brain such as central nuclei and hippocampus
49
Zhang, Lawrence M. Eng Massachusetts Institute of Technology. "Bootstrapping fully-automatic temporal fetal brain segmentation in volumetric MRI time series." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/122993.
Full textAbstract:
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 41-42).
We present a method for bootstrapping training data for the task of segmenting fetal brains in volumetric MRI time series data. Temporal analysis of MRI images requires accurate segmentation across frames, despite large amounts of unpredictable motion. We use the predicted segmentations of a baseline model and leverage anatomical structure of the fetal brain to automatically select the "good frames" that have accurate segmentations. We use these good frames to bootstrap further model training. We also introduce a novel temporal segmentation model that predicts segmentations using a history of previous segmentations, thus utilizing the temporal nature of the data. Our results show that these two approaches do not provide conclusive improvements to the quality of segmentations. Further exploration into the automatic choice of good frames is needed before
by Lawrence Zhang.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
50
VIRZì, Alessio. "3D segmentation of pelvic structures in pediatric MRI for surgical planning applications." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLT002/document.
Full textAbstract:
La planification chirurgicale repose sur l’anatomie du patient, et repose souvent sur l’analyse d’images médicales acquises avant la chirurgie. En particulier, c’est le cas pour les interventions de chirurgie pelvienne en pédiatrie, pour de nombreuses pathologies telles que des tumeurs et des malformations. Dans cette zone anatomique, en raison de sa forte vascularisation et innervation, une bonne planification chirurgicale est extrêmement importante pour éviter des lésions fonctionnelles des organes du patient, qui pourraient nuire a sa qualité de vie. En pratique clinique, la procédure standard repose sur l’analyse visuelle, coupe par coupe, des images de la région pelvienne. Cette tâche, même si elle est facilement accomplie par des radiologues experts, est très complexe et fastidieuse pour les chirurgiens, en raison de la complexité et de la variabilité des structures anatomiques et, par conséquent, de leurs images. De plus, en raison des variations anatomiques selon l’age du patient, toutes ces difficultés sont accentuées en pédiatrie et une compréhension anatomique claire est encore plus importante que pour les adultes. Pour ces raisons, il est important et utile d’être capable de fournir aux chirurgiens des modèles anatomiques 3D spécifiques aux patients, obtenus par traitement et analyse des images IRM.Dans cette thèse, nous proposons un ensemble de méthodes de segmentation d’images IRM de patients pédiatriques. Nous nous concentrons sur trois structures pelviennes importantes : les os du bassin, les vaisseaux sanguins et la vessie. Pour les os, nous proposons une méthode semi-automatique comportant une première étape de recalage de modèles osseux puis une étape de segmentation fine par modèles déformables. La principale contribution de la méthode proposée est l’introduction d’un ensemble de modèles osseux pour différentes tranches d’age, ce qui permet de prendre en compte la variabilité des os pendant la croissance. Pour les vaisseaux, nous proposons une méthode par patchs, apprentissage profond et transfert d’apprentissage, donc ne nécessitant que peu de donnes d’apprentissage. La principale contribution de ce travail est la conception d’une procédure semi-automatique pour l’extraction des patchs, qui permet a l’utilisateur de se focaliser uniquement sur les vaisseaux d’intérêt; et pour la planification chirurgicale. Pour la segmentation de la vessie, nous proposons d’utiliser une approche par modèles déformables, particulièrement robuste aux hétérogénéités de l’image et aux effets de volume partiel, souvent présents dans les images IRM pédiatriques. Toutes les méthodes proposées sont intégrées dans une plateforme logicielle libre pour le traitement d’images médicales, donnant aux chirurgiens des outils performants avec des interfacesutilisateur faciles a utiliser. De plus, nous mettons en place une stratégie de traitement et de portabilité pour la visualisation des modèles 3D du patient, permettant aux chirurgiens de générer, visualiser et partager ces modèles au sein de l’hôpital. En conclusion, les résultats obtenus avec les méthodes proposées sont quantitativement et qualitativement évalués de manière très positive par des chirurgiens pédiatriques, démontrant leurs potentialités pour l’utilisation en pratique clinique dans des procédures de planification chirurgicaleSurgical planning relies on the patient’s anatomy, and it is often based on medical images acquired before the surgery. This is in particular the case for pelvic surgery on children, for various indications such as malformations or tumors. In this particular anatomical region, due to its high vascularization and innervation, a good surgical planning is extremely important to avoid potential functional damages to the patient’s organs that could strongly affect their quality of life. In clinical practice the standard procedure is still to visually analyze, slice by slice, the images of the pelvic region. This task, even if quite easily performed by the expert radiologists, is difficult and tedious for the surgeons due to the complexity and variability of the anatomical structures and hence their images. Moreover, due to specific anatomy depending on the age of the patient, all the difficulties of the surgical planning are emphasized in the case of children, and a clear anatomical understanding is even more important than for the adults. For these reasons, it is very important and challenging to provide the surgeons with patient-specific 3D reconstructions, obtained from the segmentation of MRI images. In this work we propose a set of segmentation tools for pelvic MRI images of pediatric patients. In particular, we focus on three important pelvic structures: the pelvic bones, the pelvic vessels and the urinary bladder. For pelvic bones, we propose a semi-automatic approach based on template registration and deformable models. The main contribution of the proposed method is the introduction of a set of bones templates for different age ranges, which allows us to take into account the bones variability during growth. For vessels segmentation, we propose a patch-based deep learning approach using transfer learning, thus requiring few training data. The main contribution of this work is the design of a semi-automatic strategy for patches extraction, which allows the user to focus only on the vessels of interest for surgical planning. For bladder segmentation, we propose to use a deformable model approach that is particularly robust to image inhomogeneities and partial volume effects, which are often present in pediatric MRI images. All the developed segmentation methods are integrated in an open-source platform for medical imaging, delivering powerful tools and user-friendly GUIs to the surgeons. Furthermore, we set up a processing and portability workflow for visualization of the 3D patient specific models, allowing surgeons to generate, visualize and share within the hospital the patient specific 3D models. Finally, the results obtained with the proposed methods are quantitatively and qualitatively evaluated by pediatric surgeons, which demonstrates their potentials for clinical use in surgical planning procedures