Academic literature on the topic 'MRI IMAGE'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'MRI IMAGE.'
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.
Journal articles on the topic "MRI IMAGE"
1
Angadi, Sanjeevkumar, Mukesh Kumar Tripathi, Chudaman Devidasrao Sukte, and Shivendra Shivendra. "Medical image registration and classification using smell agent rat swarm optimization based deep Maxout network." Indonesian Journal of Electrical Engineering and Computer Science 37, no. 3 (2025): 1908. https://doi.org/10.11591/ijeecs.v37.i3.pp1908-1917.
Full textAbstract:
Medical image registration (MIR) is a crucial task in clinical image processing, involving the alignment of images from different modalities, such as magnetic resonance imaging (MRI) and computed tomography (CT), across various time points and subjects. Despite numerous advancements, no universal method caters to all MIR applications. This paper introduces the smell agent rat swarm optimization based deep Maxout network (SARSO-DMN) for MIR and classification. This work aims to enhance the accuracy and efficiency of medical image alignment and classification, addressing the challenges posed by diverse imaging modalities and temporal variations. The problem involves effectively registering CT and MRI images, followed by inhale and exhale classification. The proposed approach begins with feeding the input images into a convolutional neural network (CNN), followed by applying a deformation field to generate an intermediate output (output-1). This output, along with the input MRI images, is further processed by a CNN to produce output-2. Subsequently, output-2 and the input MRI image are subjected to another CNN, resulting in the final registered image. The classification phase utilizes a DMN optimized by the SARSO algorithm, which combines smell agent optimization (SAO) and rat swarm optimizer (RSO). The results demonstrate that SARSO-DMN achieves a maximum accuracy of 90.7%, a minimum false positive rate (FPR) of 11.3%, and a maximum true positive rate (TPR) of 91.2%. The SARSO-DMN approach provides a robust solution for MIR and classification, leveraging advanced optimization techniques to enhance performance.
2
Sanjeevkumar, Angadi Mukesh Kumar Tripathi Chudaman Devidasrao Sukte Shivendra Shivendra. "Medical image registration and classification using smell agent rat swarm optimization based deep Maxout network." Indonesian Journal of Electrical Engineering and Computer Science 37, no. 3 (2025): 1908–17. https://doi.org/10.11591/ijeecs.v37.i3.pp1908-1917.
Full textAbstract:
Medical image registration (MIR) is a crucial task in clinical image processing, involving the alignment of images from different modalities, such as magnetic resonance imaging (MRI) and computed tomography (CT), across various time points and subjects. Despite numerous advancements, no universal method caters to all MIR applications. This paper introduces the smell agent rat swarm optimization based deep Maxout network (SARSO-DMN) for MIR and classification. This work aims to enhance the accuracy and efficiency of medical image alignment and classification, addressing the challenges posed by diverse imaging modalities and temporal variations. The problem involves effectively registering CT and MRI images, followed by inhale and exhale classification. The proposed approach begins with feeding the input images into a convolutional neural network (CNN), followed by applying a deformation field to generate an intermediate output (output-1). This output, along with the input MRI images, is further processed by a CNN to produce output-2. Subsequently, output-2 and the input MRI image are subjected to another CNN, resulting in the final registered image. The classification phase utilizes a DMN optimized by the SARSO algorithm, which combines smell agent optimization (SAO) and rat swarm optimizer (RSO). The results demonstrate that SARSO-DMN achieves a maximum accuracy of 90.7%, a minimum false positive rate (FPR) of 11.3%, and a maximum true positive rate (TPR) of 91.2%. The SARSO-DMN approach provides a robust solution for MIR and classification, leveraging advanced optimization techniques to enhance performance.
3
Zhang, Huixian, Hailong Li, Jonathan R. Dillman, Nehal A. Parikh, and Lili He. "Multi-Contrast MRI Image Synthesis Using Switchable Cycle-Consistent Generative Adversarial Networks." Diagnostics 12, no. 4 (2022): 816. http://dx.doi.org/10.3390/diagnostics12040816.
Full textAbstract:
Multi-contrast MRI images use different echo and repetition times to highlight different tissues. However, not all desired image contrasts may be available due to scan-time limitations, suboptimal signal-to-noise ratio, and/or image artifacts. Deep learning approaches have brought revolutionary advances in medical image synthesis, enabling the generation of unacquired image contrasts (e.g., T1-weighted MRI images) from available image contrasts (e.g., T2-weighted images). Particularly, CycleGAN is an advanced technique for image synthesis using unpaired images. However, it requires two separate image generators, demanding more training resources and computations. Recently, a switchable CycleGAN has been proposed to address this limitation and successfully implemented using CT images. However, it remains unclear if switchable CycleGAN can be applied to cross-contrast MRI synthesis. In addition, whether switchable CycleGAN is able to outperform original CycleGAN on cross-contrast MRI image synthesis is still an open question. In this paper, we developed a switchable CycleGAN model for image synthesis between multi-contrast brain MRI images using a large set of publicly accessible pediatric structural brain MRI images. We conducted extensive experiments to compare switchable CycleGAN with original CycleGAN both quantitatively and qualitatively. Experimental results demonstrate that switchable CycleGAN is able to outperform CycleGAN model on pediatric MRI brain image synthesis.
4
Destyningtias, Budiani, Andi Kurniawan Nugroho, and Sri Heranurweni. "Analisa Citra Medis Pada Pasien Stroke dengan Metoda Peregangan Kontras Berbasis ImageJ." eLEKTRIKA 10, no. 1 (2019): 15. http://dx.doi.org/10.26623/elektrika.v10i1.1105.
Full textAbstract:
<p>This study aims to develop medical image processing technology, especially medical images of CT scans of stroke patients. Doctors in determining the severity of stroke patients usually use medical images of CT scans and have difficulty interpreting the extent of bleeding. Solutions are used with contrast stretching which will distinguish cell tissue, skull bone and type of bleeding. This study uses contrast stretching from the results of CT Scan images produced by first turning the DICOM Image into a JPEG image using the help of the ImageJ program. The results showed that the histogram equalization method and statistical texture analysis could be used to distinguish normal MRI and abnormal MRI detected by stroke.</p><p><strong>Keywords : </strong>Stroke, MRI, Dicom, JPEG, ImageJ, Contrast Stretching<strong></strong></p><p> </p>
5
Yang, Huan, Pengjiang Qian, and Chao Fan. "An Indirect Multimodal Image Registration and Completion Method Guided by Image Synthesis." Computational and Mathematical Methods in Medicine 2020 (June 30, 2020): 1–10. http://dx.doi.org/10.1155/2020/2684851.
Full textAbstract:
Multimodal registration is a challenging task due to the significant variations exhibited from images of different modalities. CT and MRI are two of the most commonly used medical images in clinical diagnosis, since MRI with multicontrast images, together with CT, can provide complementary auxiliary information. The deformable image registration between MRI and CT is essential to analyze the relationships among different modality images. Here, we proposed an indirect multimodal image registration method, i.e., sCT-guided multimodal image registration and problematic image completion method. In addition, we also designed a deep learning-based generative network, Conditional Auto-Encoder Generative Adversarial Network, called CAE-GAN, combining the idea of VAE and GAN under a conditional process to tackle the problem of synthetic CT (sCT) synthesis. Our main contributions in this work can be summarized into three aspects: (1) We designed a new generative network called CAE-GAN, which incorporates the advantages of two popular image synthesis methods, i.e., VAE and GAN, and produced high-quality synthetic images with limited training data. (2) We utilized the sCT generated from multicontrast MRI as an intermediary to transform multimodal MRI-CT registration into monomodal sCT-CT registration, which greatly reduces the registration difficulty. (3) Using normal CT as guidance and reference, we repaired the abnormal MRI while registering the MRI to the normal CT.
6
Bellam, Kiranmai, N. Krishnaraj, T. Jayasankar, N. B. Prakash, and G. R. Hemalakshmi. "Adaptive Multimodal Image Fusion with a Deep Pyramidal Residual Learning Network." Journal of Medical Imaging and Health Informatics 11, no. 8 (2021): 2135–43. http://dx.doi.org/10.1166/jmihi.2021.3763.
Full textAbstract:
Multimodal medical imaging is an indispensable requirement in the treatment of various pathologies to accelerate care. Rather than discrete images, a composite image combining complementary features from multimodal images is highly informative for clinical examinations, surgical planning, and progress monitoring. In this paper, a deep learning fusion model is proposed for the fusion of medical multimodal images. Based on pyramidal and residual learning units, the proposed model, strengthened with adaptive fusion rules, is tested on image pairs from a standard dataset. The potential of the proposed model for enhanced image exams is shown by fusion studies with deep network images and quantitative output metrics of magnetic resonance imaging and positron emission tomography (MRI/PET) and magnetic resonance imaging and single-photon emission computed tomography (MRI/SPECT). The proposed fusion model achieves the Structural Similarity Index Measure (SSIM) values of 0.9502 and 0.8103 for the MRI/SPECT and MRI/PET MRI/SPECT image sets, signifying the perceptual visual consistency of the fused images. Testing is performed on 20 pairs of MRI/SPECT and MRI/PET images. Similarly, the Mutual Information (MI) values of 2.7455 and 2.7776 obtained for the MRI/SPECT and MRI/PET image sets, indicating the model’s ability to capture the information content from the source images to the composite image. Further, the proposed model allows deploying its variants, introducing refinements on the basic model suitable for the fusion of low and high-resolution medical images of diverse modalities.
7
N., Rajalakshmi, Narayanan K., and Amudhavalli P. "Wavelet-Based Weighted Median Filter for Image Denoising of MRI Brain Images." Indonesian Journal of Electrical Engineering and Computer Science 10, no. 1 (2018): 201–6. https://doi.org/10.11591/ijeecs.v10.i1.pp201-206.
Full textAbstract:
Preliminary diagnosing of MRI images from the hospital cannot be relied on because of the chances of occurrence of artifacts resulting in degraded quality of image, while others may be confused with pathology. Obtained MRI image usually contains limited artifacts. It becomes complex one for doctors in analyzing them. By increasing the contrast of an image, it will be easy to analyze. In order to find the tumor part efficiently MRI brain image should be enhanced properly. The image enhancement methods mainly improve the visual appearance of MRI images. The goal of denoising is to remove the noise, which may corrupt an image during its acquisition or transmission, while retaining its quality. In this paper effectiveness of seven denoising algorithms viz. median filter, wiener filter, wavelet filter, wavelet based wiener, NLM, wavelet based NLM, proposed wavelet based weighted median filter(WMF) using MRI images in the presence of additive white Gaussian noise is compared. The experimental results are analyzed in terms of various image quality metrics.
8
Schramm, Georg, and Claes Nøhr Ladefoged. "Metal artifact correction strategies in MRI-based attenuation correction in PET/MRI." BJR|Open 1, no. 1 (2019): 20190033. http://dx.doi.org/10.1259/bjro.20190033.
Full textAbstract:
In hybrid positron emission tomography (PET) and MRI systems, attenuation correction for PET image reconstruction is commonly based on processing of dedicated MR images. The image quality of the latter is strongly affected by metallic objects inside the body, such as e.g. dental implants, endoprostheses, or surgical clips which all lead to substantial artifacts that propagate into MRI-based attenuation images. In this work, we review publications about metal artifact correction strategies in MRI-based attenuation correction in PET/MRI. Moreover, we also give an overview about publications investigating the impact of MRI-based attenuation correction metal artifacts on the reconstructed PET image quality and quantification.
9
Singh, Ram, and Lakhwinder Kaur. "Noise-residue learning convolutional network model for magnetic resonance image enhancement." Journal of Physics: Conference Series 2089, no. 1 (2021): 012029. http://dx.doi.org/10.1088/1742-6596/2089/1/012029.
Full textAbstract:
Abstract Magnetic Resonance Image (MRI) is an important medical image acquisition technique used to acquire high contrast images of human body anatomical structures and soft tissue organs. MRI system does not use any harmful radioactive ionized material like x-rays and computerized tomography (CT) imaging techniques. High-resolution MRI is desirable in many clinical applications such as tumor segmentation, image registration, edges & boundary detection, and image classification. During MRI acquisition, many practical constraints limit the MRI quality by introducing random Gaussian noise and some other artifacts by the thermal energy of the patient body, random scanner voltage fluctuations, body motion artifacts, electronics circuits impulse noise, etc. High-resolution MRI can be acquired by increasing scan time, but considering patient comfort, it is not preferred in practice. Hence, postacquisition image processing techniques are used to filter noise contents and enhance the MRI quality to make it fit for further image analysis tasks. The main motive of MRI enhancement is to reconstruct a high-quality MRI while improving and retaining its important features. The new deep learning image denoising and artifacts removal methods have shown tremendous potential for high-quality image reconstruction from noise degraded MRI while preserving useful image information. This paper presents a noise-residue learning convolution neural network (CNN) model to denoise and enhance the quality of noise-corrupted low-resolution MR images. The proposed technique shows better performance in comparison with other conventional MRI enhancement methods. The reconstructed image quality is evaluated by the peak-signal-to-noise ratio (PSNR) and structural similarity index (SSIM) metrics by optimizing information loss in reconstructed MRI measured in mean squared error (MSE) metric.
10
Yan, Rong. "The Value of Convolutional-Neural-Network-Algorithm-Based Magnetic Resonance Imaging in the Diagnosis of Sports Knee Osteoarthropathy." Scientific Programming 2021 (July 2, 2021): 1–11. http://dx.doi.org/10.1155/2021/2803857.
Full textAbstract:
The application value of the convolutional neural network (CNN) algorithm in the diagnosis of sports knee osteoarthropathy was investigated in this study. A network model was constructed in this experiment for image analysis of magnetic resonance imaging (MRI) technology. Then, 100 cases of sports knee osteoarthropathy patients and 50 healthy volunteers were selected. Digital radiography (DR) images and MRI images of all the research objects were collected after the inclusion of the two groups. Besides, the important physiological representations were extracted from their image data graphs, and the hidden complex relationships were learned. The state without input results was judged through convolutional network calculation, and the result prediction was given. On this basis, there was an analysis of the diagnostic efficiency of traditional DR images and MRI images based on CNN for patients with sports knee osteoarthropathy. The results showed that the MRI images analyzed by the CNN model showed a more obvious display rate than DR images for some nonbone changes of osteoarthritis. The correlation coefficient between MRI image rating and visual analog scale (VAS) was 0.865, which was higher than 0.713 of DR image rating, with a statistical meaning ( P < 0.01 ). For cases with mild lesions, the number of cases detected by MRI based on CNN algorithm in 0–4 image rating was 15, 18, 10, 6, and 7, respectively, which was markedly better than that of DR images. In short, the MRI examination based on the CNN image analysis model could extract important physiological representations from the image data and learn the hidden complex relationships. The convolutional network was calculated to determine the state of the uninput results and give the result predictions. Moreover, MRI examination based on the CNN image analysis model had high overall diagnostic efficiency and grading diagnostic efficiency for patients with motor knee osteoarthropathy, which was of great significance in clinical practice.
Dissertations / Theses on the topic "MRI IMAGE"
1
Al-Abdul, Salam Amal. "Image quality in MRI." Thesis, University of Exeter, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.288250.
Full text
2
Cui, Xuelin. "Joint CT-MRI Image Reconstruction." Diss., Virginia Tech, 2018. http://hdl.handle.net/10919/86177.
Full textAbstract:
Modern clinical diagnoses and treatments have been increasingly reliant on medical imaging
techniques. In return, medical images are required to provide more accurate and detailed
information than ever. Aside from the evolution of hardware and software, multimodal
imaging techniques offer a promising solution to produce higher quality images by fusing
medical images from different modalities. This strategy utilizes more structural and/or
functional image information, thereby allowing clinical results to be more comprehensive
and better interpreted.
Since their inception, multimodal imaging techniques have received a great deal of attention
for achieving enhanced imaging performance. In this work, a novel joint reconstruction
framework using sparse computed tomography (CT) and magnetic resonance imaging (MRI)
data is developed and evaluated. The method proposed in this study is part of the planned
joint CT-MRI system which assembles CT and MRI subsystems into a single entity. The
CT and MRI images are synchronously acquired and registered from the hybrid CT-MRI
platform. However, since their image data are highly undersampled, analytical methods, such
as filtered backprojection, are unable to generate images of sufficient quality. To overcome
this drawback, we resort to compressed sensing techniques, which employ sparse priors that
result from an application of L1-norm minimization.
To utilize multimodal information, a projection distance is introduced and is tuned to tailor
the texture and pattern of final images. Specifically CT and MRI images are alternately
reconstructed using the updated multimodal results that are calculated at the latest step
of the iterative optimization algorithm. This method exploits the structural similarities
shared by the CT and MRI images to achieve better reconstruction quality. The improved
performance of the proposed approach is demonstrated using a pair of undersampled CT-MRI
body images and a pair of undersampled CT-MRI head images. These images are
tested using joint reconstruction, analytical reconstruction, and independent reconstruction
without using multimodal imaging information. Results show that the proposed method
improves about 5dB in signal-to-noise ratio (SNR) and nearly 10% in structural similarity
measurements compared to independent reconstruction methods. It offers a similar quality
as fully sampled analytical reconstruction, yet requires as few as 25 projections for CT and
a 30% sampling rate for MRI. It is concluded that structural similarities and correlations
residing in images from different modalities are useful to mutually promote the quality of
image reconstruction.<br>Ph. D.<br>Medical imaging techniques play a central role in modern clinical diagnoses and treatments. Consequently, there is a constant demand to increase the overall quality of medical images. Since their inception, multimodal imaging techniques have received a great deal of attention for achieving enhanced imaging performance. Multimodal imaging techniques can provide more detailed diagnostic information by fusing medical images from different imaging modalities, thereby allowing clinical results to be more comprehensive to improve clinical interpretation. A new form of multimodal imaging technique, which combines the imaging procedures of computed tomography (CT) and magnetic resonance imaging (MRI), is known as the “omnitomography.” Both computed tomography and magnetic resonance imaging are the most commonly used medical imaging techniques today and their intrinsic properties are complementary. For example, computed tomography performs well for bones whereas the magnetic resonance imaging excels at contrasting soft tissues. Therefore, a multimodal imaging system built upon the fusion of these two modalities can potentially bring much more information to improve clinical diagnoses. However, the planned omni-tomography systems face enormous challenges, such as the limited ability to perform image reconstruction due to mechanical and hardware restrictions that result in significant undersampling of the raw data. Image reconstruction is a procedure required by both computed tomography and magnetic resonance imaging to convert raw data into final images. A general condition required to produce a decent quality of an image is that the number of samples of raw data must be sufficient and abundant. Therefore, undersampling on the omni-tomography system can cause significant degradation of the image quality or artifacts after image reconstruction. To overcome this drawback, we resort to compressed sensing techniques, which exploit the sparsity of the medical images, to perform iterative based image reconstruction for both computed tomography and magnetic resonance imaging. The sparsity of the images is found by applying sparse transform such as discrete gradient transform or wavelet transform in the image domain. With the sparsity and undersampled raw data, an iterative algorithm can largely compensate for the data inadequacy problem and it can reconstruct the final images from the undersampled raw data with minimal loss of quality. In addition, a novel “projection distance” is created to perform a joint reconstruction which further promotes the quality of the reconstructed images. Specifically, the projection distance exploits the structural similarities shared between the image of computed tomography and magnetic resonance imaging such that the insufficiency of raw data caused by undersampling is further accounted for. The improved performance of the proposed approach is demonstrated using a pair of undersampled body images and a pair of undersampled head images, each of which consists of an image of computed tomography and its magnetic resonance imaging counterpart. These images are tested using the proposed joint reconstruction method in this work, the conventional reconstructions such as filtered backprojection and Fourier transform, and reconstruction strategy without using multimodal imaging information (independent reconstruction). The results from this work show that the proposed method addressed these challenges by significantly improving the image quality from highly undersampled raw data. In particular, it improves about 5dB in signal-to-noise ratio and nearly 10% in structural similarity measurements compared to other methods. It achieves similar image quality by using less than 5% of the X-ray dose for computed tomography and 30% sampling rate for magnetic resonance imaging. It is concluded that, by using compressed sensing techniques and exploiting structural similarities, the planned joint computed tomography and magnetic resonance imaging system can perform imaging outstanding tasks with highly undersampled raw data.
3
Carmo, Bernardo S. "Image processing in echography and MRI." Thesis, University of Southampton, 2005. https://eprints.soton.ac.uk/194557/.
Full textAbstract:
This work deals with image processing for three medical imaging applications: speckle detection in 3D ultrasound, left ventricle detection in cardiac magnetic resonance imaging (MRI) and flow feature visualisation in velocity MRI. For speckle detection, a learning from data approach was taken using pattern recognition principles and low-level image features, including signal-to-noise ratio, co-occurrence matrix, asymmetric second moment, homodyned k-distribution and a proposed specklet detector. For left ventricle detection, template matching was used. Forvortex detection, a data processing framework is presented that consists of three main steps: restoration, abstraction and tracking. This thesis addresses the first two problems, implementing restoration with a total variation first order Lagrangian method, and abstraction with clustering and local linear expansion.
4
Gu, Wei Q. "Automated tracer-independent MRI/PET image registration." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ29596.pdf.
Full text
5
Ivarsson, Magnus. "Evaluation of 3D MRI Image Registration Methods." Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-139075.
Full textAbstract:
Image registration is the process of geometrically deforming a template image into a reference image. This technique is important and widely used within thefield of medical IT. The purpose could be to detect image variations, pathologicaldevelopment or in the company AMRA’s case, to quantify fat tissue in variousparts of the human body.From an MRI (Magnetic Resonance Imaging) scan, a water and fat tissue image isobtained. Currently, AMRA is using the Morphon algorithm to register and segment the water image in order to quantify fat and muscle tissue. During the firstpart of this master thesis, two alternative registration methods were evaluated.The first algorithm was Free Form Deformation which is a non-linear parametricbased method. The second algorithm was a non-parametric optical flow basedmethod known as the Demon algorithm. During the second part of the thesis,the Demon algorithm was used to evaluate the effect of using the fat images forregistrations.
6
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 hippocampe<br>The 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
7
Soltaninejad, Mohammadreza. "Supervised learning-based multimodal MRI brain image analysis." Thesis, University of Lincoln, 2017. http://eprints.lincoln.ac.uk/30883/.
Full textAbstract:
Medical imaging plays an important role in clinical procedures related to cancer, such as diagnosis, treatment selection, and therapy response evaluation. Magnetic resonance imaging (MRI) is one of the most popular acquisition modalities which is widely used in brain tumour analysis and can be acquired with different acquisition protocols, e.g. conventional and advanced. Automated segmentation of brain tumours in MR images is a difficult task due to their high variation in size, shape and appearance. Although many studies have been conducted, it still remains a challenging task and improving accuracy of tumour segmentation is an ongoing field. The aim of this thesis is to develop a fully automated method for detection and segmentation of the abnormal tissue associated with brain tumour (tumour core and oedema) from multimodal MRI images. In this thesis, firstly, the whole brain tumour is segmented from fluid attenuated inversion recovery (FLAIR) MRI, which is commonly acquired in clinics. The segmentation is achieved using region-wise classification, in which regions are derived from superpixels. Several image features including intensity-based, Gabor textons, fractal analysis and curvatures are calculated from each superpixel within the entire brain area in FLAIR MRI to ensure a robust classification. Extremely randomised trees (ERT) classifies each superpixel into tumour and non-tumour. Secondly, the method is extended to 3D supervoxel based learning for segmentation and classification of tumour tissue subtypes in multimodal MRI brain images. Supervoxels are generated using the information across the multimodal MRI data set. This is then followed by a random forests (RF) classifier to classify each supervoxel into tumour core, oedema or healthy brain tissue. The information from the advanced protocols of diffusion tensor imaging (DTI), i.e. isotropic (p) and anisotropic (q) components is also incorporated to the conventional MRI to improve segmentation accuracy. Thirdly, to further improve the segmentation of tumour tissue subtypes, the machine-learned features from fully convolutional neural network (FCN) are investigated and combined with hand-designed texton features to encode global information and local dependencies into feature representation. The score map with pixel-wise predictions is used as a feature map which is learned from multimodal MRI training dataset using the FCN. The machine-learned features, along with hand-designed texton features are then applied to random forests to classify each MRI image voxel into normal brain tissues and different parts of tumour. The methods are evaluated on two datasets: 1) clinical dataset, and 2) publicly available Multimodal Brain Tumour Image Segmentation Benchmark (BRATS) 2013 and 2017 dataset. The experimental results demonstrate the high detection and segmentation performance of the III single modal (FLAIR) method. The average detection sensitivity, balanced error rate (BER) and the Dice overlap measure for the segmented tumour against the ground truth for the clinical data are 89.48%, 6% and 0.91, respectively; whilst, for the BRATS dataset, the corresponding evaluation results are 88.09%, 6% and 0.88, respectively. The corresponding results for the tumour (including tumour core and oedema) in the case of multimodal MRI method are 86%, 7%, 0.84, for the clinical dataset and 96%, 2% and 0.89 for the BRATS 2013 dataset. The results of the FCN based method show that the application of the RF classifier to multimodal MRI images using machine-learned features based on FCN and hand-designed features based on textons provides promising segmentations. The Dice overlap measure for automatic brain tumor segmentation against ground truth for the BRATS 2013 dataset is 0.88, 0.80 and 0.73 for complete tumor, core and enhancing tumor, respectively, which is competitive to the state-of-the-art methods. The corresponding results for BRATS 2017 dataset are 0.86, 0.78 and 0.66 respectively. The methods demonstrate promising results in the segmentation of brain tumours. This provides a close match to expert delineation across all grades of glioma, leading to a faster and more reproducible method of brain tumour detection and delineation to aid patient management. In the experiments, texton has demonstrated its advantages of providing significant information to distinguish various patterns in both 2D and 3D spaces. The segmentation accuracy has also been largely increased by fusing information from multimodal MRI images. Moreover, a unified framework is present which complementarily integrates hand-designed features with machine-learned features to produce more accurate segmentation. The hand-designed features from shallow network (with designable filters) encode the prior-knowledge and context while the machine-learned features from a deep network (with trainable filters) learn the intrinsic features. Both global and local information are combined using these two types of networks that improve the segmentation accuracy.
8
Daga, P. "Towards efficient neurosurgery : image analysis for interventional MRI." Thesis, University College London (University of London), 2014. http://discovery.ucl.ac.uk/1449559/.
Full textAbstract:
Interventional magnetic resonance imaging (iMRI) is being increasingly used for performing imageguided neurosurgical procedures. Intermittent imaging through iMRI can help a neurosurgeon visualise the target and eloquent brain areas during neurosurgery and lead to better patient outcome. MRI plays an important role in planning and performing neurosurgical procedures because it can provide highresolution anatomical images that can be used to discriminate between healthy and diseased tissue, as well as identify location and extent of functional areas. This is of significant clinical utility as it helps the surgeons maximise target resection and avoid damage to functionally important brain areas. There is clinical interest in propagating the pre-operative surgical information to the intra-operative image space as this allows the surgeons to utilise the pre-operatively generated surgical plans during surgery. The current state of the art neuronavigation systems achieve this by performing rigid registration of pre-operative and intra-operative images. As the brain undergoes non-linear deformations after craniotomy (brain shift), the rigidly registered pre-operative images do not accurately align anymore with the intra-operative images acquired during surgery. This limits the accuracy of these neuronavigation systems and hampers the surgeon’s ability to perform more aggressive interventions. In addition, intra-operative images are typically of lower quality with susceptibility artefacts inducing severe geometric and intensity distortions around areas of resection in echo planar MRI images, significantly reducing their utility in the intraoperative setting. This thesis focuses on development of novel methods for an image processing workflow that aims to maximise the utility of iMRI in neurosurgery. I present a fast, non-rigid registration algorithm that can leverage information from both structural and diffusion weighted MRI images to localise target lesions and a critical white matter tract, the optic radiation, during surgical management of temporal lobe epilepsy. A novel method for correcting susceptibility artefacts in echo planar MRI images is also developed, which combines fieldmap and image registration based correction techniques. The work developed in this thesis has been validated and successfully integrated into the surgical workflow at the National Hospital for Neurology and Neurosurgery in London and is being clinically used to inform surgical decisions.
9
Chi, Wenjun. "MRI image analysis for abdominal and pelvic endometriosis." Thesis, University of Oxford, 2012. http://ora.ox.ac.uk/objects/uuid:27efaa89-85cd-4f8b-ab67-b786986c42e3.
Full textAbstract:
Endometriosis is an oestrogen-dependent gynaecological condition defined as the presence of endometrial tissue outside the uterus cavity. The condition is predominantly found in women in their reproductive years, and associated with significant pelvic and abdominal chronic pain and infertility. The disease is believed to affect approximately 33% of women by a recent study. Currently, surgical intervention, often laparoscopic surgery, is the gold standard for diagnosing the disease and it remains an effective and common treatment method for all stages of endometriosis. Magnetic resonance imaging (MRI) of the patient is performed before surgery in order to locate any endometriosis lesions and to determine whether a multidisciplinary surgical team meeting is required. In this dissertation, our goal is to use image processing techniques to aid surgical planning. Specifically, we aim to improve quality of the existing images, and to automatically detect bladder endometriosis lesion in MR images as a form of bladder wall thickening. One of the main problems posed by abdominal MRI is the sparse anisotropic frequency sampling process. As a consequence, the resulting images consist of thick slices and have gaps between those slices. We have devised a method to fuse multi-view MRI consisting of axial/transverse, sagittal and coronal scans, in an attempt to restore an isotropic densely sampled frequency plane of the fused image. In addition, the proposed fusion method is steerable and is able to fuse component images in any orientation. To achieve this, we apply the Riesz transform for image decomposition and reconstruction in the frequency domain, and we propose an adaptive fusion rule to fuse multiple Riesz-components of images in different orientations. The adaptive fusion is parameterised and switches between combining frequency components via the mean and maximum rule, which is effectively a trade-off between smoothing the intrinsically noisy images while retaining the sharp delineation of features. We first validate the method using simulated images, and compare it with another fusion scheme using the discrete wavelet transform. The results show that the proposed method is better in both accuracy and computational time. Improvements of fused clinical images against unfused raw images are also illustrated. For the segmentation of the bladder wall, we investigate the level set approach. While the traditional gradient based feature detection is prone to intensity non-uniformity, we present a novel way to compute phase congruency as a reliable feature representation. In order to avoid the phase wrapping problem with inverse trigonometric functions, we devise a mathematically elegant and efficient way to combine multi-scale image features via geometric algebra. As opposed to the original phase congruency, the proposed method is more robust against noise and hence more suitable for clinical data. To address the practical issues in segmenting the bladder wall, we suggest two coupled level set frameworks to utilise information in two different MRI sequences of the same patients - the T2- and T1-weighted image. The results demonstrate a dramatic decrease in the number of failed segmentations done using a single kind of image. The resulting automated segmentations are finally validated by comparing to manual segmentations done in 2D.
10
Hagio, Tomoe, and Tomoe Hagio. "Parametric Mapping and Image Analysis in Breast MRI." Diss., The University of Arizona, 2016. http://hdl.handle.net/10150/621809.
Full textAbstract:
Breast cancer is the most common and the second most fatal cancer among women in the U.S. Current knowledge indicates that there is a relationship between high breast density (measured by mammography) and increased breast cancer risk. However, the biology behind this relationship is not well understood. This may be due to the limited information provided by mammography which only yields information on the relative amount of fibroglandular to adipose tissue in the breast. In our studies, breast density is assessed using quantitative MRI, in which MRI-based tissue-dependent parameters are derived voxel-wise by mathematically modeling the acquired MRI signals. Specifically, we use data from a radial gradient- and spin-echo imaging technique, previously developed in our group, to assess fat fraction and T₂ of the water component in relation to breast density. In addition, we use diffusion-weighted imaging to obtain another parameter, apparent diffusion coefficient (ADC) of the water component in the breast. Each parametric map provides a different type of information: fat fraction gives the amount of fat present in the voxel, the T₂ of water spin relaxation is sensitive to the water component in the tissue, and the ADC of water yields other type of information, such as tissue cellularity. The challenge in deriving these parameters from breast MRI data is the presence of abundant fat in the breast, which can cause artifacts in the images and can also affect the parameter estimation. We approached this problem by modifying the imaging sequence (as in the case of diffusion-weighted imaging) and by exploring new signal models that describe the MRI signal accounting for the presence of fat. In this work, we present the improvements made in the imaging sequence and in the parametric mapping algorithms using simulation and phantom experiments. We also present preliminary results in vivo in the context of breast density-related tissue characterization.
Books on the topic "MRI IMAGE"
2
Song, In-chʻan. MRI ŭi hwajil pʻyŏngka kisul kaebal =: Technology development of MRI image quality evaluation. Sikpʻum Ŭiyakpʻum Anjŏnchʻŏng, 2007.
Find full text
3
Afrin, Farhana. fMRI and MRI image registration and statistical mapping. VDM Verlag Dr. Müller, 2008.
Find full text
4
W, Bancroft Laura, and Bridges, Mellena D., M.D., eds. MRI normal variants and pitfalls. Lippincott Williams and Wilkins, 2009.
Find full text
5
Poldrack, Russell A. Handbook of functional MRI data analysis. Cambridge University Press, 2011.
Find full text
6
Ciulla, Carlo. Improved signal and image interpolation in biomedical applications: The case of magnetic resonance imaging (MRI). Medical Information Science Reference, 2009.
Find full text
8
1953-, Nitz Wolfgang R., and Schmeets Stuart H. 1971-, eds. The physics of MRI taught through images. 2nd ed. Thieme, 2009.
Find full text
10
Johansson, Ewa-Mari. Ewa-Mari Johansson: Image 2000-2008. Silvana editoriale, 2016.
Find full textBook chapters on the topic "MRI IMAGE"
1
Ashburner, J., and K. J. Friston. "Image Registration." In Functional MRI. Springer Berlin Heidelberg, 2000. http://dx.doi.org/10.1007/978-3-642-58716-0_26.
Full text
2
Zeng, Gengsheng Lawrence. "MRI Reconstruction." In Medical Image Reconstruction. Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-05368-9_7.
Full text
3
Rajan, Sunder S. "Image Contrast and Pulse Sequences." In MRI. Springer New York, 1998. http://dx.doi.org/10.1007/978-1-4612-1632-2_4.
Full text
4
English, Philip T., and Christine Moore. "Image Production." In MRI for Radiographers. Springer London, 1995. http://dx.doi.org/10.1007/978-1-4471-3403-9_4.
Full text
5
English, Philip T., and Christine Moore. "Image Quality." In MRI for Radiographers. Springer London, 1995. http://dx.doi.org/10.1007/978-1-4471-3403-9_5.
Full text
6
English, Philip T., and Christine Moore. "Image Artifacts." In MRI for Radiographers. Springer London, 1995. http://dx.doi.org/10.1007/978-1-4471-3403-9_6.
Full text
7
Murray, Rachel, and Natasha Werpy. "Image interpretation and artefacts." In Equine MRI. John Wiley & Sons, Ltd, 2016. http://dx.doi.org/10.1002/9781118786574.ch4.
Full text
8
Qu, Liangqiong, Yongqin Zhang, Zhiming Cheng, Shuang Zeng, Xiaodan Zhang, and Yuyin Zhou. "Multimodality MRI Synthesis." In Medical Image Synthesis. CRC Press, 2023. http://dx.doi.org/10.1201/9781003243458-14.
Full text
9
Weishaupt, Dominik, Victor D. Köchli, and Borut Marincek. "Image Contrast." In How does MRI work? Springer Berlin Heidelberg, 2003. http://dx.doi.org/10.1007/978-3-662-07805-1_3.
Full text
10
Ahrar, Kamran, and R. Jason Stafford. "MRI-Guided Biopsy." In Percutaneous Image-Guided Biopsy. Springer New York, 2013. http://dx.doi.org/10.1007/978-1-4614-8217-8_5.
Full textConference papers on the topic "MRI IMAGE"
1
Yoon, Jongyeon, Elyssa M. McMaster, Chloe Cho, Kurt G. Schilling, Bennett A. Landman, and Daniel Moyer. "Tractography enhancement in clinically-feasible diffusion MRI using T1-weighted MRI and anatomical context." In Image Processing, edited by Olivier Colliot and Jhimli Mitra. SPIE, 2025. https://doi.org/10.1117/12.3047112.
Full text
2
Soomro, Toufique Ahmed, Mahaveer Rathi, Shafique Ahmed Soomro, Muhammad Usman Keerio, Pardeep Kumar, and Enrique Nava Baro. "Image Enhancement Technique for MRI Brain Images." In 2024 Global Conference on Wireless and Optical Technologies (GCWOT). IEEE, 2024. https://doi.org/10.1109/gcwot63882.2024.10805684.
Full text
3
Rivas, Carlos A., Jinwei Zhang, Shuwen Wei, Samuel W. Remedios, Aaron Carass, and Jerry L. Prince. "Unique MS lesion identification from MRI." In Image Processing, edited by Olivier Colliot and Jhimli Mitra. SPIE, 2025. https://doi.org/10.1117/12.3047269.
Full text
4
Wang, Kun, Aobo Jin, Hongchun Guo, et al. "Low Field MRI Image Synthesis." In 2025 IEEE 4th International Conference on AI in Cybersecurity (ICAIC). IEEE, 2025. https://doi.org/10.1109/icaic63015.2025.10849188.
Full text
5
S, Meharban M., Sabu M. K, and T. Santhanakrishnan. "T1W MRI to T2W MRI Image Synthesis Using SSIM-CycleGAN." In 2024 11th International Conference on Advances in Computing and Communications (ICACC). IEEE, 2024. https://doi.org/10.1109/icacc63692.2024.10845374.
Full text
6
Faghihpirayesh, Razieh, Xueqi Guo, Matthias M. Wolf, Kaman Chung, and Mohammad Abdi. "Deep-learning framework for analysis of longitudinal MRI studies." In Image Processing, edited by Olivier Colliot and Jhimli Mitra. SPIE, 2025. https://doi.org/10.1117/12.3047794.
Full text
7
Li, Tong, Anran Liu, David Kügler, and Martin Reuter. "Boost the adversarial learning with Fourier regulator: bias-field correction on MRI." In Image Processing, edited by Olivier Colliot and Jhimli Mitra. SPIE, 2025. https://doi.org/10.1117/12.3047299.
Full text
8
Yao, Tianyuan, Zhiyuan Li, Praitayini Kanakaraj, et al. "Polyhedra encoding transformers: enhancing diffusion MRI analysis beyond voxel and volumetric embedding." In Image Processing, edited by Olivier Colliot and Jhimli Mitra. SPIE, 2025. https://doi.org/10.1117/12.3047244.
Full text
9
Xu, Di, Xin Miao, Hengjie Liu, et al. "Rapid reconstruction of extremely accelerated liver 4D MRI via chained iterative refinement." In Image Processing, edited by Olivier Colliot and Jhimli Mitra. SPIE, 2025. https://doi.org/10.1117/12.3034640.
Full text
10
Yu, Tian, Yunhe Li, Michael E. Kim, et al. "Tractography with T1-weighted MRI and associated anatomical constraints on clinical quality diffusion MRI." In Image Processing, edited by Olivier Colliot and Jhimli Mitra. SPIE, 2024. http://dx.doi.org/10.1117/12.3006286.
Full textReports on the topic "MRI IMAGE"
1
DSC-MRI Consensus QIBA Profile. Chair Ona Wu, Mark Shiroishi, and Leland Hu. Radiological Society of North America (RSNA)/Quantitative Imaging Biomarkers Alliance (QIBA), 2020. https://doi.org/10.1148/qiba/20201022.
Full textAbstract:
The goal of a QIBA Profile is to help achieve a useful level of performance for a given biomarker. Profile development is an evolutionary, phased process; this Profile is in the Public Comment Resolution Draft stage. The performance claims represent expert consensus and will be empirically demonstrated at a subsequent stage. Users of this Profile are encouraged to refer to the following site to understand the document’s context: http://qibawiki.rsna.org/index.php/QIBA_Profile_Stages. The Claim (Section 2) describes the biomarker performance. The Activities (Section 3) contribute to generating the biomarker. Requirements are placed on the Actors that participate in those activities as necessary to achieve the Claim. Assessment Procedures (Section 4) for evaluating specific requirements are defined as needed. Conformance (Section 5) regroups Section 3 requirements by Actor to conveniently check Conformance. This QIBA Profile, Dynamic-Susceptibility-Contrast Magnetic Resonance Imaging (DSC-MRI), addresses the measurement of an imaging biomarker for relative Cerebral Blood Volume (rCBV) for the evaluation of brain tumor progression or response to therapy. We note here, that this profile does not claim to be measuring quantitative rCBV due to lack of existing supporting literature; it does provide claims for a biomarker that is proportional to rCBV, which is the tissue-normalized first-pass area under the contrast-agent concentration curve (AUC-TN). The AUC-TN therefore has merit as a potential biomarker for diseases or treatments that impact rCBV. This profile places requirements on Sites, Acquisition Devices, Contrast Injectors, Contrast Media, Radiologists, Physicists, Technologists, Reconstruction Software, Image Analysis Tools and Image Analysts involved in Site Conformance, Staff Qualification, Product Validation, Pre-delivery, Periodic QA, Protocol Design, Subject Handling, Image Data Acquisition, Image Data Reconstruction, Image QA, Image Distribution, Image Analysis and Image Interpretation. The requirements are focused on achieving known (ideally negligible) bias and avoiding unnecessary variability of the of the AUC-TN measurements. The clinical performance is characterized by a 95% confidence interval for the AUC-TN true change (Y2-Y1) in enhancing tumor tissue (𝑌−𝑌)±1.96× (𝑌×0.31) +(𝑌×0.31) and in normal tissue (𝑌−𝑌)±1.96× (𝑌×0.40) +(𝑌×0.40), where Y1 is the baseline measurement and Y2 is the follow-up measurement. These estimates are based on current literature values but may be updated based on future studies (see Section 2.2 for details). This document is intended to help clinicians basing decisions on this biomarker, imaging staff generating this biomarker, vendor staff developing related products, purchasers of such products and investigators designing trials with imaging endpoints. Note that this document only states requirements to achieve the claim, not “requirements on standard of care.” Conformance to this Profile is secondary to properly caring for the patient. QIBA Profiles addressing other imaging biomarkers using CT, MRI, PET and Ultrasound can be found at qibawiki.rsna.org.
2
MRI-Based PDFF of the Liver, Consensus QIBA Profile. Chair Diego Hernando and Houchun (Harry) Hu. Radiological Society of North America (RSNA)/Quantitative Imaging Biomarkers Alliance (QIBA), 2024. https://doi.org/10.1148/qiba/20240619.
Full textAbstract:
A QIBA Profile is an implementation guide to generate a biomarker with an effective level of performance, mostly by reducing variability and bias in the measurement. The expected performance is expressed as Claims (Section 1.2). To achieve those claims, Actors, both human and equipment, (for example: scanners, data acquisition parameters, data reconstruction software and algorithms, image analysis tools, technologists and radiographers, medical physicists, radiologists) must meet the Checklist Requirements (Section 3) covering Periodic QA, Subject Handling, Image Data Acquisition, Image Data Reconstruction, Image QA, and Image Analysis. This Profile is at the Initial Draft stage (qibawiki.rsna.org/index.php/QIBA_Profile_Stages) so, Claim Confirmed: The requirements have been performed and found to be practical by multiple sites; The claim is verified in a multi-site, multi-vendor study; results are expected to be generalizable in similar settings. Technically Confirmed: The requirements have been performed and found to be practical by multiple sites; The claim is a hypothesis based on committee assessment of literature and QIBA groundwork. QIBA Profiles for other CT, MRI, PET, and Ultrasound biomarkers can be found at qibawiki.rsna.org. Consensus: The requirements are believed to be practical based on consensus of experts within and beyond the committee; The claim is a hypothesis based on committee assessment of literature and QIBA groundwork. This document is intended to help clinicians and researchers basing decisions on this biomarker, imaging staff generating this biomarker, vendor staff developing related products, purchasers of such products and investigators designing trials with imaging endpoints. Note that this document only states requirements to achieve the claim, not “requirements on standard of care.” Conformance to this Profile is secondary to properly caring for the patient.
3
Yang, Xiaofeng, Tian Liu, Jani Ashesh, Hui Mao, and Walter Curran. Fusion of Ultrasound Tissue-Typing Images with Multiparametric MRI for Image-guided Prostate Cancer Radiation Therapy. Defense Technical Information Center, 2014. http://dx.doi.org/10.21236/ada622473.
Full text
4
CT Tumor Volume Change for Advanced Disease, Clinically Feasible Profile. Chair Ritu Gill, Rudresh Jarecha, and Ehsan Samei. Radiological Society of North America (RSNA) / Quantitative Imaging Biomarkers Alliance (QIBA), 2022. http://dx.doi.org/10.1148/qiba/20220721.
Full textAbstract:
A QIBA Profile is an implementation guide to generate a biomarker with an effective level of performance, mostly by reducing variability and bias in the measurement. The expected performance is expressed as Claims (Section 1.2). To achieve those claims, Actors (Scanners, Technologists, Physicists, Radiologists, Reconstruction Software, and Image Analysis Tools) must meet the Checklist Requirements (Section 3) covering Periodic QA, Subject Handling, Image Data Acquisition, Image Data Reconstruction, Image QA, and Image Analysis. This Profile is at the Clinically Feasible stage (qibawiki.rsna.org/index.php/QIBA_Profile_Stages) so, *The requirements have been performed and found to be practical by multiple sites *The claim is a hypothesis based on committee assessment of literature and QIBA groundwork CT Tumor Volume Change is used as a biomarker of disease risk, characterization, progression, and response to treatment. This involves measuring tumor volumes and assessing longitudinal changes within subjects, based on image processing of CT scans acquired at different timepoints. See Appendix B for a discussion of usage of this biomarker in practice. QIBA Profiles for other CT, MRI, PET, and Ultrasound biomarkers can be found at qibawiki.rsna.org
5
Pepin, Kay, ed. MR Elastography of the Liver, Clinically Feasible Profile. Chair Richard Ehman and Patricia Cole. Radiological Society of North America (RSNA) / Quantitative Imaging Biomarkers Alliance (QIBA), 2023. http://dx.doi.org/10.1148/qiba/20231107.
Full textAbstract:
The goal of a QIBA Profile is to help achieve a useful level of performance for a given biomarker. The Claim (Section 2) describes the biomarker performance. The Activities (Section 3) contribute to generating the biomarker. Requirements are placed on the Actors that participate in those activities as necessary to achieve the Claim. Assessment Procedures (Section 4) for evaluating specific requirements are defined as needed. This QIBA Profile (Magnetic Resonance Elastography of the Liver) addresses the application of Magnetic Resonance Elastography (MRE) for the quantification of liver stiffness, which is often used as a biomarker of liver fibrosis. It places requirements on Acquisition Devices, Technologists, Radiologists, Reconstruction Software and Image Analysis Tools involved in Subject Handling, Image Data Acquisition, Image Data Reconstruction, Image QA and Image Analysis. The requirements are focused on achieving sufficient accuracy and avoiding unnecessary variability of the measurement of hepatic stiffness. The clinical performance target is to achieve a 95% confidence interval for a true change in stiffness has occurred when there is a measured change in hepatic stiffness of 19% or larger. This document is intended to help clinicians basing decisions on this biomarker, imaging staff generating this biomarker, vendor staff developing related products, purchasers of such products and investigators designing trials with imaging endpoints. Note that this document only states requirements to achieve the claim, not “requirements on standard of care.” Conformance to this Profile is secondary to properly caring for the patient. QIBA Profiles addressing other imaging biomarkers using CT, MRI, PET and Ultrasound can be found at https://qibawiki.rsna.org/index.php/Profiles
6
MR (Diffusion-Weighted Imaging (DWI) of the Apparent Diffusion Coefficient (ADC), Clinically Feasible Profile. Chair Michael Boss, Dariya Malyarenko, and Daniel Margolis. Radiological Society of North America (RSNA) / Quantitative Imaging Biomarkers Alliance (QIBA), 2022. http://dx.doi.org/10.1148/qiba/20221215.
Full textAbstract:
The goal of a QIBA Profile is to help achieve a useful level of performance for a given biomarker. The Claim (Section 2) describes the biomarker performance and is derived from the body of scientific literature meeting specific requirements, in particular test-retest studies. The Activities (Section 3) contribute to generating the biomarker. Requirements are placed on the Actors that participate in those activities as necessary to achieve the Claim. Assessment Procedures (Section 4) for evaluating specific requirements are defined as needed to ensure acceptable performance. Diffusion-Weighted Imaging (DWI) and the Apparent Diffusion Coefficient (ADC) are being used clinically as qualitative (DWI) and quantitative (ADC) indicators of disease presence, progression or response to treatment. Use of ADC as a robust quantitative biomarker with finite confidence intervals places additional requirements on Sites, Acquisition Devices and Protocols, Field Engineers, Scanner Operators (MR Technologists, Radiologists, Physicists and other Scientists), Image Analysts, Reconstruction Software and Image Analysis Tools. Additionally, due to the intrinsic dependence of measured ADC values on biophysical tissue properties, both the Profile Claims and the associated scan protocols (Section 3.6.2) are organ-specific. All of these are considered Actors involved in Activities of Acquisition Device Pre-delivery and Installation, Subject Handling, Image Data Acquisition, Reconstruction, Registration, ADC map generation, Quality Assurance (QA), Distribution, Analysis, and Interpretation. The requirements addressed in this Profile are focused on achieving ADC values with minimal systematic bias and measurement variability. DISCLAIMER: Technical performance of the MRI system can be assessed using a phantom having known diffusion properties, such as the QIBA DWI phantom. The clinical performance target is to achieve a 95% confidence interval for measurement of ADC with a variable precision depending on the organ being imaged and assuming adequate technical performance requirements are met. While in vivo DWI/ADC measurements have been performed throughout the human body, this Profile focused on four organ systems, namely brain, liver, prostate, and breast as having high clinical utilization of ADC with a sufficient level of statistical evidence to support the Profile Claims derived from the current peer-reviewed literature. In due time, new DWI technologies with proven greater performance levels, as well as more organ systems will be incorporated in future Profiles. This document is intended to help a variety of users: clinicians using this biomarker to aid patient management; imaging staff generating this biomarker; MRI system architects developing related products; purchasers of such products; and investigators designing clinical trials utilizing quantitative diffusion-based imaging endpoints. Note that this document only states requirements specific to DWI to achieve the claim, not requirements that pertain to clinical standard of care. Conforming to this Profile is secondary to proper patient care.
7
Ultrasound Volume Blood Flow, Consensus QIBA Profile. Chair J. Brian Fowlkes, James Jago, and Oliver Kripfgans. American Institute of Ultrasound in Medicine (AIUM)/Radiological Society of North America (RSNA)/Quantitative Imaging Biomarkers Alliance (QIBA), 2024. https://doi.org/10.1148/qiba/20240105.
Full textAbstract:
A QIBA Profile is an implementation guide to generate a biomarker with an effective level of performance, mostly by reducing variability and bias in the measurement. The expected performance is expressed as Claims (Section 1.2). To achieve those claims, Actors (Manufacturers/Vendors/Field Service Engineers, Sonographers/Technologists, Physicians, Physicist/Clinical Engineer/QA manager, and Image Analysis Tools) must meet the Checklist Requirements (Section 3) covering Product Validation, Staff Qualification, Pre-delivery, Installation, Periodic QA, Subject Handling, Image Data Acquisition, Image QA, and Image Analysis. This Profile is at the Public Comment stage (qibawiki.rsna.org/index.php/QIBA_Profile_Stages) so, The requirements are believed to be practical by the committee. Simplifications will be considered for future versions of the profile. The claim is a hypothesis based on committee assessment of literature and QIBA groundwork QIBA Profiles for other CT, MRI, PET, and Ultrasound biomarkers can be found at qibawiki.rsna.org. This QIBA Profile (US Volume Blood Flow) addresses volumetric blood flow (volume of blood passing through a given vessel per unit time), which can be used as a biomarker of normal/abnormal physiologic conditions, disease progression or response to therapy. The requirements are focused on achieving sufficient accuracy and avoiding unnecessary variability of volume blood flow measurements. In addition, traditional methods for volume flow using 2D imaging and spectral Doppler ultrasound measurements have not been widely used due to high variability, implicit assumptions, and high user interaction requirements.
8
MR MSK Cartilage for Joint Disease, Consensus Profile. Chair Thomas Link and Xiaojuan Li. Radiological Society of North America (RSNA) / Quantitative Imaging Biomarkers Alliance (QIBA), 2021. http://dx.doi.org/10.1148/qiba/20210925.
Full textAbstract:
The goal of a QIBA Profile is to help achieve a useful level of performance for a given biomarker. The Claim (Section 2) describes the biomarker performance. The Activities (Section 3) contribute to generating the biomarker. Requirements are placed on the Actors that participate in those activities as necessary to achieve the Claim. Assessment Procedures (Section 4) for evaluating specific requirements are defined as needed. This QIBA Profile (MR-based cartilage compositional biomarkers (T1ρ, T2) ) addresses the application of T1ρ and T2 for the quantification of cartilage composition, which can be used as an imaging biomarker to diagnose, predict and monitor early osteoarthritis. It places requirements on Acquisition Devices, Technologists, MRI Physicists, Radiologists, Reconstruction Software and Image Analysis Tools involved in Subject Handling, Image Data Acquisition, Image Data Reconstruction, Image Quality Assurance (QA) and Image Analysis. The requirements are focused on achieving sufficient reproducibility and accuracy for measuring cartilage composition. The clinical performance target is to achieve a reproducibility of 4-5% for measurements of global cartilage composition with T2 and T1ρ relaxation time measurements and a 95% confidence level for a true/critical change in cartilage composition (least significant change) with a precision of 11-14% and 9-12% if only an increase is expected (claim is one-sided). The target applies to 3T MR scanners of one manufacturer with identical scan parameters across different sites. It does not apply to scanners from different manufacturers. This document is intended to help clinicians basing decisions on this biomarker, imaging staff generating this biomarker, vendor staff developing related products, purchasers of such products and investigators designing trials with imaging endpoints. Note that this document only states requirements to achieve the claim, not “requirements on standard of care.” Conformance to this Profile is secondary to properly caring for the patient. Summary for Clinical Trial Use The MR-based cartilage compositional biomarkers profile defines the behavioral performance levels and quality control specifications for T1ρ, T2 scans used in single- and multi-center clinical trials of osteoarthritis and other trials assessing cartilage composition longitudinally with a focus on therapies to treat degenerative joint disease. While the emphasis is on clinical trials, this process is also intended to be applied for clinical practice. The specific claims for accuracy are detailed below in the Claims. The specifications that must be met to achieve conformance with this Profile correspond to acceptable levels specified in the T1ρ, T2 Protocols. The aim of the QIBA Profile specifications is to minimize intra- and inter-subject, intra- and inter-platform, and interinstitutional variability of quantitative scan data due to factors other than the intervention under investigation. T1ρ and T2 studies performed according to the technical specifications of this QIBA Profile in clinical trials can provide quantitative data for single timepoint assessments (e.g. disease burden, investigation of predictive and/or prognostic biomarker(s)) and/or for multi-time-point comparative assessments (e.g., response assessment, investigation of predictive and/or prognostic biomarkers of treatment efficacy). A motivation for the development of this Profile is that while a typical MR T1ρ and T2 measurement may be stable over days or weeks, this stability cannot be expected over the time that it takes to complete a clinical trial. In addition, there are well known differences between scanners and the operation of the same type of scanner at different imaging sites. The intended audiences of this document include: Biopharmaceutical companies, rheumatologists and orthopedic surgeons, and clinical trial scientists designing trials with imaging endpoints. Clinical research professionals. Radiologists, technologists, physicists and administrators at healthcare institutions considering specifications for procuring new MRI equipment for cartilage measurements. Radiologists, technologists, and physicists designing T1ρ and T2 acquisition protocols. Radiologists, and other physicians making quantitative measurements from T1ρ and T2 sequence protocols. Regulators, rheumatologists, orthopedic surgeons, and others making decisions based on quantitative image measurements. Technical staff of software and device manufacturers who create products for this purpose. Note that specifications stated as 'requirements' in this document are only requirements to achieve the claim, not 'requirements on standard of care.' Specifically, meeting the goals of this Profile is secondary to properly caring for the patient.
9
Atherosclerosis Biomarkers by Computed Tomography Angiography (CTA). Chair Andrew Buckler, Luca Saba, and Uwe Joseph Schoepf. Radiological Society of North America (RSNA) / Quantitative Imaging Biomarkers Alliance (QIBA), 2023. http://dx.doi.org/10.1148/qiba/20230328.
Full textAbstract:
The clinical application of Computed Tomography Angiography (CTA) is widely available as a technique to optimize the therapeutic approach to treating vascular disease. Evaluation of atherosclerotic arterial plaque characteristics is currently based on qualitative biomarkers. However, the reproducibility of such findings has historically been limited even among experts (1). Quantitative imaging biomarkers have been shown to have additive value above traditional qualitative imaging metrics and clinical risk scores regarding patient outcomes (2). However, many definitions and cut-offs are present in the current literature; therefore, standardization of quantitative evaluation of CTA datasets is needed before becoming a valuable tool in daily clinical practice. To establish these biomarkers in clinical practice, techniques are required to standardize quantitative imaging across different manufacturers with cross-calibration. Moreover, the post-processing of atherosclerotic plaque segmentation needs to be optimized and standardized. The goal of a Quantitative Imaging Biomarker Alliance (QIBA) Profile is to provide an implementation guide to generate a biomarker with an effective level of performance, mostly by reducing variability and bias in the measurement. The performance claims represent expert consensus and will be empirically demonstrated at a subsequent stage. Users of this Profile are encouraged to refer to the following site to understand the document’s context: http://qibawiki.rsna.org/index.php/QIBA_Profile_Stages. All statistical performance assessments are stated in carefully considered metrics and according to strict definitions as given in (3-8), which also includes detailed, peer-reviewed rationale on the importance of adhering to such standards. The expected performance is expressed as Claims (Section 1.2). To achieve those claims, Actors (Scanners, Reconstruction Software, Image Analysis Tools, Imaging Physicians, Physicists, and Technologists) must meet the Checklist Requirements (Section 3) covering Subject Handling, Image Data Acquisition, Image Data Reconstruction, Image QA, and Image Analysis. This Profile is at the Clinically Feasible stage (qibawiki.rsna.org/index.php/QIBA_Profile_Stages) which indicate that multiple sites have performed the Profile and found it to be practical and expect it to achieve the claimed performance. QIBA Profiles for other CT, MRI, PET, and Ultrasound biomarkers can be found at qibawiki.rsna.org
10
Saba, Luca, and Uwe Joseph Schoepf. Atherosclerosis Biomarkers by Computed Tomography Angiography (CTA) - Maintenance version June 2024. Chair Andrew Buckler. Radiological Society of North America (RSNA) / Quantitative Imaging Biomarkers Alliance (QIBA), 2024. http://dx.doi.org/10.1148/qiba/202406.
Full textAbstract:
The clinical application of Computed Tomography Angiography (CTA) is widely available as a technique to optimize the therapeutic approach to treating vascular disease. Evaluation of atherosclerotic arterial plaque characteristics is currently based on qualitative biomarkers. However, the reproducibility of such findings has historically been limited even among experts. Quantitative imaging biomarkers have been shown to have additive value above traditional qualitative imaging metrics and clinical risk scores regarding patient outcomes. However, many definitions and cut-offs are present in the current literature; therefore, standardization of quantitative evaluation of CTA datasets is needed before becoming a valuable tool in daily clinical practice. To establish these biomarkers in clinical practice, techniques are required to standardize quantitative imaging across different manufacturers with cross-calibration. Moreover, the post-processing of atherosclerotic plaque segmentation needs to be optimized and standardized. The goal of a Quantitative Imaging Biomarker Alliance (QIBA) Profile is to provide an implementation guide to generate a biomarker with an effective level of performance, mostly by reducing variability and bias in the measurement. The performance claims represent expert consensus and will be empirically demonstrated at a subsequent stage. Users of this Profile are encouraged to refer to the following site to understand the document’s context: http://qibawiki.rsna.org/index.php/QIBA_Profile_Stages. All statistical performance assessments are stated in carefully considered metrics and according to strict definitions as given in (3-8), which also includes detailed, peer-reviewed rationale on the importance of adhering to such standards. The expected performance is expressed as Claims (Section 1.2). To achieve those claims, Actors (Scanners, Reconstruction Software, Image Analysis Tools, Imaging Physicians, Physicists, and Technologists) must meet the Checklist Requirements (Section 3) covering Subject Handling, Image Data Acquisition, Image Data Reconstruction, Image QA, and Image Analysis. This Profile is at the Clinically Feasible stage (qibawiki.rsna.org/index.php/QIBA_Profile_Stages) which indicate that multiple sites have performed the Profile and found it to be practical and expect it to achieve the claimed performance. QIBA Profiles for other CT, MRI, PET, and Ultrasound biomarkers can be found at qibawiki.rsna.org.