Search

The brain relies heavily on consistent blood supply to prevent cerebral ischemia, with altered hemodynamics linked to a variety of conditions. Despite the detailed measurements of cerebrovascular flow provided by 4D Flow MRI, achieving accurate hemodynamic quantification necessitates labor-intensive manual data analysis. In this study, we propose a deep learning-based automated processing pipeline for intracranial artery labeling to streamline the post-processing of 4D Flow MRI data, framing the problem as a semantic segmentation task. The study evaluates different loss functions and network depths to enhance segmentation accuracy. The best performance was achieved using a hybrid loss function and a 6-layer U-Net model, yielding a Dice similarity coefficient (DSC) exceeding 89%. Experiments were conducted on a dataset of 18 patients, focusing on seven major cerebral vessels. The hybrid loss function combined Dice and cross-entropy losses, providing higher and more consistent segmentation accuracy compared to using either loss function alone. Increasing the network depth to 6 layers balanced complexity and spatial resolution, outperforming both shallower and deeper networks. The results demonstrate the feasibility of using convolutional neural networks for automatic cerebral vessel segmentation, showing high potential for streamlining cumbersome post-processing tasks in 4D Flow MRI data analysis by only requiring a vessel segmentation mask., Hjärnan är starkt beroende av en konsekvent blodtillförsel för att förhindra cerebral ischemi, och förändrad hemodynamik är kopplat till en mängd olika tillstånd. Trots att 4D Flow MRI kan ge detaljerade mätningar av cerebrovaskulärt flöde, kräver exakt hemodynamisk kvantifiering arbetsintensiv manuell dataanalys. I denna studie föreslår vi en djupinlärningsbaserad automatiserad bearbetningspipeline för märkning av intrakraniella artärer för att effektivisera behandlingen av 4D Flow MRI-data genom att betrakta problemet som ett semantiskt segmenteringsproblem. Studien utvärderar olika förlustfunktioner och nätverksdjup för att förbättra segmenteringsnoggrannheten. Den bästa prestandan uppnåddes med en hybrid förlustfunktion och en U-Net-modell med 6 lager, vilket gav en Dice similarity coefficient (DSC) över 89%. Experiment utfördes på ett dataset med 18 patienter, med fokus på sju stora cerebrala kärl. Den hybrida förlustfunktionen kombinerade Dice och korsentropiförluster, vilket gav större och mer konsekvent segmenteringsnoggrannhet jämfört med att använda vardera förlustfunktion för sig. Ökandet av nätverksdjup till 6 lager balanserade komplexitet och spatial upplösning, och presterade bättre än både grundare och djupare nätverk. Resultaten belyser möjligheten att använda konvolutionella neurala nätverk för automatisk segmentering av cerebrala kärl, och visar en stor potential för att effektivisera tidskrävande behandlingsuppgifter i 4D Flow MRI-data genom att endast kräva en kärlsegmenteringsmask.

The brain relies heavily on consistent blood supply to prevent cerebral ischemia, with altered hemodynamics linked to a variety of conditions. Despite the detailed measurements of cerebrovascular flow provided by 4D Flow MRI, achieving accurate hemodynamic quantification necessitates labor-intensive manual data analysis. In this study, we propose a deep learning-based automated processing pipeline for intracranial artery labeling to streamline the post-processing of 4D Flow MRI data, framing the problem as a semantic segmentation task. The study evaluates different loss functions and network depths to enhance segmentation accuracy. The best performance was achieved using a hybrid loss function and a 6-layer U-Net model, yielding a Dice similarity coefficient (DSC) exceeding 89%. Experiments were conducted on a dataset of 18 patients, focusing on seven major cerebral vessels. The hybrid loss function combined Dice and cross-entropy losses, providing higher and more consistent segmentation accuracy compared to using either loss function alone. Increasing the network depth to 6 layers balanced complexity and spatial resolution, outperforming both shallower and deeper networks. The results demonstrate the feasibility of using convolutional neural networks for automatic cerebral vessel segmentation, showing high potential for streamlining cumbersome post-processing tasks in 4D Flow MRI data analysis by only requiring a vessel segmentation mask., Hjärnan är starkt beroende av en konsekvent blodtillförsel för att förhindra cerebral ischemi, och förändrad hemodynamik är kopplat till en mängd olika tillstånd. Trots att 4D Flow MRI kan ge detaljerade mätningar av cerebrovaskulärt flöde, kräver exakt hemodynamisk kvantifiering arbetsintensiv manuell dataanalys. I denna studie föreslår vi en djupinlärningsbaserad automatiserad bearbetningspipeline för märkning av intrakraniella artärer för att effektivisera behandlingen av 4D Flow MRI-data genom att betrakta problemet som ett semantiskt segmenteringsproblem. Studien utvärderar olika förlustfunktioner och nätverksdjup för att förbättra segmenteringsnoggrannheten. Den bästa prestandan uppnåddes med en hybrid förlustfunktion och en U-Net-modell med 6 lager, vilket gav en Dice similarity coefficient (DSC) över 89%. Experiment utfördes på ett dataset med 18 patienter, med fokus på sju stora cerebrala kärl. Den hybrida förlustfunktionen kombinerade Dice och korsentropiförluster, vilket gav större och mer konsekvent segmenteringsnoggrannhet jämfört med att använda vardera förlustfunktion för sig. Ökandet av nätverksdjup till 6 lager balanserade komplexitet och spatial upplösning, och presterade bättre än både grundare och djupare nätverk. Resultaten belyser möjligheten att använda konvolutionella neurala nätverk för automatisk segmentering av cerebrala kärl, och visar en stor potential för att effektivisera tidskrävande behandlingsuppgifter i 4D Flow MRI-data genom att endast kräva en kärlsegmenteringsmask.

In the rapidly evolving field of medical imaging, the development of effective artificial intelligence systems requires both advanced deep learning algorithms and substantial, high-quality datasets. However, the acquisition and annotation of such data, particularly in specialized domains like clinical disease prognostics, is often prohibitively expensive and time-consuming. This research explores the potential of cross-domain self-supervised learning (CDSSL) as an innovative solution to these challenges, with a specific focus on enhancing Alzheimer's disease progression models using brain Magnetic Resonance Imaging (MRI) data. Our study introduces a novel CDSSL approach tailored for disease prognostic modeling, emphasizing regression tasks in medical imaging. Using Alzheimer's disease progression prediction from brain MRI as a case study, we demonstrate that self-supervised pretraining significantly improves prognostic accuracy. Notably, models pretrained on extended, unlabeled brain MRI datasets consistently outperform those using natural images, with an optimal combination of both data sources yielding the best results. Furthermore, we address the critical issue of data harmonization in medical imaging, investigating the impact of scanner-specific variations arising from diverse manufacturers and models. Our findings highlight CDSSL's potential in ensuring data consistency across different scanner environments, thereby enhancing data comparability and reproducibility. Specifically, we propose two methods Augmentation CDSSL and Auxiliary CDSSL, and show improved prognostic model and scanner variability reduction. Additionally, we compare our methods with an unsupervised harmonization model, demonstrating that our approach achieves better results in most of the datasets. This research underscores the significance of scanner-aware self-supervised learning in refining medical imaging methodologies, particularly in the context of Alzheimer's disease (AD) progression mo

Computational fluid dynamics (CFD) can be used for evaluation of hemodynamics. However, its routine use is limited by labor-intensive manual segmentation, CFD mesh creation, and time-consuming simulation. This study aims to train a deep learning model to both generate patient-specific volume-meshes of the pulmonary artery from 3D cardiac MRI data and directly estimate CFD flow fields. This study used 135 3D cardiac MRIs from both a public and private dataset. The pulmonary arteries in the MRIs were manually segmented and converted into volume-meshes. CFD simulations were performed on ground truth meshes and interpolated onto point-point correspondent meshes to create the ground truth dataset. The dataset was split 85/10/15 for training, validation and testing. Image2Flow, a hybrid image and graph convolutional neural network, was trained to transform a pulmonary artery template to patient-specific anatomy and CFD values. Image2Flow was evaluated in terms of segmentation and accuracy of CFD predicted was assessed using node-wise comparisons. Centerline comparisons of Image2Flow and CFD simulations performed using machine learning segmentation were also performed. Image2Flow achieved excellent segmentation accuracy with a median Dice score of 0.9 (IQR: 0.86-0.92). The median node-wise normalized absolute error for pressure and velocity magnitude was 11.98% (IQR: 9.44-17.90%) and 8.06% (IQR: 7.54-10.41), respectively. Centerline analysis showed no significant difference between the Image2Flow and conventional CFD simulated on machine learning-generated volume-meshes. This proof-of-concept study has shown it is possible to simultaneously perform patient specific volume-mesh based segmentation and pressure and flow field estimation. Image2Flow completes segmentation and CFD in ~205ms, which ~7000 times faster than manual methods, making it more feasible in a clinical environment., Comment: 22 pages, 7 figures, 3 tables

Automated segmentation of distinct tumor regions is critical for accurate diagnosis and treatment planning in pediatric brain tumors. This study evaluates the efficacy of the Multi-Planner U-Net (MPUnet) approach in segmenting different tumor subregions across three challenging datasets: Pediatrics Tumor Challenge (PED), Brain Metastasis Challenge (MET), and Sub-Sahara-Africa Adult Glioma (SSA). These datasets represent diverse scenarios and anatomical variations, making them suitable for assessing the robustness and generalization capabilities of the MPUnet model. By utilizing multi-planar information, the MPUnet architecture aims to enhance segmentation accuracy. Our results show varying performance levels across the evaluated challenges, with the tumor core (TC) class demonstrating relatively higher segmentation accuracy. However, variability is observed in the segmentation of other classes, such as the edema and enhancing tumor (ET) regions. These findings emphasize the complexity of brain tumor segmentation and highlight the potential for further refinement of the MPUnet approach and inclusion of MRI more data and preprocessing.

Automated segmentation of distinct tumor regions is critical for accurate diagnosis and treatment planning in pediatric brain tumors. This study evaluates the efficacy of the Multi-Planner U-Net (MPUnet) approach in segmenting different tumor subregions across three challenging datasets: Pediatrics Tumor Challenge (PED), Brain Metastasis Challenge (MET), and Sub-Sahara-Africa Adult Glioma (SSA). These datasets represent diverse scenarios and anatomical variations, making them suitable for assessing the robustness and generalization capabilities of the MPUnet model. By utilizing multi-planar information, the MPUnet architecture aims to enhance segmentation accuracy. Our results show varying performance levels across the evaluated challenges, with the tumor core (TC) class demonstrating relatively higher segmentation accuracy. However, variability is observed in the segmentation of other classes, such as the edema and enhancing tumor (ET) regions. These findings emphasize the complexity of brain tumor segmentation and highlight the potential for further refinement of the MPUnet approach and inclusion of MRI more data and preprocessing.

A large range of sophisticated brain image analysis tools have been developed by the neuroscience community, greatly advancing the field of human brain mapping. Here we introduce the Computational Anatomy Toolbox (CAT)-a powerful suite of tools for brain morphometric analyses with an intuitive graphical user interface but also usable as a shell script. CAT is suitable for beginners, casual users, experts, and developers alike, providing a comprehensive set of analysis options, workflows, and integrated pipelines. The available analysis streams-illustrated on an example dataset-allow for voxel-based, surface-based, and region-based morphometric analyses. Notably, CAT incorporates multiple quality control options and covers the entire analysis workflow, including the preprocessing of cross-sectional and longitudinal data, statistical analysis, and the visualization of results. The overarching aim of this article is to provide a complete description and evaluation of CAT while offering a citable standard for the neuroscience community., De två sista författarna delar sistaförfattarskapet.

Magnetic resonance imaging (MRI) has become an essential and a frontline technique in the detection of brain tumor. However, segmenting tumors manually from scans is laborious and time-consuming. This has led to an increasing trend towards fully automated methods for precise tumor segmentation in MRI scans. Accurate tumor segmentation is crucial for improved diagnosis, treatment, and prognosis. This study benchmarks and evaluates four widely used CNN-based methods for brain tumor segmentation CaPTk, 2DVNet, EnsembleUNets, and ResNet50. Using 1251 multimodal MRI scans from the BraTS2021 dataset, we compared the performance of these methods against a reference dataset of segmented images assisted by radiologists. This comparison was conducted using segmented images directly and further by radiomic features extracted from the segmented images using pyRadiomics. Performance was assessed using the Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD). EnsembleUNets excelled, achieving a DSC of 0.93 and an HD of 18, outperforming the other methods. Further comparative analysis of radiomic features confirmed EnsembleUNets as the most precise segmentation method, surpassing other methods. EnsembleUNets recorded a Concordance Correlation Coefficient (CCC) of 0.79, a Total Deviation Index (TDI) of 1.14, and a Root Mean Square Error (RMSE) of 0.53, underscoring its superior performance. We also performed validation on an independent dataset of 611 samples (UPENN-GBM), which further supported the accuracy of EnsembleUNets, with a DSC of 0.85 and an HD of 17.5. These findings provide valuable insight into the efficacy of EnsembleUNets, supporting informed decisions for accurate brain tumor segmentation.

A large range of sophisticated brain image analysis tools have been developed by the neuroscience community, greatly advancing the field of human brain mapping. Here we introduce the Computational Anatomy Toolbox (CAT)-a powerful suite of tools for brain morphometric analyses with an intuitive graphical user interface but also usable as a shell script. CAT is suitable for beginners, casual users, experts, and developers alike, providing a comprehensive set of analysis options, workflows, and integrated pipelines. The available analysis streams-illustrated on an example dataset-allow for voxel-based, surface-based, and region-based morphometric analyses. Notably, CAT incorporates multiple quality control options and covers the entire analysis workflow, including the preprocessing of cross-sectional and longitudinal data, statistical analysis, and the visualization of results. The overarching aim of this article is to provide a complete description and evaluation of CAT while offering a citable standard for the neuroscience community., De två sista författarna delar sistaförfattarskapet.

A large range of sophisticated brain image analysis tools have been developed by the neuroscience community, greatly advancing the field of human brain mapping. Here we introduce the Computational Anatomy Toolbox (CAT)-a powerful suite of tools for brain morphometric analyses with an intuitive graphical user interface but also usable as a shell script. CAT is suitable for beginners, casual users, experts, and developers alike, providing a comprehensive set of analysis options, workflows, and integrated pipelines. The available analysis streams-illustrated on an example dataset-allow for voxel-based, surface-based, and region-based morphometric analyses. Notably, CAT incorporates multiple quality control options and covers the entire analysis workflow, including the preprocessing of cross-sectional and longitudinal data, statistical analysis, and the visualization of results. The overarching aim of this article is to provide a complete description and evaluation of CAT while offering a citable standard for the neuroscience community., De två sista författarna delar sistaförfattarskapet.

A large range of sophisticated brain image analysis tools have been developed by the neuroscience community, greatly advancing the field of human brain mapping. Here we introduce the Computational Anatomy Toolbox (CAT)-a powerful suite of tools for brain morphometric analyses with an intuitive graphical user interface but also usable as a shell script. CAT is suitable for beginners, casual users, experts, and developers alike, providing a comprehensive set of analysis options, workflows, and integrated pipelines. The available analysis streams-illustrated on an example dataset-allow for voxel-based, surface-based, and region-based morphometric analyses. Notably, CAT incorporates multiple quality control options and covers the entire analysis workflow, including the preprocessing of cross-sectional and longitudinal data, statistical analysis, and the visualization of results. The overarching aim of this article is to provide a complete description and evaluation of CAT while offering a citable standard for the neuroscience community., De två sista författarna delar sistaförfattarskapet.

A large range of sophisticated brain image analysis tools have been developed by the neuroscience community, greatly advancing the field of human brain mapping. Here we introduce the Computational Anatomy Toolbox (CAT)-a powerful suite of tools for brain morphometric analyses with an intuitive graphical user interface but also usable as a shell script. CAT is suitable for beginners, casual users, experts, and developers alike, providing a comprehensive set of analysis options, workflows, and integrated pipelines. The available analysis streams-illustrated on an example dataset-allow for voxel-based, surface-based, and region-based morphometric analyses. Notably, CAT incorporates multiple quality control options and covers the entire analysis workflow, including the preprocessing of cross-sectional and longitudinal data, statistical analysis, and the visualization of results. The overarching aim of this article is to provide a complete description and evaluation of CAT while offering a citable standard for the neuroscience community., De två sista författarna delar sistaförfattarskapet.

Background Magnetic Resonance Imaging (MRI) is a highly demanded medical imaging system due to high resolution, large volumetric coverage, and ability to capture the dynamic and functional information of body organs e.g. cardiac MRI is employed to assess cardiac structure and evaluate blood flow dynamics through the cardiac valves. Long scan time is the main drawback of MRI, which makes it difficult for the patients to remain still during the scanning process.Objective By collecting fewer measurements, MRI scan time can be shortened, but this undersampling causes aliasing artifacts in the reconstructed images. Advanced image reconstruction algorithms have been used in literature to overcome these undersampling artifacts. These algorithms are computationally expensive and require a long time for reconstruction which makes them infeasible for real-time clinical applications e.g. cardiac MRI. However, exploiting the inherent parallelism in these algorithms can help to reduce their computation time.Methods Low-rank plus sparse (L+S) matrix decomposition model is a technique used in literature to reconstruct the highly undersampled dynamic MRI (dMRI) data at the expense of long reconstruction time. In this paper, Compressed Singular Value Decomposition (cSVD) model is used in L+S decomposition model (instead of conventional SVD) to reduce the reconstruction time. The results provide improved quality of the reconstructed images. Furthermore, it has been observed that cSVD and other parts of the L+S model possess highly parallel operations; therefore, a customized GPU based parallel architecture of the modified L+S model has been presented to further reduce the reconstruction time.Results Four cardiac MRI datasets (three different cardiac perfusion acquired from different patients and one cardiac cine data), each with different acceleration factors of 2, 6 and 8 are used for experiments in this paper. Experimental results demonstrate that using the proposed parallel archit

Automated segmentation of distinct tumor regions is critical for accurate diagnosis and treatment planning in pediatric brain tumors. This study evaluates the efficacy of the Multi-Planner U-Net (MPUnet) approach in segmenting different tumor subregions across three challenging datasets: Pediatrics Tumor Challenge (PED), Brain Metastasis Challenge (MET), and Sub-Sahara-Africa Adult Glioma (SSA). These datasets represent diverse scenarios and anatomical variations, making them suitable for assessing the robustness and generalization capabilities of the MPUnet model. By utilizing multi-planar information, the MPUnet architecture aims to enhance segmentation accuracy. Our results show varying performance levels across the evaluated challenges, with the tumor core (TC) class demonstrating relatively higher segmentation accuracy. However, variability is observed in the segmentation of other classes, such as the edema and enhancing tumor (ET) regions. These findings emphasize the complexity of brain tumor segmentation and highlight the potential for further refinement of the MPUnet approach and inclusion of MRI more data and preprocessing.

Quantitative analysis of pseudo-diffusion in diffusion-weighted magnetic resonance imaging (DWI) data shows potential for assessing fetal lung maturation and generating valuable imaging biomarkers. Yet, the clinical utility of DWI data is hindered by unavoidable fetal motion during acquisition. We present IVIM-morph, a self-supervised deep neural network model for motion-corrected quantitative analysis of DWI data using the Intra-voxel Incoherent Motion (IVIM) model. IVIM-morph combines two sub-networks, a registration sub-network, and an IVIM model fitting sub-network, enabling simultaneous estimation of IVIM model parameters and motion. To promote physically plausible image registration, we introduce a biophysically informed loss function that effectively balances registration and model-fitting quality. We validated the efficacy of IVIM-morph by establishing a correlation between the predicted IVIM model parameters of the lung and gestational age (GA) using fetal DWI data of 39 subjects. IVIM-morph exhibited a notably improved correlation with gestational age (GA) when performing in-vivo quantitative analysis of fetal lung DWI data during the canalicular phase. IVIM-morph shows potential in developing valuable biomarkers for non-invasive assessment of fetal lung maturity with DWI data. Moreover, its adaptability opens the door to potential applications in other clinical contexts where motion compensation is essential for quantitative DWI analysis. The IVIM-morph code is readily available at: https://github.com/TechnionComputationalMRILab/qDWI-Morph.

Synthetic longitudinal brain MRI simulates brain aging and would enable more efficient research on neurodevelopmental and neurodegenerative conditions. Synthetically generated, age-adjusted brain images could serve as valuable alternatives to costly longitudinal imaging acquisitions, serve as internal controls for studies looking at the effects of environmental or therapeutic modifiers on brain development, and allow data augmentation for diverse populations. In this paper, we present a diffusion-based approach called SynthBrainGrow for synthetic brain aging with a two-year step. To validate the feasibility of using synthetically-generated data on downstream tasks, we compared structural volumetrics of two-year-aged brains against synthetically-aged brain MRI. Results show that SynthBrainGrow can accurately capture substructure volumetrics and simulate structural changes such as ventricle enlargement and cortical thinning. Our approach provides a novel way to generate longitudinal brain datasets from cross-sectional data to enable augmented training and benchmarking of computational tools for analyzing lifespan trajectories. This work signifies an important advance in generative modeling to synthesize realistic longitudinal data with limited lifelong MRI scans. The code is available at XXX., Comment: 8 pages, 4 figures

Imaging sites around the world generate growing amounts of medical scan data with ever more versatile and affordable technology. Large-scale studies acquire MRI for tens of thousands of participants, together with metadata ranging from lifestyle questionnaires to biochemical assays, genetic analyses and more. These large datasets encode substantial information about human health and hold considerable potential for machine learning training and analysis. This chapter examines ongoing large-scale studies and the challenge of distribution shifts between them. Transfer learning for overcoming such shifts is discussed, together with federated learning for safe access to distributed training data securely held at multiple institutions. Finally, representation learning is reviewed as a methodology for encoding embeddings that express abstract relationships in multi-modal input formats., Comment: Book chapter pre-print

Magnetic resonance imaging (MRI), is a noninvasive medical imaging testing techniquewhich is used to produce detailed images of internal structure of the human body, includingbones, muscles, organs, and blood vessels. MRI scanners use large magnets and radiowaves to create images of the body. Cardiac MRI scan helps doctors to detect and monitorcardiac diseases like blood clots, artery blockages, and scar tissue etc. Cardiovasculardisease is a type of disease that affects the heart or the blood vessels.This thesis aims to explore the reconstruction of accelerated cardiovascular MRI datato reconstruct under-sampled MRI data acquired after applying accelerated techniques.The focus of this research is to study and implement deep learning techniques to overcomethe aliasing artifacts caused by accelerated imaging. The results of this study will becompared with fully sampled data acquired with traditional existing techniques such asParallel Imaging (PI) and Compressed Sensing (CS).The primary findings of this study show that the proposed deep learning network caneffectively reconstruct under-sampled cardiovascular MRI data acquired using acceleratedimaging techniques. Many experiments were performed to handle 4D Flow data with limitedmemory for training the network. The network’s performance was found to be comparableto the fully sampled data acquired using traditional imaging techniques such asPI and CS. It is also important to note that this study also aimed to investigate the generalizabilityof the proposed deep learning network, specifically FlowVN, when appliedto different datasets. To explore this aspect, two different models were employed: a pretrainedmodel using previous research data and configurations, and a model trained fromscratch using CMIV data with experiments performed to address limited memory issuesassociated with 4D Flow data.

Magnetic resonance imaging (MRI), is a noninvasive medical imaging testing techniquewhich is used to produce detailed images of internal structure of the human body, includingbones, muscles, organs, and blood vessels. MRI scanners use large magnets and radiowaves to create images of the body. Cardiac MRI scan helps doctors to detect and monitorcardiac diseases like blood clots, artery blockages, and scar tissue etc. Cardiovasculardisease is a type of disease that affects the heart or the blood vessels.This thesis aims to explore the reconstruction of accelerated cardiovascular MRI datato reconstruct under-sampled MRI data acquired after applying accelerated techniques.The focus of this research is to study and implement deep learning techniques to overcomethe aliasing artifacts caused by accelerated imaging. The results of this study will becompared with fully sampled data acquired with traditional existing techniques such asParallel Imaging (PI) and Compressed Sensing (CS).The primary findings of this study show that the proposed deep learning network caneffectively reconstruct under-sampled cardiovascular MRI data acquired using acceleratedimaging techniques. Many experiments were performed to handle 4D Flow data with limitedmemory for training the network. The network’s performance was found to be comparableto the fully sampled data acquired using traditional imaging techniques such asPI and CS. It is also important to note that this study also aimed to investigate the generalizabilityof the proposed deep learning network, specifically FlowVN, when appliedto different datasets. To explore this aspect, two different models were employed: a pretrainedmodel using previous research data and configurations, and a model trained fromscratch using CMIV data with experiments performed to address limited memory issuesassociated with 4D Flow data.

Despite the proliferation of deep learning techniques for accelerated MRI acquisition and enhanced image reconstruction, the construction of large and diverse MRI datasets continues to pose a barrier to effective clinical translation of these technologies. One major challenge is in collecting the MRI raw data (required for image reconstruction) from clinical scanning, as only magnitude images are typically saved and used for clinical assessment and diagnosis. The image phase and multi-channel RF coil information are not retained when magnitude-only images are saved in clinical imaging archives. Additionally, preprocessing used for data in clinical imaging can lead to biased results. While several groups have begun concerted efforts to collect large amounts of MRI raw data, current databases are limited in the diversity of anatomy, pathology, annotations, and acquisition types they contain. To address this, we present a method for synthesizing realistic MR data from magnitude-only data, allowing for the use of diverse data from clinical imaging archives in advanced MRI reconstruction development. Our method uses a conditional GAN-based framework to generate synthetic phase images from input magnitude images. We then applied ESPIRiT to derive RF coil sensitivity maps from fully sampled real data to generate multi-coil data. The synthetic data generation method was evaluated by comparing image reconstruction results from training Variational Networks either with real data or synthetic data. We demonstrate that the Variational Network trained on synthetic MRI data from our method, consisting of GAN-derived synthetic phase and multi-coil information, outperformed Variational Networks trained on data with synthetic phase generated using current state-of-the-art methods. Additionally, we demonstrate that the Variational Networks trained with synthetic k-space data from our method perform comparably to image reconstruction networks trained on undersampled real k-space data.

Patient outcome prediction is critical in management of ischemic stroke. In this paper, a novel machine learning model is proposed for stroke outcome prediction using multimodal Magnetic Resonance Imaging (MRI). The proposed model consists of two serial levels of Autoencoders (AEs), where different AEs at level 1 are used for learning unimodal features from different MRI modalities and a AE at level 2 is used to combine the unimodal features into compressed multimodal features. The sequences of multimodal features of a given patient are then used by an LSTM network for predicting outcome score. The proposed AE2-LSTM model is proved to be an effective approach for better addressing the multimodality and volumetric nature of MRI data. Experimental results show that the proposed AE2-LSTM outperforms the existing state-of-the art models by achieving highest AUC=0.71 and lowest MAE=0.34., Comment: The IEEE International Symposium on Biomedical Imaging (ISBI). arXiv admin note: text overlap with arXiv:2205.05545

The integration of different imaging modalities, such as structural, diffusion tensor, and functional magnetic resonance imaging, with deep learning models has yielded promising outcomes in discerning phenotypic characteristics and enhancing disease diagnosis. The development of such a technique hinges on the efficient fusion of heterogeneous multimodal features, which initially reside within distinct representation spaces. Naively fusing the multimodal features does not adequately capture the complementary information and could even produce redundancy. In this work, we present a novel joint self-supervised and supervised contrastive learning method to learn the robust latent feature representation from multimodal MRI data, allowing the projection of heterogeneous features into a shared common space, and thereby amalgamating both complementary and analogous information across various modalities and among similar subjects. We performed a comparative analysis between our proposed method and alternative deep multimodal learning approaches. Through extensive experiments on two independent datasets, the results demonstrated that our method is significantly superior to several other deep multimodal learning methods in predicting abnormal neurodevelopment. Our method has the capability to facilitate computer-aided diagnosis within clinical practice, harnessing the power of multimodal data., Comment: 35 pages. Submitted to journal

Exploiting 4D-flow magnetic resonance imaging (MRI) data to quantify hemodynamics requires an adequate spatio-temporal vector field resolution at a low noise level. To address this challenge, we provide a learned solution to super-resolve in vivo 4D-flow MRI data at a post-processing level. We propose a deep convolutional neural network (CNN) that learns the inter-scale relationship of the velocity vector map and leverages an efficient residual learning scheme to make it computationally feasible. A novel, direction-sensitive, and robust loss function is crucial to learning vector-field data. We present a detailed comparative study between the proposed super-resolution and the conventional cubic B-spline based vector-field super-resolution. Our method improves the peak-velocity to noise ratio of the flow field by 10 and 30% for in vivo cardiovascular and cerebrovascular data, respectively, for 4 × super-resolution over the state-of-the-art cubic B-spline. Significantly, our method offers 10x faster inference over the cubic B-spline. The proposed approach for super-resolution of 4D-flow data would potentially improve the subsequent calculation of hemodynamic quantities.

Delineating visual field maps and iso-eccentricities from fMRI data is an important but time-consuming task for many neuroimaging studies on the human visual cortex because the traditional methods of doing so using retinotopic mapping experiments require substantial expertise as well as scanner, computer, and human time. Automated methods based on gray-matter anatomy or a combination of anatomy and functional mapping can reduce these requirements but are less accurate than experts. Convolutional Neural Networks (CNNs) are powerful tools for automated medical image segmentation. We hypothesize that CNNs can define visual area boundaries with high accuracy. We trained U-Net CNNs with ResNet18 backbones to predict either V1, V2, and V3 boundaries or 5 regions of iso-eccentricity using human-labeled maps. Separate CNNs were trained to predict these regions using different combinations of the following input data: (1) anatomical data from a T1-weighted image only, (2) anatomical data from T1-weighted and T2*-weighted images, (3) white-matter tract endpoints from diffusion-weighted imaging, (4) functional data from retinotopic mapping. All CNNs using functional data had cross-validated accuracy that was statistically indistinguishable from the inter-rater reliability of the training dataset (dice coefficient of 92%) while the CNNs lacking functional data had lower but similar accuracies (~75%). Existing models that do not use CNNs had accuracies lower than any of the CNNs. These results demonstrate that with current methods and data quality, CNNs can replace the time and effort of human experts in manually defining early retinotopic maps, but cannot yet replace the acquisition of functional data.

Graph topology inference is a research field that studies how to learn the structure of a graph from data related to it. It is a very popular research topic in which algorithms are being developed faster and more efficient year after year. Graphs are a mathematical tool that allows us to model relationships between data obtained from complex structures, such as the human brain. In this thesis, we have developed a graph topology inference algorithm based on the estimation of the precision matrix with Laplacian constraints, where we have used real data obtained by f-MRI to evaluate the algorithm. Then, we have applied network science parameters, such as the small-world parameter, in order to compare different graph network topologies and provide valuable information about the structure of these graphs., La inferencia de topología de grafos es un campo de investigación en el que se estudia cómo aprender la estructura de un grafo a partir de datos relacionados con él. Es un tema de investigación muy popular en el que se desarrollan algoritmos cada vez más rápidos y eficientes año tras año. Los grafos son una herramienta matemática que nos permite modelar las relaciones entre datos obtenidos en estructuras complejas, como por ejemplo el cerebro humano. En esta tesis, hemos desarrollado un algoritmo de inferencia de topología de grafos basado en la estimación de la matriz de precisión con restricciones de Laplaciana, donde hemos utilizado datos reales obtenidos por f-MRI para evaluar el algoritmo. Después, hemos aplicado parámetros de ciencia de redes, como por ejemplo el parámetro "small-world", para poder comparar diferentes topologías de grafos y proporcionar una información valiosa sobre la estructura de estos grafos., La inferència de topologia de grafs és un camp de recerca en el qual s'estudia com aprendre l'estructura d'un graf a partir de dades relacionades amb ell. És un tema de recerca molt popular en el qual es desenvolupen algorismes cada vegada més ràpids i eficients any rere any. Els grafs són una eina matemàtica que ens permet modelar les relacions entre dades obtingudes en estructures complexes, com per exemple el cervell humà. En aquesta tesi, hem dut a terme un algorisme d'inferència de topologia de grafs basat en l'estimació de la matriu de precisió amb restriccions de Laplaciana, on hem utilitzat dades reals aconseguides per f-MRI per avaluar l'algorisme. Després, hem aplicat paràmetres de ciència de xarxes, com per exemple el paràmetre "small-world", per poder comparar diferents topologies de grafs i proporcionar una informació valuosa sobre l'estructura d'aquests grafs.

Magnetic resonance imaging (MRI) is a commonly used non-invasive imaging technique that provides high resolution images of soft tissue. One problem with MRI is that it is sensitive to signal quality issues. The issues can arise for various reasons, for example by metal located either inside or outside of the body. Another common signal quality issue is caused by the patient being partly placed outside field of view of the MRI scanner. This thesis aims to investigate the possibility to automatically detect these signal quality issues using deep neural networks. More specifically, two different 3D CNN network types were studied, a classification-based approach and a reconstruction-based approach. The datasets used consist of MRI volumes from UK Biobank which have been processed and manually annotated by operators at AMRA Medical. For the classification method four different network architectures were explored utilising supervised learning with multi-label classification. The classification method was evaluated using accuracy and label-based evaluation metrics, such as macro-precision, macro-recall and macro-F1. The reconstruction method was based on anomaly detection using an autoencoder which was trained to reconstruct volumes without any artefacts. A mean squared prediction error was calculated for the reconstructed volume and compared against a threshold in order to classify a volume with or without artefacts. The idea was that volumes containing artefacts should be more difficult to reconstruct and thus, result in a higher prediction error. The reconstruction method was evaluated using accuracy, precision, recall and F1-score. The results show that the classification method has overall higher performance than the reconstruction method. The achieved accuracy for the classification method was 98.0% for metal artefacts and 97.5% for outside field of view artefacts. The best architecture for the classification method proved to be DenseNet201. The reconstruction met

Magnetic resonance imaging (MRI) is a commonly used non-invasive imaging technique that provides high resolution images of soft tissue. One problem with MRI is that it is sensitive to signal quality issues. The issues can arise for various reasons, for example by metal located either inside or outside of the body. Another common signal quality issue is caused by the patient being partly placed outside field of view of the MRI scanner. This thesis aims to investigate the possibility to automatically detect these signal quality issues using deep neural networks. More specifically, two different 3D CNN network types were studied, a classification-based approach and a reconstruction-based approach. The datasets used consist of MRI volumes from UK Biobank which have been processed and manually annotated by operators at AMRA Medical. For the classification method four different network architectures were explored utilising supervised learning with multi-label classification. The classification method was evaluated using accuracy and label-based evaluation metrics, such as macro-precision, macro-recall and macro-F1. The reconstruction method was based on anomaly detection using an autoencoder which was trained to reconstruct volumes without any artefacts. A mean squared prediction error was calculated for the reconstructed volume and compared against a threshold in order to classify a volume with or without artefacts. The idea was that volumes containing artefacts should be more difficult to reconstruct and thus, result in a higher prediction error. The reconstruction method was evaluated using accuracy, precision, recall and F1-score. The results show that the classification method has overall higher performance than the reconstruction method. The achieved accuracy for the classification method was 98.0% for metal artefacts and 97.5% for outside field of view artefacts. The best architecture for the classification method proved to be DenseNet201. The reconstruction met

Enhancing the process of generating entirely automated visualization schemes of complex fluid flow patterns within brain tumors is critical for gaining insights into their movements and behaviors. This study focused on optimizing and automating the processing of 3D volumetric and vector field data sets obtained from DCE-MRI (Dynamic Contrast-Enhanced Magnetic Resonance Imaging) scans. It is crucial to maintain performance, preserve data quality and resolution, and provide an accessible platform for biomedical scientists. In this paper, we represent an innovative approach to enhance fluid flow visualization of brain tumors through scalable visualization techniques. New techniques have been designed, benchmarked, and authenticated to produce X3D visualizations in Web3D environments using Python, and ParaView. The proposed approach does not only enhance fluid flow visualization in the context of brain tumor research but also provides a reproducible and transparent framework for future studies with both human and mouse scans.

Magnetic Resonance Imaging data collected in rats injected with isotonic acid in the left hippocampus, and humans with multiple sclerosis and controls.

Accurate detection of arterial input function is a crucial step in obtaining perfusion hemodynamic parameters using dynamic susceptibility contrast-enhanced magnetic resonance imaging. It is required as input for perfusion quantification and has a great impact on the result of the deconvolution operation. To improve the reproducibility and reliability of arterial input function detection, several semi- or fully automatic methods have been proposed. This study provides an overview of the current state of the field of arterial input function detection. Methods most commonly used for semi- and fully automatic arterial input function detection are reviewed, and their advantages and disadvantages are listed., Comment: 7 pages

Amyotrophic Lateral Sclerosis (ALS) is a complex neurodegenerative disorder involving motor neuron degeneration. Significant research has begun to establish brain magnetic resonance imaging (MRI) as a potential biomarker to diagnose and monitor the state of the disease. Deep learning has turned into a prominent class of machine learning programs in computer vision and has been successfully employed to solve diverse medical image analysis tasks. However, deep learning-based methods applied to neuroimaging have not achieved superior performance in ALS patients classification from healthy controls due to having insignificant structural changes correlated with pathological features. Therefore, the critical challenge in deep models is to determine useful discriminative features with limited training data. By exploiting the long-range relationship of image features, this study introduces a framework named SF2Former that leverages vision transformer architecture's power to distinguish the ALS subjects from the control group. To further improve the network's performance, spatial and frequency domain information are combined because MRI scans are captured in the frequency domain before being converted to the spatial domain. The proposed framework is trained with a set of consecutive coronal 2D slices, which uses the pre-trained weights on ImageNet by leveraging transfer learning. Finally, a majority voting scheme has been employed to those coronal slices of a particular subject to produce the final classification decision. Our proposed architecture has been thoroughly assessed with multi-modal neuroimaging data using two well-organized versions of the Canadian ALS Neuroimaging Consortium (CALSNIC) multi-center datasets. The experimental results demonstrate the superiority of our proposed strategy in terms of classification accuracy compared with several popular deep learning-based techniques., Comment: 17 pages, 8 figures

Delineating visual field maps and iso-eccentricities from fMRI data is an important but time-consuming task for many neuroimaging studies on the human visual cortex because the traditional methods of doing so using retinotopic mapping experiments require substantial expertise as well as scanner, computer, and human time. Automated methods based on gray-matter anatomy or a combination of anatomy and functional mapping can reduce these requirements but are less accurate than experts. Convolutional Neural Networks (CNNs) are powerful tools for automated medical image segmentation. We hypothesize that CNNs can define visual area boundaries with high accuracy. We trained U-Net CNNs with ResNet18 backbones to predict either V1, V2, and V3 boundaries or 5 regions of iso-eccentricity using human-labeled maps. Separate CNNs were trained to predict these regions using different combinations of the following input data: (1) anatomical data from a T1-weighted image only, (2) anatomical data from T1-weighted and T2*-weighted images, (3) white-matter tract endpoints from diffusion-weighted imaging, (4) functional data from retinotopic mapping. All CNNs using functional data had cross-validated accuracy that was statistically indistinguishable from the inter-rater reliability of the training dataset (dice coefficient of 92%) while the CNNs lacking functional data had lower but similar accuracies (~75%). Existing models that do not use CNNs had accuracies lower than any of the CNNs. These results demonstrate that with current methods and data quality, CNNs can replace the time and effort of human experts in manually defining early retinotopic maps, but cannot yet replace the acquisition of functional data.

Image segmentation, real-value prediction, and cross-modal translation are critical challenges in medical imaging. In this study, we propose a versatile multi-task neural network framework, based on an enhanced Transformer U-Net architecture, capable of simultaneously, selectively, and adaptively addressing these medical image tasks. Validation is performed on a public repository of human brain MR and CT images. We decompose the traditional problem of synthesizing CT images into distinct subtasks, which include skull segmentation, Hounsfield unit (HU) value prediction, and image sequential reconstruction. To enhance the framework's versatility in handling multi-modal data, we expand the model with multiple image channels. Comparisons between synthesized CT images derived from T1-weighted and T2-Flair images were conducted, evaluating the model's capability to integrate multi-modal information from both morphological and pixel value perspectives., Comment: 4 pages, 3 figures, 2 tables

Identifying and utilising various biomarkers for tracking Alzheimer's disease (AD) progression have received many recent attentions and enable helping clinicians make the prompt decisions. Traditional progression models focus on extracting morphological biomarkers in regions of interest (ROIs) from MRI/PET images, such as regional average cortical thickness and regional volume. They are effective but ignore the relationships between brain ROIs over time, which would lead to synergistic deterioration. For exploring the synergistic deteriorating relationship between these biomarkers, in this paper, we propose a novel spatio-temporal similarity measure based multi-task learning approach for effectively predicting AD progression and sensitively capturing the critical relationships between biomarkers. Specifically, we firstly define a temporal measure for estimating the magnitude and velocity of biomarker change over time, which indicate a changing trend(temporal). Converting this trend into the vector, we then compare this variability between biomarkers in a unified vector space(spatial). The experimental results show that compared with directly ROI based learning, our proposed method is more effective in predicting disease progression. Our method also enables performing longitudinal stability selection to identify the changing relationships between biomarkers, which play a key role in disease progression. We prove that the synergistic deteriorating biomarkers between cortical volumes or surface areas have a significant effect on the cognitive prediction.

Pooling publicly-available MRI data from multiple sites allows to assemble extensive groups of subjects, increase statistical power, and promote data reuse with machine learning techniques. The harmonization of multicenter data is necessary to reduce the confounding effect associated with non-biological sources of variability in the data. However, when applied to the entire dataset before machine learning, the harmonization leads to data leakage, because information outside the training set may affect model building, and potentially falsely overestimate performance. We propose a 1) measurement of the efficacy of data harmonization; 2) harmonizer transformer, i.e., an implementation of the ComBat harmonization allowing its encapsulation among the preprocessing steps of a machine learning pipeline, avoiding data leakage. We tested these tools using brain T1-weighted MRI data from 1740 healthy subjects acquired at 36 sites. After harmonization, the site effect was removed or reduced, and we showed the data leakage effect in predicting individual age from MRI data, highlighting that introducing the harmonizer transformer into a machine learning pipeline allows for avoiding data leakage.

In dieser Doktorarbeit wird die Frage untersucht, wie erfolgreich deep learning bei der Diagnostik von neurodegenerativen Erkrankungen unterstützen kann. In 5 experimentellen Studien wird die Anwendung von Convolutional Neural Networks (CNNs) auf Daten der Magnetresonanztomographie (MRT) untersucht. Ein Schwerpunkt wird dabei auf die Erklärbarkeit der eigentlich intransparenten Modelle gelegt. Mit Hilfe von Methoden der erklärbaren künstlichen Intelligenz (KI) werden Heatmaps erstellt, die die Relevanz einzelner Bildbereiche für das Modell darstellen. Die 5 Studien dieser Dissertation zeigen das Potenzial von CNNs zur Krankheitserkennung auf neurologischen MRT, insbesondere bei der Kombination mit Methoden der erklärbaren KI. Mehrere Herausforderungen wurden in den Studien aufgezeigt und Lösungsansätze in den Experimenten evaluiert. Über alle Studien hinweg haben CNNs gute Klassifikationsgenauigkeiten erzielt und konnten durch den Vergleich von Heatmaps zur klinischen Literatur validiert werden. Weiterhin wurde eine neue CNN Architektur entwickelt, spezialisiert auf die räumlichen Eigenschaften von Gehirn MRT Bildern., Deep learning and especially convolutional neural networks (CNNs) have a high potential of being implemented into clinical decision support software for tasks such as diagnosis and prediction of disease courses. This thesis has studied the application of CNNs on structural MRI data for diagnosing neurological diseases. Specifically, multiple sclerosis and Alzheimer’s disease were used as classification targets due to their high prevalence, data availability and apparent biomarkers in structural MRI data. The classification task is challenging since pathology can be highly individual and difficult for human experts to detect and due to small sample sizes, which are caused by the high acquisition cost and sensitivity of medical imaging data. A roadblock in adopting CNNs to clinical practice is their lack of interpretability. Therefore, after optimizing the machine learning models for predictive performance (e.g. balanced accuracy), we have employed explainability methods to study the reliability and validity of the trained models. The deep learning models achieved good predictive performance of over 87% balanced accuracy on all tasks and the explainability heatmaps showed coherence with known clinical biomarkers for both disorders. Explainability methods were compared quantitatively using brain atlases and shortcomings regarding their robustness were revealed. Further investigations showed clear benefits of transfer-learning and image registration on the model performance. Lastly, a new CNN layer type was introduced, which incorporates a prior on the spatial homogeneity of neuro-MRI data. CNNs excel when used on natural images which possess spatial heterogeneity, and even though MRI data and natural images share computational similarities, the composition and orientation of neuro-MRI is very distinct. The introduced patch-individual filter (PIF) layer breaks the assumption of spatial invariance of CNNs and reduces convergence time on different data sets without reduci

In dieser Doktorarbeit wird die Frage untersucht, wie erfolgreich deep learning bei der Diagnostik von neurodegenerativen Erkrankungen unterstützen kann. In 5 experimentellen Studien wird die Anwendung von Convolutional Neural Networks (CNNs) auf Daten der Magnetresonanztomographie (MRT) untersucht. Ein Schwerpunkt wird dabei auf die Erklärbarkeit der eigentlich intransparenten Modelle gelegt. Mit Hilfe von Methoden der erklärbaren künstlichen Intelligenz (KI) werden Heatmaps erstellt, die die Relevanz einzelner Bildbereiche für das Modell darstellen. Die 5 Studien dieser Dissertation zeigen das Potenzial von CNNs zur Krankheitserkennung auf neurologischen MRT, insbesondere bei der Kombination mit Methoden der erklärbaren KI. Mehrere Herausforderungen wurden in den Studien aufgezeigt und Lösungsansätze in den Experimenten evaluiert. Über alle Studien hinweg haben CNNs gute Klassifikationsgenauigkeiten erzielt und konnten durch den Vergleich von Heatmaps zur klinischen Literatur validiert werden. Weiterhin wurde eine neue CNN Architektur entwickelt, spezialisiert auf die räumlichen Eigenschaften von Gehirn MRT Bildern., Deep learning and especially convolutional neural networks (CNNs) have a high potential of being implemented into clinical decision support software for tasks such as diagnosis and prediction of disease courses. This thesis has studied the application of CNNs on structural MRI data for diagnosing neurological diseases. Specifically, multiple sclerosis and Alzheimer’s disease were used as classification targets due to their high prevalence, data availability and apparent biomarkers in structural MRI data. The classification task is challenging since pathology can be highly individual and difficult for human experts to detect and due to small sample sizes, which are caused by the high acquisition cost and sensitivity of medical imaging data. A roadblock in adopting CNNs to clinical practice is their lack of interpretability. Therefore, after optimizing the machine learning models for predictive performance (e.g. balanced accuracy), we have employed explainability methods to study the reliability and validity of the trained models. The deep learning models achieved good predictive performance of over 87% balanced accuracy on all tasks and the explainability heatmaps showed coherence with known clinical biomarkers for both disorders. Explainability methods were compared quantitatively using brain atlases and shortcomings regarding their robustness were revealed. Further investigations showed clear benefits of transfer-learning and image registration on the model performance. Lastly, a new CNN layer type was introduced, which incorporates a prior on the spatial homogeneity of neuro-MRI data. CNNs excel when used on natural images which possess spatial heterogeneity, and even though MRI data and natural images share computational similarities, the composition and orientation of neuro-MRI is very distinct. The introduced patch-individual filter (PIF) layer breaks the assumption of spatial invariance of CNNs and reduces convergence time on different data sets without reduci

There is an increasing need of sharing harmonized data from large, cooperative studies as this is essential to develop new diagnostic and prognostic biomarkers. In the field of multiple sclerosis (MS), the issue has become of paramount importance due to the need to translate into the clinical setting some of the most recent MRI achievements. However, differences in MRI acquisition parameters, image analysis and data storage across sites, with their potential bias, represent a substantial constraint. This review focuses on the state of the art, recent technical advances, and desirable future developments of the harmonization of acquisition, analysis and storage of large-scale multicentre MRI data of MS cohorts. Huge efforts are currently being made to achieve all the requirements needed to provide harmonized MRI datasets in the MS field, as proper management of large imaging datasets is one of our greatest opportunities and challenges in the coming years. Recommendations based on these achievements will be provided here. Despite the advances that have been made, the complexity of these tasks requires further research by specialized academical centres, with dedicated technical and human resources. Such collective efforts involving different professional figures are of crucial importance to offer to MS patients a personalised management while minimizing consumption of resources

Brain metastases occur when tumour cells developed anywhere in the body spread to the brain. Radiotherapy (RT) is a treatment option for brain metastases that aims to eliminate the tumor cells within the brain, but it also causes healthy tissue damage that can lead to cognitive decline. In order to measure the effects of different RT treatments on the patients, the quality of life (QoL) is measured to determine which one leads to the best cognitive outcome. For this purpose, tests with varying degrees of specificity, such as, neurocognitive assessment (NCA), patient reported outcome (PRO) and Karnofsky Performance Scale (KPS) aim to quantify the cognitive change of the patients before and after RT. However, the high cost of NCAs, patient dependency of PROs and unreliability of KPS highlight the need for a new approach to measure the cognitive state of patients. Such novel approach could estimate the QoL of the patients solely based on anatomical markers from MRI scans, reducing costs and patient interactions alike. In order to develop such tool, the anatomical markers related to cognitive must be identified first. In response, we performed a systematic review to analyse existing literature on the anatomical changes captured in MRI that have been linked to cognitive decline. We searched the Pubmed database where studies that evaluated cognitive change as a result of a specific anatomical change after RT were selected. Out of 298 publications, 16 were chosen, wherein tumor morphology, lesion number and location, peritumoral edema and necrosis were identified as the most relevant anatomical markers for the estimation of the QoL of brain metastatic patients based on MRI data. We identified multiple limitations within our review regarding inhomogeneous patient cohorts, low-quality image processing and the lack of correlation between the anatomical changes and the effect that might have in the QoL of patients. Consequently, although the studies reviewed all reached simila

PurposeThe paraspinal muscles (PSM) are a key feature potentially related to low back pain (LBP), and their structure and composition can be quantified using MRI. Most commonly, quantifying PSM measures across individual muscles and individual spinal levels renders numerous separate metrics that are analyzed in isolation. However, comprehensive multivariate approaches would be more appropriate for analyzing the PSM within an individual. To establish and test these methods, we hypothesized that multivariate summaries of PSM MRI measures would associate with the presence of LBP symptoms (i.e., pain intensity).MethodsWe applied hierarchical multiple factor analysis (hMFA), an unsupervised integrative method, to clinical PSM MRI data from unique cohort datasets including a longitudinal cohort of astronauts with pre- and post-spaceflight data and a cohort of chronic LBP subjects and asymptomatic controls. Three specific use cases were investigated: (1) predicting longitudinal changes in pain using combinations of baseline PSM measures; (2) integrating baseline and post-spaceflight MRI to assess longitudinal change in PSM and how it relates to pain; and (3) integrating PSM quality and adjacent spinal pathology between LBP patients and controls.ResultsOverall, we found distinct complex relationships with pain intensity between particular muscles and spinal levels. Subjects with high asymmetry between left and right lean muscle composition and differences between spinal segments PSM quality and structure are more likely to increase in pain reported outcome after prolonged time in microgravity. Moreover, changes in PSM quality and structure between pre and post-spaceflight relate to increase in pain after prolonged microgravity. Finally, we show how unsupervised hMFA recapitulates previous research on the association of CEP damage and LBP diagnostic.ConclusionOur analysis considers the spine as a multi-segmental unit as opposed to a series of discrete and isolated spine segm

PurposeThe paraspinal muscles (PSM) are a key feature potentially related to low back pain (LBP), and their structure and composition can be quantified using MRI. Most commonly, quantifying PSM measures across individual muscles and individual spinal levels renders numerous separate metrics that are analyzed in isolation. However, comprehensive multivariate approaches would be more appropriate for analyzing the PSM within an individual. To establish and test these methods, we hypothesized that multivariate summaries of PSM MRI measures would associate with the presence of LBP symptoms (i.e., pain intensity).MethodsWe applied hierarchical multiple factor analysis (hMFA), an unsupervised integrative method, to clinical PSM MRI data from unique cohort datasets including a longitudinal cohort of astronauts with pre- and post-spaceflight data and a cohort of chronic LBP subjects and asymptomatic controls. Three specific use cases were investigated: (1) predicting longitudinal changes in pain using combinations of baseline PSM measures; (2) integrating baseline and post-spaceflight MRI to assess longitudinal change in PSM and how it relates to pain; and (3) integrating PSM quality and adjacent spinal pathology between LBP patients and controls.ResultsOverall, we found distinct complex relationships with pain intensity between particular muscles and spinal levels. Subjects with high asymmetry between left and right lean muscle composition and differences between spinal segments PSM quality and structure are more likely to increase in pain reported outcome after prolonged time in microgravity. Moreover, changes in PSM quality and structure between pre and post-spaceflight relate to increase in pain after prolonged microgravity. Finally, we show how unsupervised hMFA recapitulates previous research on the association of CEP damage and LBP diagnostic.ConclusionOur analysis considers the spine as a multi-segmental unit as opposed to a series of discrete and isolated spine segm

BackgroundReal-time metabolic conversion of intravenously-injected hyperpolarized [1-13C]pyruvate to [1-13C]lactate and [13C]bicarbonate in the brain can be measured using dynamic hyperpolarized carbon-13 (HP-13C) MRI. However, voxel-wise evaluation of metabolism in patients with glioma is challenged by the limited signal-to-noise ratio (SNR) of downstream 13C metabolites, especially within lesions. The purpose of this study was to evaluate the ability of higher-order singular value decomposition (HOSVD) denoising methods to enhance dynamic HP [1-13C]pyruvate MRI data acquired from patients with glioma.MethodsDynamic HP-13C MRI were acquired from 14 patients with glioma. The effects of two HOSVD denoising techniques, tensor rank truncation-image enhancement (TRI) and global-local HOSVD (GL-HOSVD), on the SNR and kinetic modeling were analyzed in [1-13C]lactate data with simulated noise that matched the levels of [13C]bicarbonate signals. Both methods were then evaluated in patient data based on their ability to improve [1-13C]pyruvate, [1-13C]lactate and [13C]bicarbonate SNR. The effects of denoising on voxel-wise kinetic modeling of kPL and kPB was also evaluated. The number of voxels with reliable kinetic modeling of pyruvate-to-lactate (kPL) and pyruvate-to-bicarbonate (kPB) conversion rates within regions of interest (ROIs) before and after denoising was then compared.ResultsBoth denoising methods improved metabolite SNR and regional signal coverage. In patient data, the average increase in peak dynamic metabolite SNR was 2-fold using TRI and 4-5 folds using GL-HOSVD denoising compared to acquired data. Denoising reduced kPL modeling errors from a native average of 23% to 16% (TRI) and 15% (GL-HOSVD); and kPB error from 42% to 34% (TRI) and 37% (GL-HOSVD) (values were averaged voxelwise over all datasets). In contrast-enhancing lesions, the average number of voxels demonstrating within-tolerance kPL modeling error relative to the total voxels increased from 48%

Machine learning is a powerful approach for fitting microstructural models to diffusion MRI data. Early machine learning microstructure imaging implementations trained regressors to estimate model parameters in a supervised way, using synthetic training data with known ground truth. However, a drawback of this approach is that the choice of training data impacts fitted parameter values. Self-supervised learning is emerging as an attractive alternative to supervised learning in this context. Thus far, both supervised and self-supervised learning have typically been applied to isotropic models, such as intravoxel incoherent motion (IVIM), as opposed to models where the directionality of anisotropic structures is also estimated. In this paper, we demonstrate self-supervised machine learning model fitting for a directional microstructural model. In particular, we fit a combined T1-ball-stick model to the multidimensional diffusion (MUDI) challenge diffusion-relaxation dataset. Our self-supervised approach shows clear improvements in parameter estimation and computational time, for both simulated and in-vivo brain data, compared to standard non-linear least squares fitting. Code for the artificial neural net constructed for this study is available for public use from the following GitHub repository: https://github.com/jplte/deep-T1-ball-stick, Comment: Oral Presentation in: Computational Diffusion MRI Workshop (CDMRI) at Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022

Deep learning algorithms for predicting neuroimaging data have shown considerable promise in various applications. Prior work has demonstrated that deep learning models that take advantage of the data's 3D structure can outperform standard machine learning on several learning tasks. However, most prior research in this area has focused on neuroimaging data from adults. Within the Adolescent Brain and Cognitive Development (ABCD) dataset, a large longitudinal development study, we examine structural MRI data to predict gender and identify gender-related changes in brain structure. Results demonstrate that gender prediction accuracy is exceptionally high (>97%) with training epochs >200 and that this accuracy increases with age. Brain regions identified as the most discriminative in the task under study include predominantly frontal areas and the temporal lobe. When evaluating gender predictive changes specific to a two-year increase in age, a broader set of visual, cingulate, and insular regions are revealed. Our findings show a robust gender-related structural brain change pattern, even over a small age range. This suggests that it might be possible to study how the brain changes during adolescence by looking at how these changes are related to different behavioral and environmental factors., Comment: I submitted the wrong paper

Magnetic resonance imaging (MRI) data is heterogeneous due to differences in device manufacturers, scanning protocols, and inter-subject variability. A conventional way to mitigate MR image heterogeneity is to apply preprocessing transformations such as anatomy alignment, voxel resampling, signal intensity equalization, image denoising, and localization of regions of interest. Although a preprocessing pipeline standardizes image appearance, its influence on the quality of image segmentation and on other downstream tasks in deep neural networks has never been rigorously studied. We conduct experiments on three publicly available datasets and evaluate the effect of different preprocessing steps in intra- and inter-dataset training scenarios. Our results demonstrate that most popular standardization steps add no value to the network performance; moreover, preprocessing can hamper model performance. We suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization. Finally, we show that the contribution of skull-stripping in data preprocessing is almost negligible if measured in terms of estimated tumor volume. We show that the only essential transformation for accurate deep learning analysis is the unification of voxel spacing across the dataset. In contrast, inter-subjects anatomy alignment in the form of non-rigid atlas registration is not necessary and intensity equalization steps (denoising, bias-field correction and histogram matching) do not improve models' performance. The study code is accessible online https://github.com/MedImAIR/brain-mri-processing-pipeline

Brain metastases occur when tumour cells developed anywhere in the body spread to the brain. Radiotherapy (RT) is a treatment option for brain metastases that aims to eliminate the tumor cells within the brain, but it also causes healthy tissue damage that can lead to cognitive decline. In order to measure the effects of different RT treatments on the patients, the quality of life (QoL) is measured to determine which one leads to the best cognitive outcome. For this purpose, tests with varying degrees of specificity, such as, neurocognitive assessment (NCA), patient reported outcome (PRO) and Karnofsky Performance Scale (KPS) aim to quantify the cognitive change of the patients before and after RT. However, the high cost of NCAs, patient dependency of PROs and unreliability of KPS highlight the need for a new approach to measure the cognitive state of patients. Such novel approach could estimate the QoL of the patients solely based on anatomical markers from MRI scans, reducing costs and patient interactions alike. In order to develop such tool, the anatomical markers related to cognitive must be identified first. In response, we performed a systematic review to analyse existing literature on the anatomical changes captured in MRI that have been linked to cognitive decline. We searched the Pubmed database where studies that evaluated cognitive change as a result of a specific anatomical change after RT were selected. Out of 298 publications, 16 were chosen, wherein tumor morphology, lesion number and location, peritumoral edema and necrosis were identified as the most relevant anatomical markers for the estimation of the QoL of brain metastatic patients based on MRI data. We identified multiple limitations within our review regarding inhomogeneous patient cohorts, low-quality image processing and the lack of correlation between the anatomical changes and the effect that might have in the QoL of patients. Consequently, although the studies reviewed all reached simila

The recent introduction of wireless head-mounted displays (HMD) promises to enhance 3D image visualization by immersing the user into 3D morphology. This work introduces a prototype holographic augmented reality (HAR) interface for the 3D visualization of magnetic resonance imaging (MRI) data for the purpose of planning neurosurgical procedures. The computational platform generates a HAR scene that fuses pre-operative MRI sets, segmented anatomical structures, and a tubular tool for planning an access path to the targeted pathology. The operator can manipulate the presented images and segmented structures and perform path-planning using voice and gestures. On-the-fly, the software uses defined forbidden-regions to prevent the operator from harming vital structures. In silico studies using the platform with a HoloLens HMD assessed its functionality and the computational load and memory for different tasks. A preliminary qualitative evaluation revealed that holographic visualization of high-resolution 3D MRI data offers an intuitive and interactive perspective of the complex brain vasculature and anatomical structures. This initial work suggests that immersive experiences may be an unparalleled tool for planning neurosurgical procedures. © 2021, Society for Imaging Informatics in Medicine.