Enhancing Hierarchical Transformers for Whole Brain Segmentation with Intracranial Measurements Integration.

Whole brain segmentation with magnetic resonance imaging (MRI) enables the non-invasive measurement of brain regions, including total intracranial volume (TICV) and posterior fossa volume (PFV). Enhancing the existing whole brain segmentation methodology to incorporate intracranial measurements offers a heightened level of comprehensiveness in the analysis of brain structures. Despite its potential, the task of generalizing deep learning techniques for intracranial measurements faces data availability constraints due to limited manually annotated atlases encompassing whole brain and TICV/PFV labels. In this paper, we enhancing the hierarchical transformer UNesT for whole brain segmentation to achieve segmenting whole brain with 133 classes and TICV/PFV simultaneously. To address the problem of data scarcity, the model is first pretrained on 4859 T1-weighted (T1w) 3D volumes sourced from 8 different sites. These volumes are processed through a multi-atlas segmentation pipeline for label generation, while TICV/PFV labels are unavailable. Subsequently, the model is finetuned with 45 T1w 3D volumes from Open Access Series Imaging Studies (OASIS) where both 133 whole brain classes and TICV/PFV labels are available. We evaluate our method with Dice similarity coefficients(DSC). We show that our model is able to conduct precise TICV/PFV estimation while maintaining the 132 brain regions performance at a comparable level. Code and trained model are available at: https://github.com/MASILab/UNesT/wholebrainSeg.

Quantitative assessment of brain structural abnormalities in children with autism spectrum disorder based on artificial intelligence automatic brain segmentation technology and machine learning methods.

RATIONALE AND OBJECTIVES: To explore the characteristics of brain structure in Chinese children with autism spectrum disorder (ASD) using artificial intelligence automatic brain segmentation technique, and to diagnose children with ASD using machine learning (ML) methods in combination with structural magnetic resonance imaging (sMRI) features. METHODS: A total of 60 ASD children and 48 age- and sex-matched typically developing (TD) children were prospectively enrolled from January 2023 to April 2024. All subjects were scanned using 3D-T1 sequences. Automated brain segmentation techniques were utilized to obtain the standardized volume of each brain structure (the ratio of the absolute volume of brain structure to the whole brain volume). The standardized volumes of each brain structure in the two groups were statistically compared, and the volume data of brain areas with significant differences were combined with ML methods to diagnose and predict ASD patients. RESULTS: Compared with the TD group, the volumes of the right lateral orbitofrontal cortex, right medial orbitofrontal cortex, right pars opercularis, right pars triangularis, left hippocampus, bilateral parahippocampal gyrus, left fusiform gyrus, right superior temporal gyrus, bilateral insula, bilateral inferior parietal cortex, right precuneus cortex, bilateral putamen, left pallidum, and right thalamus were significantly increased in the ASD group (P< 0.05). Among six ML algorithms, support vector machine (SVM) and adaboost (AB) had better performance in differentiating subjects with ASD from those TD children, with their average area under curve (AUC) reaching 0.91 and 0.92, respectively. CONCLUSION: Automatic brain segmentation technology based on artificial intelligence can rapidly and directly measure and display the volume of brain structures in children with autism spectrum disorder and typically developing children. Children with ASD show abnormalities in multiple brain structures, and when paired with sMRI features, ML algorithms perform well in the diagnosis of ASD.

Methodological challenges of measuring brain volumes and cortical thickness in idiopathic normal pressure hydrocephalus with a surface-based approach.

Identifying disease-specific imaging features of idiopathic Normal Pressure Hydrocephalus (iNPH) is crucial to develop accurate diagnoses, although the abnormal brain anatomy of patients with iNPH creates challenges in neuroimaging analysis. We quantified cortical thickness and volume using FreeSurfer 7.3.2 in 19 patients with iNPH, 28 patients with Alzheimer's disease (AD), and 30 healthy controls (HC). We noted the frequent need for manual correction of the automated segmentation in iNPH and examined the effect of correction on the results. We identified statistically significant higher proportion of volume changes associated with manual edits in individuals with iNPH compared to both HC and patients with AD. Changes in cortical thickness and volume related to manual correction were also partly correlated with the severity of radiological features of iNPH. We highlight the challenges posed by the abnormal anatomy in iNPH when conducting neuroimaging analysis and emphasise the importance of quality checking and correction in this clinical population.

Evaluating age-and gender-related changes in brain volumes in normal adult using synthetic magnetic resonance imaging.

OBJECTIVE: Normal aging is associated with brain volume change, and brain segmentation can be performed within an acceptable scan time using synthetic magnetic resonance imaging (MRI). This study aimed to investigate the brain volume changes in healthy adult according to age and gender, and provide age- and gender-specific reference values using synthetic MRI. METHODS: A total of 300 healthy adults (141 males, median age 48; 159 females, median age 50) were underwent synthetic MRI on 3.0 T. Brain parenchymal volume (BPV), gray matter volume (GMV), white matter volume (WMV), myelin volume (MYV), and cerebrospinal fluid volume (CSFV) were calculated using synthetic MRI software. These volumes were normalized by intracranial volume to normalized GMV (nGMV), normalized WMV (nWMV), normalized MYV (nMYV), normalized BPV (nBPV), and normalized CSFV (nCSFV). The normalized brain volumes were plotted against age in both males and females, and a curve fitting model that best explained the age dependence of brain volume was identified. The normalized brain volumes were compared between different age and gender groups. RESULTS: The approximate curves of nGMV, nWMV, nCSFV, nBPV, and nMYV were best fitted by quadratic curves. The nBPV decreased monotonously through all ages in both males and females, while the changes of nCSFV showed the opposite trend. The nWMV and nMYV in both males and females increased gradually and then decrease with age. In early adulthood (20s), nWMV and nMYV in males were lower and peaked later than that in females (p < .005). The nGMV in both males and females decreased in the early adulthood until the 30s and then remains stable. A significant decline in nWMV, nBPV, and nMYV was noted in the 60s (Turkey test, p < .05). CONCLUSIONS: Our study provides age- and gender-specific reference values of brain volumes using synthetic MRI, which could be objective tools for discriminating brain disorders from healthy brains.

Semi-supervised learning framework with shape encoding for neonatal ventricular segmentation from 3D ultrasound.

BACKGROUND: Three-dimensional (3D) ultrasound (US) imaging has shown promise in non-invasive monitoring of changes in the lateral brain ventricles of neonates suffering from intraventricular hemorrhaging. Due to the poorly defined anatomical boundaries and low signal-to-noise ratio, fully supervised methods for segmentation of the lateral ventricles in 3D US images require a large dataset of annotated images by trained physicians, which is tedious, time-consuming, and expensive. Training fully supervised segmentation methods on a small dataset may lead to overfitting and hence reduce its generalizability. Semi-supervised learning (SSL) methods for 3D US segmentation may be able to address these challenges but most existing SSL methods have been developed for magnetic resonance or computed tomography (CT) images. PURPOSE: To develop a fast, lightweight, and accurate SSL method, specifically for 3D US images, that will use unlabeled data towards improving segmentation performance. METHODS: We propose an SSL framework that leverages the shape-encoding ability of an autoencoder network to enforce complex shape and size constraints on a 3D U-Net segmentation model. The autoencoder created pseudo-labels, based on the 3D U-Net predicted segmentations, that enforces shape constraints. An adversarial discriminator network then determined whether images came from the labeled or unlabeled data distributions. We used 887 3D US images, of which 87 had manually annotated labels and 800 images were unlabeled. Training/validation/testing sets of 25/12/50, 25/12/25 and 50/12/25 images were used for model experimentation. The Dice similarity coefficient (DSC), mean absolute surface distance (MAD), and absolute volumetric difference (VD) were used as metrics for comparing to other benchmarks. The baseline benchmark was the fully supervised vanilla 3D U-Net while dual task consistency, shape-aware semi-supervised network, correlation-aware mutual learning, and 3D U-Net Ensemble models were used as state-of-the-art benchmarks with DSC, MAD, and VD as comparison metrics. The Wilcoxon signed-rank test was used to test statistical significance between algorithms for DSC and VD with the threshold being p < 0.05 and corrected to p < 0.01 using the Bonferroni correction. The random-access memory (RAM) trace and number of trainable parameters were used to compare the computing efficiency between models. RESULTS: Relative to the baseline 3D U-Net model, our shape-encoding SSL method reported a mean DSC improvement of 6.5%, 7.7%, and 4.1% with a 95% confidence interval of 4.2%, 5.7%, and 2.1% using image data splits of 25/12/50, 25/12/25, and 50/12/25, respectively. Our method only used a 1GB increase in RAM compared to the baseline 3D U-Net and required less than half the RAM and trainable parameters compared to the 3D U-Net ensemble method. CONCLUSIONS: Based on our extensive literature survey, this is one of the first reported works to propose an SSL method designed for segmenting organs in 3D US images and specifically one that incorporates unlabeled data for segmenting neonatal cerebral lateral ventricles. When compared to the state-of-the-art SSL and fully supervised learning methods, our method yielded the highest DSC and lowest VD while being computationally efficient.

Autism-associated brain differences can be observed in utero using MRI.

Developmental changes that occur before birth are thought to be associated with the development of autism spectrum disorders. Identifying anatomical predictors of early brain development may contribute to our understanding of the neurobiology of autism spectrum disorders and allow for earlier and more effective identification and treatment of autism spectrum disorders. In this study, we used retrospective clinical brain magnetic resonance imaging data from fetuses who were diagnosed with autism spectrum disorders later in life (prospective autism spectrum disorders) in order to identify the earliest magnetic resonance imaging-based regional volumetric biomarkers. Our results showed that magnetic resonance imaging-based autism spectrum disorder biomarkers can be found as early as in the fetal period and suggested that the increased volume of the insular cortex may be the most promising magnetic resonance imaging-based fetal biomarker for the future emergence of autism spectrum disorders, along with some additional, potentially useful changes in regional volumes and hemispheric asymmetries.

suMRak: a multi-tool solution for preclinical brain MRI data analysis.

Introduction: Magnetic resonance imaging (MRI) is invaluable for understanding brain disorders, but data complexity poses a challenge in experimental research. In this study, we introduce suMRak, a MATLAB application designed for efficient preclinical brain MRI analysis. SuMRak integrates brain segmentation, volumetry, image registration, and parameter map generation into a unified interface, thereby reducing the number of separate tools that researchers may require for straightforward data handling. Methods and implementation: All functionalities of suMRak are implemented using the MATLAB App Designer and the MATLAB-integrated Python engine. A total of six helper applications were developed alongside the main suMRak interface to allow for a cohesive and streamlined workflow. The brain segmentation strategy was validated by comparing suMRak against manual segmentation and ITK-SNAP, a popular open-source application for biomedical image segmentation. Results: When compared with the manual segmentation of coronal mouse brain slices, suMRak achieved a high Sørensen-Dice similarity coefficient (0.98 ± 0.01), approaching manual accuracy. Additionally, suMRak exhibited significant improvement (p = 0.03) when compared to ITK-SNAP, particularly for caudally located brain slices. Furthermore, suMRak was capable of effectively analyzing preclinical MRI data obtained in our own studies. Most notably, the results of brain perfusion map registration to T2-weighted images were shown, improving the topographic connection to anatomical areas and enabling further data analysis to better account for the inherent spatial distortions of echoplanar imaging. Discussion: SuMRak offers efficient MRI data processing of preclinical brain images, enabling researchers' consistency and precision. Notably, the accelerated brain segmentation, achieved through K-means clustering and morphological operations, significantly reduces processing time and allows for easier handling of larger datasets.

Neural deformation fields for template-based reconstruction of cortical surfaces from MRI.

The reconstruction of cortical surfaces is a prerequisite for quantitative analyses of the cerebral cortex in magnetic resonance imaging (MRI). Existing segmentation-based methods separate the surface registration from the surface extraction, which is computationally inefficient and prone to distortions. We introduce Vox2Cortex-Flow (V2C-Flow), a deep mesh-deformation technique that learns a deformation field from a brain template to the cortical surfaces of an MRI scan. To this end, we present a geometric neural network that models the deformation-describing ordinary differential equation in a continuous manner. The network architecture comprises convolutional and graph-convolutional layers, which allows it to work with images and meshes at the same time. V2C-Flow is not only very fast, requiring less than two seconds to infer all four cortical surfaces, but also establishes vertex-wise correspondences to the template during reconstruction. In addition, V2C-Flow is the first approach for cortex reconstruction that models white matter and pial surfaces jointly, therefore avoiding intersections between them. Our comprehensive experiments on internal and external test data demonstrate that V2C-Flow results in cortical surfaces that are state-of-the-art in terms of accuracy. Moreover, we show that the established correspondences are more consistent than in FreeSurfer and that they can directly be utilized for cortex parcellation and group analyses of cortical thickness.

CT-based volumetric measures obtained through deep learning: Association with biomarkers of neurodegeneration.

INTRODUCTION: Cranial computed tomography (CT) is an affordable and widely available imaging modality that is used to assess structural abnormalities, but not to quantify neurodegeneration. Previously we developed a deep-learning-based model that produced accurate and robust cranial CT tissue classification. MATERIALS AND METHODS: We analyzed 917 CT and 744 magnetic resonance (MR) scans from the Gothenburg H70 Birth Cohort, and 204 CT and 241 MR scans from participants of the Memory Clinic Cohort, Singapore. We tested associations between six CT-based volumetric measures (CTVMs) and existing clinical diagnoses, fluid and imaging biomarkers, and measures of cognition. RESULTS: CTVMs differentiated cognitively healthy individuals from dementia and prodromal dementia patients with high accuracy levels comparable to MR-based measures. CTVMs were significantly associated with measures of cognition and biochemical markers of neurodegeneration. DISCUSSION: These findings suggest the potential future use of CT-based volumetric measures as an informative first-line examination tool for neurodegenerative disease diagnostics after further validation. HIGHLIGHTS: Computed tomography (CT)-based volumetric measures can distinguish between patients with neurodegenerative disease and healthy controls, as well as between patients with prodromal dementia and controls. CT-based volumetric measures associate well with relevant cognitive, biochemical, and neuroimaging markers of neurodegenerative diseases. Model performance, in terms of brain tissue classification, was consistent across two cohorts of diverse nature. Intermodality agreement between our automated CT-based and established magnetic resonance (MR)-based image segmentations was stronger than the agreement between visual CT and MR imaging assessment.

Reproducibility evaluation of the effects of MRI defacing on brain segmentation.

Purpose: Recent advances in magnetic resonance (MR) scanner quality and the rapidly improving nature of facial recognition software have necessitated the introduction of MR defacing algorithms to protect patient privacy. As a result, there are a number of MR defacing algorithms available to the neuroimaging community, with several appearing in just the last 5 years. While some qualities of these defacing algorithms, such as patient identifiability, have been explored in the previous works, the potential impact of defacing on neuroimage processing has yet to be explored. Approach: We qualitatively evaluate eight MR defacing algorithms on 179 subjects from the OASIS-3 cohort and 21 subjects from the Kirby-21 dataset. We also evaluate the effects of defacing on two neuroimaging pipelines-SLANT and FreeSurfer-by comparing the segmentation consistency between the original and defaced images. Results: Defacing can alter brain segmentation and even lead to catastrophic failures, which are more frequent with some algorithms, such as Quickshear, MRI_Deface, and FSL_deface. Compared to FreeSurfer, SLANT is less affected by defacing. On outputs that pass the quality check, the effects of defacing are less pronounced than those of rescanning, as measured by the Dice similarity coefficient. Conclusions: The effects of defacing are noticeable and should not be disregarded. Extra attention, in particular, should be paid to the possibility of catastrophic failures. It is crucial to adopt a robust defacing algorithm and perform a thorough quality check before releasing defaced datasets. To improve the reliability of analysis in scenarios involving defaced MRIs, it is encouraged to include multiple brain segmentation pipelines.

Dimensionality Reduction Hybrid U-Net for Brain Extraction in Magnetic Resonance Imaging.

In various applications, such as disease diagnosis, surgical navigation, human brain atlas analysis, and other neuroimage processing scenarios, brain extraction is typically regarded as the initial stage in MRI image processing. Whole-brain semantic segmentation algorithms, such as U-Net, have demonstrated the ability to achieve relatively satisfactory results even with a limited number of training samples. In order to enhance the precision of brain semantic segmentation, various frameworks have been developed, including 3D U-Net, slice U-Net, and auto-context U-Net. However, the processing methods employed in these models are relatively complex when applied to 3D data models. In this article, we aim to reduce the complexity of the model while maintaining appropriate performance. As an initial step to enhance segmentation accuracy, the preprocessing extraction of full-scale information from magnetic resonance images is performed with a cluster tool. Subsequently, three multi-input hybrid U-Net model frameworks are tested and compared. Finally, we propose utilizing a fusion of two-dimensional segmentation outcomes from different planes to attain improved results. The performance of the proposed framework was tested using publicly accessible benchmark datasets, namely LPBA40, in which we obtained Dice overlap coefficients of 98.05%. Improvement was achieved via our algorithm against several previous studies.

Reproducibility and Reliability of Computing Models in Segmentation and Volumetric Measurement of Brain.

Background: Segmentation and morphometric measurement of brain tissue and regions from non-invasive magnetic resonance images have clinical and research applications. Several software tools and models have been developed by different research groups which are increasingly used for segmentation and morphometric measurements. Variability in results has been observed in the imaging data processed with different neuroimaging pipelines which have increased the focus on standardization. Purpose: The availability of several tools and models for brain morphometry poses challenges as an analysis done on the same set of data using different sets of tools and pipelines may result in different results and interpretations and there is a need for understanding the reliability and accuracy of such models. Methods: T1-weighted (T1-w) brain volumes from the publicly available OASIS3 dataset have been analysed using recent versions of FreeSurfer, FSL-FAST, CAT12, and ANTs pipelines. grey matter (GM), white matter (WM), and estimated total intracranial volume (eTIV) have been extracted and compared for inter-method variability and accuracy. Results: All four methods are consistent and strongly reproducible in their measurement across subjects however there is a significant degree of variability between these methods. Conclusion: CAT12 and FreeSurfer methods have the highest degree of agreement in tissue class segmentation and are most reproducible compared to others.

UNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation.

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realizes global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissue structures. To address such challenges and inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting of multiple modalities, anatomies, and a wide range of tissue classes, including 133 structures in the brain, 14 organs in the abdomen, 4 hierarchical components in the kidneys, inter-connected kidney tumors and brain tumors. We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in a single network, outperforming prior state-of-the-art method SLANT27 ensembled with 27 networks. Our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively. Code, pre-trained models, and use case pipeline are available at: https://github.com/MASILab/UNesT.

Brain MRI Segmentation using Template-Based Training and Visual Perception Augmentation.

Deep learning models usually require sufficient training data to achieve high accuracy, but obtaining labeled data can be time-consuming and labor-intensive. Here we introduce a template-based training method to train a 3D U-Net model from scratch using only one population-averaged brain MRI template and its associated segmentation label. The process incorporated visual perception augmentation to enhance the model's robustness in handling diverse image inputs and mitigating overfitting. Leveraging this approach, we trained 3D U-Net models for mouse, rat, marmoset, rhesus, and human brain MRI to achieve segmentation tasks such as skull-stripping, brain segmentation, and tissue probability mapping. This tool effectively addresses the limited availability of training data and holds significant potential for expanding deep learning applications in image analysis, providing researchers with a unified solution to train deep neural networks with only one image sample.

Semi-Automatic GUI Platform to Characterize Brain Development in Preterm Children Using Ultrasound Images.

The third trimester of pregnancy is the most critical period for human brain development, during which significant changes occur in the morphology of the brain. The development of sulci and gyri allows for a considerable increase in the brain surface. In preterm newborns, these changes occur in an extrauterine environment that may cause a disruption of the normal brain maturation process. We hypothesize that a normalized atlas of brain maturation with cerebral ultrasound images from birth to term equivalent age will help clinicians assess these changes. This work proposes a semi-automatic Graphical User Interface (GUI) platform for segmenting the main cerebral sulci in the clinical setting from ultrasound images. This platform has been obtained from images of a cerebral ultrasound neonatal database images provided by two clinical researchers from the Hospital Sant Joan de Déu in Barcelona, Spain. The primary objective is to provide a user-friendly design platform for clinicians for running and visualizing an atlas of images validated by medical experts. This GUI offers different segmentation approaches and pre-processing tools and is user-friendly and designed for running, visualizing images, and segmenting the principal sulci. The presented results are discussed in detail in this paper, providing an exhaustive analysis of the proposed approach's effectiveness.

A reproducibility evaluation of the effects of MRI defacing on brain segmentation.

Purpose: Recent advances in magnetic resonance (MR) scanner quality and the rapidly improving nature of facial recognition software have necessitated the introduction of MR defacing algorithms to protect patient privacy. As a result, there are a number of MR defacing algorithms available to the neuroimaging community, with several appearing in just the last five years. While some qualities of these defacing algorithms, such as patient identifiability, have been explored in previous works, the potential impact of defacing on neuroimage processing has yet to be explored. Approach: We qualitatively evaluate eight MR defacing algorithms on 179 subjects from the OASIS-3 cohort and the 21 subjects from the Kirby-21 dataset. We also evaluate the effects of defacing on two neuroimaging pipelines-SLANT and FreeSurfer-by comparing the segmentation consistency between the original and defaced images. Results: Defacing can alter brain segmentation and even lead to catastrophic failures, which are more frequent with some algorithms such as Quickshear, MRI_Deface, and FSL_deface. Compared to FreeSurfer, SLANT is less affected by defacing. On outputs that pass the quality check, the effects of defacing are less pronounced than those of rescanning, as measured by the Dice similarity coefficient. Conclusions: The effects of defacing are noticeable and should not be disregarded. Extra attention, in particular, should be paid to the possibility of catastrophic failures. It is crucial to adopt a robust defacing algorithm and perform a thorough quality check before releasing defaced datasets. To improve the reliability of analysis in scenarios involving defaced MRIs, it's encouraged to include multiple brain segmentation pipelines.

Deep whole brain segmentation of 7T structural MRI.

7T magnetic resonance imaging (MRI) has the potential to drive our understanding of human brain function through new contrast and enhanced resolution. Whole brain segmentation is a key neuroimaging technique that allows for region-by-region analysis of the brain. Segmentation is also an important preliminary step that provides spatial and volumetric information for running other neuroimaging pipelines. Spatially localized atlas network tiles (SLANT) is a popular 3D convolutional neural network (CNN) tool that breaks the whole brain segmentation task into localized sub-tasks. Each sub-task involves a specific spatial location handled by an independent 3D convolutional network to provide high resolution whole brain segmentation results. SLANT has been widely used to generate whole brain segmentations from structural scans acquired on 3T MRI. However, the use of SLANT for whole brain segmentation from structural 7T MRI scans has not been successful due to the inhomogeneous image contrast usually seen across the brain in 7T MRI. For instance, we demonstrate the mean percent difference of SLANT label volumes between a 3T scan-rescan is approximately 1.73%, whereas its 3T-7T scan-rescan counterpart has higher differences around 15.13%. Our approach to address this problem is to register the whole brain segmentation performed on 3T MRI to 7T MRI and use this information to finetune SLANT for structural 7T MRI. With the finetuned SLANT pipeline, we observe a lower mean relative difference in the label volumes of ~8.43% acquired from structural 7T MRI data. Dice similarity coefficient between SLANT segmentation on the 3T MRI scan and the after finetuning SLANT segmentation on the 7T MRI increased from 0.79 to 0.83 with p<0.01. These results suggest finetuning of SLANT is a viable solution for improving whole brain segmentation on high resolution 7T structural imaging.

A Fully Automated Visual Grading System for White Matter Hyperintensities of T2-Fluid Attenuated Inversion Recovery Magnetic Resonance Imaging.

BACKGROUND: The Fazekas scale is one of the most commonly used visual grading systems for white matter hyperintensity (WMH) for brain disorders like dementia from T2-fluid attenuated inversion recovery magnetic resonance (MR) images (T2-FLAIRs). However, the visual grading of the Fazekas scale suffers from low-intra and inter-rater reliability and high labor-intensive work. Therefore, we developed a fully automated visual grading system using quantifiable measurements. METHODS: Our approach involves four stages: (1) the deep learning-based segmentation of ventricles and WMH lesions, (2) the categorization into periventricular white matter hyperintensity (PWMH) and deep white matter hyperintensity (DWMH), (3) the WMH diameter measurement, and (4) automated scoring, following the quantifiable method modified for Fazekas grading. We compared the performances of our method and that of the modified Fazekas scale graded by three neuroradiologists for 404 subjects with T2-FLAIR utilized from a clinical site in Korea. RESULTS: The Krippendorff's alpha across our method and raters (A) versus those only between the radiologists (R) were comparable, showing substantial (0.694 vs. 0.732; 0.658 vs. 0.671) and moderate (0.579 vs. 0.586) level of agreements for the modified Fazekas, the DWMH, and the PWMH scales, respectively. Also, the average of areas under the receiver operating characteristic curve between the radiologists (0.80 ± 0.09) and the radiologists against our approach (0.80 ± 0.03) was comparable. CONCLUSIONS: Our fully automated visual grading system for WMH demonstrated comparable performance to the radiologists, which we believe has the potential to assist the radiologist in clinical findings with unbiased and consistent scoring.

RU-Net: skull stripping in rat brain MR images after ischemic stroke with rat U-Net.

BACKGROUND: Experimental ischemic stroke models play a fundamental role in interpreting the mechanism of cerebral ischemia and appraising the development of pathological extent. An accurate and automatic skull stripping tool for rat brain image volumes with magnetic resonance imaging (MRI) are crucial in experimental stroke analysis. Due to the deficiency of reliable rat brain segmentation methods and motivated by the demand for preclinical studies, this paper develops a new skull stripping algorithm to extract the rat brain region in MR images after stroke, which is named Rat U-Net (RU-Net). METHODS: Based on a U-shape like deep learning architecture, the proposed framework integrates batch normalization with the residual network to achieve efficient end-to-end segmentation. A pooling index transmission mechanism between the encoder and decoder is exploited to reinforce the spatial correlation. Two different modalities of diffusion-weighted imaging (DWI) and T2-weighted MRI (T2WI) corresponding to two in-house datasets with each consisting of 55 subjects were employed to evaluate the performance of the proposed RU-Net. RESULTS: Extensive experiments indicated great segmentation accuracy across diversified rat brain MR images. It was suggested that our rat skull stripping network outperformed several state-of-the-art methods and achieved the highest average Dice scores of 98.04% (p < 0.001) and 97.67% (p < 0.001) in the DWI and T2WI image datasets, respectively. CONCLUSION: The proposed RU-Net is believed to be potential for advancing preclinical stroke investigation and providing an efficient tool for pathological rat brain image extraction, where accurate segmentation of the rat brain region is fundamental.

An open-source tool for longitudinal whole-brain and white matter lesion segmentation.

In this paper we describe and validate a longitudinal method for whole-brain segmentation of longitudinal MRI scans. It builds upon an existing whole-brain segmentation method that can handle multi-contrast data and robustly analyze images with white matter lesions. This method is here extended with subject-specific latent variables that encourage temporal consistency between its segmentation results, enabling it to better track subtle morphological changes in dozens of neuroanatomical structures and white matter lesions. We validate the proposed method on multiple datasets of control subjects and patients suffering from Alzheimer's disease and multiple sclerosis, and compare its results against those obtained with its original cross-sectional formulation and two benchmark longitudinal methods. The results indicate that the method attains a higher test-retest reliability, while being more sensitive to longitudinal disease effect differences between patient groups. An implementation is publicly available as part of the open-source neuroimaging package FreeSurfer.