Robust skull stripping using multiple MR image contrasts insensitive to pathology

Synthetic data in generalizable, learning-based neuroimaging

Synthetic data have emerged as an attractive option for developing machine-learning methods in human neuroimaging, particularly in magnetic resonance imaging (MRI)-a modality where image contrast depends enormously on acquisition hardware and parameters. This retrospective paper reviews a family of recently proposed methods, based on synthetic data, for generalizable machine learning in brain MRI analysis. Central to this framework is the concept of domain randomization, which involves training neural networks on a vastly diverse array of synthetically generated images with random contrast properties. This technique has enabled robust, adaptable models that are capable of handling diverse MRI contrasts, resolutions, and pathologies, while working out-of-the-box, without retraining. We have successfully applied this method to tasks such as whole-brain segmentation (SynthSeg), skull-stripping (SynthStrip), registration (SynthMorph, EasyReg), super-resolution, and MR contrast transfer (SynthSR). Beyond these applications, the paper discusses other possible use cases and future work in our methodology. Neural networks trained with synthetic data enable the analysis of clinical MRI, including large retrospective datasets, while greatly alleviating (and sometimes eliminating) the need for substantial labeled datasets, and offer enormous potential as robust tools to address various research goals.

Biologically informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post treatment glioblastoma

Intratumoral heterogeneity poses a significant challenge to the diagnosis and treatment of recurrent glioblastoma. This study addresses the need for non-invasive approaches to map heterogeneous landscape of histopathological alterations throughout the entire lesion for each patient. We developed BioNet, a biologically-informed neural network, to predict regional distributions of two primary tissue-specific gene modules: proliferating tumor (Pro) and reactive/inflammatory cells (Inf). BioNet significantly outperforms existing methods (p < 2e-26). In cross-validation, BioNet achieved AUCs of 0.80 (Pro) and 0.81 (Inf), with accuracies of 80% and 75%, respectively. In blind tests, BioNet achieved AUCs of 0.80 (Pro) and 0.76 (Inf), with accuracies of 81% and 74%. Competing methods had AUCs lower or around 0.6 and accuracies lower or around 70%. BioNet's voxel-level prediction maps reveal intratumoral heterogeneity, potentially improving biopsy targeting and treatment evaluation. This non-invasive approach facilitates regular monitoring and timely therapeutic adjustments, highlighting the role of ML in precision medicine.

Effect of Human Head Shape on the Risk of Traumatic Brain Injury: A Gaussian Process Regression-Based Machine Learning Approach

INTRODUCTION

Computational head injury models are promising tools for understanding and predicting traumatic brain injuries. However, most available head injury models are "average" models that employ a single set of head geometry (e.g., 50th-percentile U.S. male) without considering variability in these parameters across the human population. A significant variability of head shapes exists in U.S. Army soldiers, evident from the Anthropometric Survey of U.S. Army Personnel (ANSUR II). The objective of this study is to elucidate the effects of head shape on the predicted risk of traumatic brain injury from computational head injury models.

MATERIALS AND METHODS

Magnetic resonance imaging scans of 25 human subjects are collected. These images are registered to the standard MNI152 brain atlas, and the resulting transformation matrix components (called head shape parameters) are used to quantify head shapes of the subjects. A generative machine learning model is used to generate 25 additional head shape parameter datasets to augment our database. Head injury models are developed for these head shapes, and a rapid injurious head rotation event is simulated to obtain several brain injury predictor variables (BIPVs): Peak cumulative maximum principal strain (CMPS), average CMPS, and the volume fraction of brain exceeding an injurious CMPS threshold. A Gaussian process regression model is trained between head shape parameters and BIPVs, which is then used to study the relative sensitivity of the various BIPVs on individual head shape parameters. We distinguish head shape parameters into 2 types: Scaling components ${T_{xx}}$, ${T_{yy}}$, and ${T_{zz}}$ that capture the breadth, length, and height of the head, respectively, and shearing components (${T_{xy}},{T_{xz}},{T_{yx}},{T_{yz}},{T_{zx}}$, and ${T_{zy}}$) that capture the relative skewness of the head shape.

RESULTS

An overall positive correlation is evident between scaling components and BIPVs. Notably, a very high, positive correlation is seen between the BIPVs and the head volume. As an example, a 57% increase in peak CMPS was noted between the smallest and the largest investigated head volume parameters. The variation in shearing components ${T_{xy}},{T_{xz}},{T_{yx}},{T_{yz}},{T_{zx}}$, and ${T_{zy}}$ on average does not cause notable changes in the BIPVs. From the Gaussian process regression model, all 3 BIPVs showed an increasing trend with each of the 3 scaling components, but the BIPVs are found to be most sensitive to the height dimension of the head. From the Sobol sensitivity analysis, the ${T_{zz}}$ scaling parameter contributes nearly 60% to the total variance in peak and average CMPS; ${T_{yy}}$ contributes approximately 20%, whereas ${T_{xx}}$ contributes less than 5%. The remaining contribution is from the 6 shearing components. Unlike peak and average CMPS, the VF-CMPS BIPV is associated with relatively evenly distributed Sobol indices across the 3 scaling parameters. Furthermore, the contribution of shearing components on the total variance in this case is negligible.

CONCLUSIONS

Head shape has a considerable influence on the injury predictions of computational head injury models. Available "average" head injury models based on a 50th-percentile U.S. male are likely associated with considerable uncertainty. In general, larger head sizes correspond to greater BIPV magnitudes, which point to potentially a greater injury risk under rapid neck rotation for people with larger heads.

nBEST: Deep-learning-based non-human primates Brain Extraction and Segmentation Toolbox across ages, sites and species

Accurate processing and analysis of non-human primate (NHP) brain magnetic resonance imaging (MRI) serves an indispensable role in understanding brain evolution, development, aging, and diseases. Despite the accumulation of diverse NHP brain MRI datasets at various developmental stages and from various imaging sites/scanners, existing computational tools designed for human MRI typically perform poor on NHP data, due to huge differences in brain sizes, morphologies, and imaging appearances across species, sites, and ages, highlighting the imperative for NHP-specialized MRI processing tools. To address this issue, in this paper, we present a robust, generic, and fully automated computational pipeline, called non-human primates Brain Extraction and Segmentation Toolbox (nBEST), whose main functionality includes brain extraction, non-cerebrum removal, and tissue segmentation. Building on cutting-edge deep learning techniques by employing lifelong learning to flexibly integrate data from diverse NHP populations and innovatively constructing 3D U-NeXt architecture, nBEST can well handle structural NHP brain MR images from multi-species, multi-site, and multi-developmental-stage (from neonates to the elderly). We extensively validated nBEST based on, to our knowledge, the largest assemblage dataset in NHP brain studies, encompassing 1,469 scans with 11 species (e.g., rhesus macaques, cynomolgus macaques, chimpanzees, marmosets, squirrel monkeys, etc.) from 23 independent datasets. Compared to alternative tools, nBEST outperforms in precision, applicability, robustness, comprehensiveness, and generalizability, greatly benefiting downstream longitudinal, cross-sectional, and cross-species quantitative analyses. We have made nBEST an open-source toolbox (https://github.com/TaoZhong11/nBEST) and we are committed to its continual refinement through lifelong learning with incoming data to greatly contribute to the research field.

GNN-based structural information to improve DNN-based basal ganglia segmentation in children following early brain lesion

Analyzing the basal ganglia following an early brain lesion is crucial due to their noteworthy role in sensory-motor functions. However, the segmentation of these subcortical structures on MRI is challenging in children and is further complicated by the presence of a lesion. Although current deep neural networks (DNN) perform well in segmenting subcortical brain structures in healthy brains, they lack robustness when faced with lesion variability, leading to structural inconsistencies. Given the established spatial organization of the basal ganglia, we propose enhancing the DNN-based segmentation through post-processing with a graph neural network (GNN). The GNN conducts node classification on graphs encoding both class probabilities and spatial information regarding the regions segmented by the DNN. In this study, we focus on neonatal arterial ischemic stroke (NAIS) in children. The approach is evaluated on both healthy children and children after NAIS using three DNN backbones: U-Net, UNETr, and MSGSE-Net. The results show an improvement in segmentation performance, with an increase in the median Dice score by up to 4% and a reduction in the median Hausdorff distance (HD) by up to 93% for healthy children (from 36.45 to 2.57) and up to 91% for children suffering from NAIS (from 40.64 to 3.50). The performance of the method is compared with atlas-based methods. Severe cases of neonatal stroke result in a decline in performance in the injured hemisphere, without negatively affecting the segmentation of the contra-injured hemisphere. Furthermore, the approach demonstrates resilience to small training datasets, a widespread challenge in the medical field, particularly in pediatrics and for rare pathologies.

Assessing the Accuracy and Reproducibility of PARIETAL: A Deep Learning Brain Extraction Algorithm

BACKGROUND

Manual brain extraction from magnetic resonance (MR) images is time-consuming and prone to intra- and inter-rater variability. Several automated approaches have been developed to alleviate these constraints, including deep learning pipelines. However, these methods tend to reduce their performance in unseen magnetic resonance imaging (MRI) scanner vendors and different imaging protocols.

PURPOSE

To present and evaluate for clinical use PARIETAL, a pre-trained deep learning brain extraction method. We compare its reproducibility in a scan/rescan analysis and its robustness among scanners of different manufacturers.

STUDY TYPE

Retrospective.

POPULATION

Twenty-one subjects (12 women) with age range 22-48 years acquired using three different MRI scanner machines including scan/rescan in each of them.

FIELD STRENGTH/SEQUENCE

T1-weighted images acquired in a 3-T Siemens with magnetization prepared rapid gradient-echo sequence and two 1.5 T scanners, Philips and GE, with spin-echo and spoiled gradient-recalled (SPGR) sequences, respectively.

ASSESSMENT

Analysis of the intracranial cavity volumes obtained for each subject on the three different scanners and the scan/rescan acquisitions.

STATISTICAL TESTS

Parametric permutation tests of the differences in volumes to rank and statistically evaluate the performance of PARIETAL compared to state-of-the-art methods.

RESULTS

The mean absolute intracranial volume differences obtained by PARIETAL in the scan/rescan analysis were 1.88 mL, 3.91 mL, and 4.71 mL for Siemens, GE, and Philips scanners, respectively. PARIETAL was the best-ranked method on Siemens and GE scanners, while decreasing to Rank 2 on the Philips images. Intracranial differences for the same subject between scanners were 5.46 mL, 27.16 mL, and 30.44 mL for GE/Philips, Siemens/Philips, and Siemens/GE comparison, respectively. The permutation tests revealed that PARIETAL was always in Rank 1, obtaining the most similar volumetric results between scanners.

DATA CONCLUSION

PARIETAL accurately segments the brain and it generalizes to images acquired at different sites without the need of training or fine-tuning it again. PARIETAL is publicly available.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY STAGE: 2.

Neuroimaging Findings in US Government Personnel and Their Family Members Involved in Anomalous Health Incidents

Importance

US government personnel stationed internationally have reported anomalous health incidents (AHIs), with some individuals experiencing persistent debilitating symptoms.

Objective

To assess the potential presence of magnetic resonance imaging (MRI)-detectable brain lesions in participants with AHIs, with respect to a well-matched control group.

Design, Setting, and Participants

This exploratory study was conducted at the National Institutes of Health (NIH) Clinical Center and the NIH MRI Research Facility between June 2018 and November 2022. Eighty-one participants with AHIs and 48 age- and sex-matched control participants, 29 of whom had similar employment as the AHI group, were assessed with clinical, volumetric, and functional MRI. A high-quality diffusion MRI scan and a second volumetric scan were also acquired during a different session. The structural MRI acquisition protocol was optimized to achieve high reproducibility. Forty-nine participants with AHIs had at least 1 additional imaging session approximately 6 to 12 months from the first visit.

Exposure

AHIs.

Main Outcomes and Measures

Group-level quantitative metrics obtained from multiple modalities: (1) volumetric measurement, voxel-wise and region of interest (ROI)-wise; (2) diffusion MRI-derived metrics, voxel-wise and ROI-wise; and (3) ROI-wise within-network resting-state functional connectivity using functional MRI. Exploratory data analyses used both standard, nonparametric tests and bayesian multilevel modeling.

Results

Among the 81 participants with AHIs, the mean (SD) age was 42 (9) years and 49% were female; among the 48 control participants, the mean (SD) age was 43 (11) years and 42% were female. Imaging scans were performed as early as 14 days after experiencing AHIs with a median delay period of 80 (IQR, 36-544) days. After adjustment for multiple comparisons, no significant differences between participants with AHIs and control participants were found for any MRI modality. At an unadjusted threshold (P < .05), compared with control participants, participants with AHIs had lower intranetwork connectivity in the salience networks, a larger corpus callosum, and diffusion MRI differences in the corpus callosum, superior longitudinal fasciculus, cingulum, inferior cerebellar peduncle, and amygdala. The structural MRI measurements were highly reproducible (median coefficient of variation <1% across all global volumetric ROIs and <1.5% for all white matter ROIs for diffusion metrics). Even individuals with large differences from control participants exhibited stable longitudinal results (typically, <±1% across visits), suggesting the absence of evolving lesions. The relationships between the imaging and clinical variables were weak (median Spearman ρ = 0.10). The study did not replicate the results of a previously published investigation of AHIs.

Conclusions and Relevance

In this exploratory neuroimaging study, there were no significant differences in imaging measures of brain structure or function between individuals reporting AHIs and matched control participants after adjustment for multiple comparisons.

Hippocampal volume changes after (R,S)-ketamine administration in patients with major depressive disorder and healthy volunteers

The hippocampus and amygdala have been implicated in the pathophysiology and treatment of major depressive disorder (MDD). Preclinical models suggest that stress-related changes in these regions can be reversed by antidepressants, including ketamine. Clinical studies have identified reduced volumes in MDD that are thought to be potentiated by early life stress and worsened by repeated depressive episodes. This study used 3T and 7T structural magnetic resonance imaging data to examine longitudinal changes in hippocampal and amygdalar subfield volumes associated with ketamine treatment. Data were drawn from a previous double-blind, placebo-controlled, crossover trial of healthy volunteers (HVs) unmedicated individuals with treatment-resistant depression (TRD) (3T: 18 HV, 26 TRD, 7T: 17 HV, 30 TRD) who were scanned at baseline and twice following either a 40 min IV ketamine (0.5 mg/kg) or saline infusion (acute: 1-2 days, interim: 9-10 days post infusion). No baseline differences were noted between the two groups. At 10 days post-infusion, a slight increase was observed between ketamine and placebo scans in whole left amygdalar volume in individuals with TRD. No other differences were found between individuals with TRD and HVs at either field strength. These findings shed light on the timing of ketamine's effects on cortical structures.

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.

k-strip: A novel segmentation algorithm in k-space for the application of skull stripping

BACKGROUND AND OBJECTIVE

We present a novel deep learning-based skull stripping algorithm for magnetic resonance imaging (MRI) that works directly in the information rich complex valued k-space.

METHODS

Using four datasets from different institutions with a total of around 200,000 MRI slices, we show that our network can perform skull-stripping on the raw data of MRIs while preserving the phase information which no other skull stripping algorithm is able to work with. For two of the datasets, skull stripping performed by HD-BET (Brain Extraction Tool) in the image domain is used as the ground truth, whereas the third and fourth dataset comes with per-hand annotated brain segmentations.

RESULTS

All four datasets were very similar to the ground truth (DICE scores of 92 %-99 % and Hausdorff distances of under 5.5 pixel). Results on slices above the eye-region reach DICE scores of up to 99 %, whereas the accuracy drops in regions around the eyes and below, with partially blurred output. The output of k-Strip often has smoothed edges at the demarcation to the skull. Binary masks are created with an appropriate threshold.

CONCLUSION

With this proof-of-concept study, we were able to show the feasibility of working in the k-space frequency domain, preserving phase information, with consistent results. Besides preserving valuable information for further diagnostics, this approach makes an immediate anonymization of patient data possible, already before being transformed into the image domain. Future research should be dedicated to discovering additional ways the k-space can be used for innovative image analysis and further workflows.

Deep-learning model for diagnostic clue: detecting the dural tail sign for meningiomas on contrast-enhanced T1 weighted images

Background

Meningiomas are the most common primary central nervous system tumors, and magnetic resonance imaging (MRI), especially contrast-enhanced T1 weighted image (CE T1WI), is used as a fundamental imaging modality for the detection and analysis of the tumors. In this study, we propose an automated deep-learning model for meningioma detection using the dural tail sign.

Methods

The dataset included 123 patients with 3,824 dural tail signs on sagittal CE T1WI. The dataset was divided into training and test datasets based on specific time point, and 78 and 45 patients were comprised for the training and test dataset, respectively. To compensate for the small sample size of the training dataset, 39 additional patients with 69 dural tail signs from the open dataset were appended to the training dataset. A You Only Look Once (YOLO) v4 network was trained with sagittal CE T1WI to detect dural tail signs. The normal group dataset, comprised of 51 patients with no abnormal finding on MRI, was employed to evaluate the specificity of the trained model.

Results

The sensitivity and false positive average were 82.22% and 29.73, respectively, in the test dataset. The specificity and false positive average were 17.65% and 3.16, respectively, in the normal dataset. Most of the false-positive cases in the test dataset were enhancing vessels, misinterpreted as dural thickening.

Conclusions

The proposed model demonstrates an automated detection system for the dural tail sign to identify meningioma in general screening MRI. Our model can facilitate and alleviate radiologists' reading process by notifying the possibility of incidental dural mass based on dural tail sign detection.

Intelligent noninvasive meningioma grading with a fully automatic segmentation using interpretable multiparametric deep learning

OBJECTIVES

To establish a robust interpretable multiparametric deep learning (DL) model for automatic noninvasive grading of meningiomas along with segmentation.

METHODS

In total, 257 patients with pathologically confirmed meningiomas (162 low-grade, 95 high-grade) who underwent a preoperative brain MRI, including T2-weighted (T2) and contrast-enhanced T1-weighted images (T1C), were included in the institutional training set. A two-stage DL grading model was constructed for segmentation and classification based on multiparametric three-dimensional U-net and ResNet. The models were validated in the external validation set consisting of 61 patients with meningiomas (46 low-grade, 15 high-grade). Relevance-weighted Class Activation Mapping (RCAM) method was used to interpret the DL features contributing to the prediction of the DL grading model.

RESULTS

On external validation, the combined T1C and T2 model showed a Dice coefficient of 0.910 in segmentation and the highest performance for meningioma grading compared to the T2 or T1C only models, with an area under the curve (AUC) of 0.770 (95% confidence interval: 0.644-0.895) and accuracy, sensitivity, and specificity of 72.1%, 73.3%, and 71.7%, respectively. The AUC and accuracy of the combined DL grading model were higher than those of the human readers (AUCs of 0.675-0.690 and accuracies of 65.6-68.9%, respectively). The RCAM of the DL grading model showed activated maps at the surface regions of meningiomas indicating that the model recognized the features at the tumor margin for grading.

CONCLUSIONS

An interpretable multiparametric DL model combining T1C and T2 can enable fully automatic grading of meningiomas along with segmentation.

KEY POINTS

• The multiparametric DL model showed robustness in grading and segmentation on external validation. • The diagnostic performance of the combined DL grading model was higher than that of the human readers. • The RCAM interpreted that DL grading model recognized the meaningful features at the tumor margin for grading.

Image-based models of T-cell distribution identify a clinically meaningful response to a dendritic cell vaccine in patients with glioblastoma

BACKGROUND

Glioblastoma is an extraordinarily heterogeneous tumor, yet the current treatment paradigm is a "one size fits all" approach. Hundreds of glioblastoma clinical trials have been deemed failures because they did not extend median survival, but these cohorts are comprised of patients with diverse tumors. Current methods of assessing treatment efficacy fail to fully account for this heterogeneity.

METHODS

Using an image-based modeling approach, we predicted T-cell abundance from serial MRIs of patients enrolled in the dendritic cell (DC) vaccine clinical trial. T-cell predictions were quantified in both the contrast-enhancing and non-enhancing regions of the imageable tumor, and changes over time were assessed.

RESULTS

A subset of patients in a DC vaccine clinical trial, who had previously gone undetected, were identified as treatment responsive and benefited from prolonged survival. A mere two months after initial vaccine administration, responsive patients had a decrease in model-predicted T-cells within the contrast-enhancing region, with a simultaneous increase in the T2/FLAIR region.

CONCLUSIONS

In a field that has yet to see breakthrough therapies, these results highlight the value of machine learning in enhancing clinical trial assessment, improving our ability to prospectively prognosticate patient outcomes, and advancing the pursuit towards individualized medicine.

RAPID BRAIN MENINGES SURFACE RECONSTRUCTION WITH LAYER TOPOLOGY GUARANTEE

The meninges, located between the skull and brain, are composed of three membrane layers: the pia, the arachnoid, and the dura. Reconstruction of these layers can aid in studying volume differences between patients with neurodegenerative diseases and normal aging subjects. In this work, we use convolutional neural networks (CNNs) to reconstruct surfaces representing meningeal layer boundaries from magnetic resonance (MR) images. We first use the CNNs to predict the signed distance functions (SDFs) representing these surfaces while preserving their anatomical ordering. The marching cubes algorithm is then used to generate continuous surface representations; both the subarachnoid space (SAS) and the intracranial volume (ICV) are computed from these surfaces. The proposed method is compared to a state-of-the-art deformable model-based reconstruction method, and we show that our method can reconstruct smoother and more accurate surfaces using less computation time. Finally, we conduct experiments with volumetric analysis on both subjects with multiple sclerosis and healthy controls. For healthy and MS subjects, ICVs and SAS volumes are found to be significantly correlated to sex (p<0.01) and age (p ≤ 0.03) changes, respectively.

AUTOMATED VENTRICLE PARCELLATION AND EVAN'S RATIO COMPUTATION IN PRE- AND POST-SURGICAL VENTRICULOMEGALY

Normal pressure hydrocephalus (NPH) is a brain disorder associated with enlarged ventricles and multiple cognitive and motor symptoms. The degree of ventricular enlargement can be measured using magnetic resonance images (MRIs) and characterized quantitatively using the Evan's ratio (ER). Automatic computation of ER is desired to avoid the extra time and variations associated with manual measurements on MRI. Because shunt surgery is often used to treat NPH, it is necessary that this process be robust to image artifacts caused by the shunt and related implants. In this paper, we propose a 3D regions-of-interest aware (ROI-aware) network for segmenting the ventricles. The method achieves state-of-the-art performance on both pre-surgery MRIs and post-surgery MRIs with artifacts. Based on our segmentation results, we also describe an automated approach to compute ER from these results. Experimental results on multiple datasets demonstrate the potential of the proposed method to assist clinicians in the diagnosis and management of NPH.

Automatic analysis of skull thickness, scalp-to-cortex distance and association with age and sex in cognitively normal elderly

Personalized neurostimulation has been a potential treatment for many brain diseases, which requires insights into brain/skull geometry. Here, we developed an open source efficient pipeline BrainCalculator for automatically computing the skull thickness map, scalp-to-cortex distance (SCD), and brain volume based on T 1 -weighted magnetic resonance imaging (MRI) data. We examined the influence of age and sex cross-sectionally in 407 cognitively normal older adults (71.9±8.0 years, 60.2% female) from the ADNI. We demonstrated the compatibility of our pipeline with commonly used preprocessing packages and found that BrainSuite Skullfinder was better suited for such automatic analysis compared to FSL Brain Extraction Tool 2 and SPM12- based unified segmentation using ground truth. We found that the sphenoid bone and temporal bone were thinnest among the skull regions in both females and males. There was no increase in regional minimum skull thickness with age except in the female sphenoid bone. No sex difference in minimum skull thickness or SCD was observed. Positive correlations between age and SCD were observed, faster in females (0.307%/y) than males (0.216%/y) in temporal SCD. A negative correlation was observed between age and whole brain volume computed based on brain surface (females -1.031%/y, males -0.998%/y). In conclusion, we developed an automatic pipeline for MR-based skull thickness map, SCD, and brain volume analysis and demonstrated the sex-dependent association between minimum regional skull thickness, SCD and brain volume with age. This pipeline might be useful for personalized neurostimulation planning.

Methods of Brain Extraction from Magnetic Resonance Images of Human Head: A Review

Medical images are providing vital information to aid physicians in diagnosing a disease afflicting the organ of a human body. Magnetic resonance imaging is an important imaging modality in capturing the soft tissues of the brain. Segmenting and extracting the brain is essential in studying the structure and pathological condition of brain. There are several methods that are developed for this purpose. Researchers in brain extraction or segmentation need to know the current status of the work that have been done. Such an information is also important for improving the existing method to get more accurate results or to reduce the complexity of the algorithm. In this paper we review the classical methods and convolutional neural network-based deep learning brain extraction methods.

SynthStrip: skull-stripping for any brain image

The removal of non-brain signal from magnetic resonance imaging (MRI) data, known as skull-stripping, is an integral component of many neuroimage analysis streams. Despite their abundance, popular classical skull-stripping methods are usually tailored to images with specific acquisition properties, namely near-isotropic resolution and T1-weighted (T1w) MRI contrast, which are prevalent in research settings. As a result, existing tools tend to adapt poorly to other image types, such as stacks of thick slices acquired with fast spin-echo (FSE) MRI that are common in the clinic. While learning-based approaches for brain extraction have gained traction in recent years, these methods face a similar burden, as they are only effective for image types seen during the training procedure. To achieve robust skull-stripping across a landscape of imaging protocols, we introduce SynthStrip, a rapid, learning-based brain-extraction tool. By leveraging anatomical segmentations to generate an entirely synthetic training dataset with anatomies, intensity distributions, and artifacts that far exceed the realistic range of medical images, SynthStrip learns to successfully generalize to a variety of real acquired brain images, removing the need for training data with target contrasts. We demonstrate the efficacy of SynthStrip for a diverse set of image acquisitions and resolutions across subject populations, ranging from newborn to adult. We show substantial improvements in accuracy over popular skull-stripping baselines - all with a single trained model. Our method and labeled evaluation data are available at https://w3id.org/synthstrip.

Development and validation of subject-specific 3D human head models based on a nonlinear visco-hyperelastic constitutive framework

Computational head models are promising tools for understanding and predicting traumatic brain injuries. Most available head models are developed using inputs (i.e. head geometry, material properties and boundary conditions) from experiments on cadavers or animals and employ hereditary integral-based constitutive models that assume linear viscoelasticity in part of the rate-sensitive material response. This leads to high uncertainty and poor accuracy in capturing the nonlinear brain tissue response. To resolve these issues, a framework for the development of subject-specific three-dimensional head models is proposed, in which all inputs are derived in vivo from the same living human subject: head geometry via magnetic resonance imaging (MRI), brain tissue properties via magnetic resonance elastography (MRE), and full-field strain-response of the brain under rapid head rotation via tagged MRI. A nonlinear, viscous dissipation-based visco-hyperelastic constitutive model is employed to capture brain tissue response. Head models are validated using quantitative metrics that compare spatial strain distribution, temporal strain evolution, and the magnitude of strain maxima, with the corresponding experimental observations from tagged MRI. Results show that our head models accurately capture the strain-response of the brain. Further, employment of the nonlinear visco-hyperelastic constitutive framework provides improvements in the prediction of peak strains and temporal strain evolution over hereditary integral-based models.

Adding radiomics to the 2021 WHO updates may improve prognostic prediction for current IDH-wildtype histological lower-grade gliomas with known EGFR amplification and TERT promoter mutation status

OBJECTIVES

To assess whether radiomic features could improve the accuracy of survival predictions of IDH-wildtype (IDHwt) histological lower-grade gliomas (LGGs) over clinicopathological features.

METHODS

Preoperative MRI data of 61 patients with IDHwt histological LGGs were included as the institutional training set. The test set consisted of 32 patients from The Cancer Genome Atlas. Radiomic features (n = 186) were extracted using conventional MRIs. The radiomics risk score (RRS) for overall survival (OS) was derived from the elastic net. Multivariable Cox regression analyses with clinicopathological features (including epidermal growth factor receptor [EGFR] amplification and telomerase reverse transcriptase promoter [TERTp] mutation status) and the RRS were performed. The integrated area under the receiver operating curves (iAUCs) from the models with and without the RRS were compared. The net reclassification index (NRI) for 1-year OS was also calculated. The prognostic value of the RRS was evaluated using the external validation set.

RESULTS

The RRS independently predicted OS (hazard ratio = 48.08; p = 0.001). Compared with the clinicopathological model alone, adding the RRS had a better OS prediction performance (iAUCs 0.775 vs. 0.910), which was internally validated (iAUCs 0.726 vs. 0.884, 1-year OS NRI = 0.497), and a similar trend was found on external validation (iAUCs 0.683 vs. 0.705, 1-year OS NRI = 0.733). The prognostic significance of the RRS was confirmed in the external validation set (p = 0.001).

CONCLUSIONS

Integrating radiomics with clinicopathological features (including EGFR amplification and TERTp mutation status) can improve survival prediction in patients with IDHwt LGGs.

KEY POINTS

• Radiomics risk score has the potential to improve survival prediction when added to clinicopathological features (iAUCs increased from 0.775 to 0.910). • NRIs for 1-year OS showed that the radiomics risk score had incremental value over the clinicopathological model. • The prognostic significance of the radiomics risk score was confirmed in the external validation set (p = 0.001).

A general skull stripping of multiparametric brain MRIs using 3D convolutional neural network

Accurate skull stripping facilitates following neuro-image analysis. For computer-aided methods, the presence of brain skull in structural magnetic resonance imaging (MRI) impacts brain tissue identification, which could result in serious misjudgments, specifically for patients with brain tumors. Though there are several existing works on skull stripping in literature, most of them either focus on healthy brain MRIs or only apply for a single image modality. These methods may be not optimal for multiparametric MRI scans. In the paper, we propose an ensemble neural network (EnNet), a 3D convolutional neural network (3DCNN) based method, for brain extraction on multiparametric MRI scans (mpMRIs). We comprehensively investigate the skull stripping performance by using the proposed method on a total of 15 image modality combinations. The comparison shows that utilizing all modalities provides the best performance on skull stripping. We have collected a retrospective dataset of 815 cases with/without glioblastoma multiforme (GBM) at the University of Pittsburgh Medical Center (UPMC) and The Cancer Imaging Archive (TCIA). The ground truths of the skull stripping are verified by at least one qualified radiologist. The quantitative evaluation gives an average dice score coefficient and Hausdorff distance at the 95th percentile, respectively. We also compare the performance to the state-of-the-art methods/tools. The proposed method offers the best performance.The contributions of the work have five folds: first, the proposed method is a fully automatic end-to-end for skull stripping using a 3D deep learning method. Second, it is applicable for mpMRIs and is also easy to customize for any MRI modality combination. Third, the proposed method not only works for healthy brain mpMRIs but also pre-/post-operative brain mpMRIs with GBM. Fourth, the proposed method handles multicenter data. Finally, to the best of our knowledge, we are the first group to quantitatively compare the skull stripping performance using different modalities. All code and pre-trained model are available at: https://github.com/plmoer/skull_stripping_code_SR .

Deep learning network for integrated coil inhomogeneity correction and brain extraction of mixed MRI data

Magnetic Resonance Imaging (MRI) has been widely used to acquire structural and functional information about the brain. In a group- or voxel-wise analysis, it is essential to correct the bias field of the radiofrequency coil and to extract the brain for accurate registration to the brain template. Although automatic methods have been developed, manual editing is still required, particularly for echo-planar imaging (EPI) due to its lower spatial resolution and larger geometric distortion. The needs of user interventions slow down data processing and lead to variable results between operators. Deep learning networks have been successfully used for automatic postprocessing. However, most networks are only designed for a specific processing and/or single image contrast (e.g., spin-echo or gradient-echo). This limitation markedly restricts the application and generalization of deep learning tools. To address these limitations, we developed a deep learning network based on the generative adversarial net (GAN) to automatically correct coil inhomogeneity and extract the brain from both spin- and gradient-echo EPI without user intervention. Using various quantitative indices, we show that this method achieved high similarity to the reference target and performed consistently across datasets acquired from rodents. These results highlight the potential of deep networks to integrate different postprocessing methods and adapt to different image contrasts. The use of the same network to process multimodality data would be a critical step toward a fully automatic postprocessing pipeline that could facilitate the analysis of large datasets with high consistency.

Cycle-consistent adversarial networks improves generalizability of radiomics model in grading meningiomas on external validation

The heterogeneity of MRI is one of the major reasons for decreased performance of a radiomics model on external validation, limiting the model’s generalizability and clinical application. We aimed to establish a generalizable radiomics model to predict meningioma grade on external validation through leveraging Cycle-Consistent Adversarial Networks (CycleGAN). In this retrospective study, 257 patients with meningioma were included in the institutional training set. Radiomic features (n = 214) were extracted from T2-weighted (T2) and contrast-enhanced T1 (T1C) images. After radiomics feature selection, extreme gradient boosting classifiers were developed. The models were validated in the external validation set consisting of 61 patients with meningiomas. To reduce the gap in generalization associated with the inter-institutional heterogeneity of MRI, the smaller image set style of the external validation was translated into the larger image set style of the institutional training set using CycleGAN. On external validation before CycleGAN application, the performance of the combined T2 and T1C models showed an area under the curve (AUC), accuracy, and F1 score of 0.77 (95% confidence interval 0.63–0.91), 70.7%, and 0.54, respectively. After applying CycleGAN, the performance of the combined T2 and T1C models increased, with an AUC, accuracy, and F1 score of 0.83 (95% confidence interval 0.70–0.97), 73.2%, and 0.59, respectively. Quantitative metrics (by Fréchet Inception Distance) showed that CycleGAN can decrease inter-institutional image heterogeneity while preserving predictive information. In conclusion, leveraging CycleGAN may be helpful to increase the generalizability of a radiomics model in differentiating meningioma grade on external validation.

Weakly Supervised Skull Stripping of Magnetic Resonance Imaging of Brain Tumor Patients

Automatic brain tumor segmentation is particularly challenging on magnetic resonance imaging (MRI) with marked pathologies, such as brain tumors, which usually cause large displacement, abnormal appearance, and deformation of brain tissue. Despite an abundance of previous literature on learning-based methodologies for MRI segmentation, few works have focused on tackling MRI skull stripping of brain tumor patient data. This gap in literature can be associated with the lack of publicly available data (due to concerns about patient identification) and the labor-intensive nature of generating ground truth labels for model training. In this retrospective study, we assessed the performance of Dense-Vnet in skull stripping brain tumor patient MRI trained on our large multi-institutional brain tumor patient dataset. Our data included pretreatment MRI of 668 patients from our in-house institutional review board-approved multi-institutional brain tumor repository. Because of the absence of ground truth, we used imperfect automatically generated training labels using SPM12 software. We trained the network using common MRI sequences in oncology: T1-weighted with gadolinium contrast, T2-weighted fluid-attenuated inversion recovery, or both. We measured model performance against 30 independent brain tumor test cases with available manual brain masks. All images were harmonized for voxel spacing and volumetric dimensions before model training. Model training was performed using the modularly structured deep learning platform NiftyNet that is tailored toward simplifying medical image analysis. Our proposed approach showed the success of a weakly supervised deep learning approach in MRI brain extraction even in the presence of pathology. Our best model achieved an average Dice score, sensitivity, and specificity of, respectively, 94.5, 96.4, and 98.5% on the multi-institutional independent brain tumor test set. To further contextualize our results within existing literature on healthy brain segmentation, we tested the model against healthy subjects from the benchmark LBPA40 dataset. For this dataset, the model achieved an average Dice score, sensitivity, and specificity of 96.2, 96.6, and 99.2%, which are, although comparable to other publications, slightly lower than the performance of models trained on healthy patients. We associate this drop in performance with the use of brain tumor data for model training and its influence on brain appearance.

Central Vein Sign Profile of Newly Developing Lesions in Multiple Sclerosis: A 3-Year Longitudinal Study

BACKGROUND AND OBJECTIVES

The central vein sign (CVS), a central linear hypointensity within lesions on T2*-weighted imaging, has been established as a sensitive and specific biomarker for the diagnosis of multiple sclerosis (MS). However, the CVS has not yet been comprehensively studied in newly developing MS lesions. We aimed to identify the CVS profiles of new white matter lesions in patients with MS followed over time and investigate demographic and clinical risk factors associated with new CVS+ or CVS- lesion development.

METHODS

In this retrospective longitudinal cohort study, adults from the NIH MS Natural History Study were considered for inclusion. Participants with new T2 or enhancing lesions were identified through review of the radiology report and/or longitudinal subtraction imaging. Each new lesion was evaluated for the CVS. Clinical characteristics were identified through chart review.

RESULTS

A total of 153 adults (95 relapsing-remitting MS, 27 secondary progressive MS, 16 primary progressive MS, 5 clinically isolated syndrome, and 10 healthy; 67% female) were included. Of this cohort, 96 had at least 1 new T2 or contrast-enhancing lesion during median 3.1 years (Q1-Q3: 0.7-6.3) of follow-up; lesions eligible for CVS evaluation were found in 62 (65%). Of 233 new CVS-eligible lesions, 159 (68%) were CVS+, with 30 (48%) individuals having only CVS+, 12 (19%) only CVS-, and 20 (32%) both CVS+ and CVS- lesions. In gadolinium-enhancing (Gd+) lesions, the CVS+ percentage increased from 102/152 (67%) at the first time point where the lesion was observed, to 92/114 (82%) after a median follow-up of 2.8 years. Younger age (OR = 0.5 per 10-year increase, 95% CI = 0.3-0.8) and higher CVS+ percentage at baseline (OR = 1.4 per 10% increase, 95% CI = 1.1-1.9) were associated with increased likelihood of new CVS+ lesion development.

DISCUSSION

In a cohort of adults with MS followed over a median duration of 3 years, most newly developing T2 or enhancing lesions were CVS+ (68%), and nearly half (48%) developed new CVS+ lesions only. Importantly, the effects of edema and T2 signal changes can obscure small veins in Gd+ lesions; therefore, caution and follow-up is necessary when determining their CVS status.

TRIAL REGISTRATION INFORMATION

Clinical trial registration number NCT00001248.

CLASSIFICATION OF EVIDENCE

This study provides Class III evidence that younger age and higher CVS+ percentage at baseline are associated with new CVS+ lesion development.

Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury

Registration-based methods are commonly used in the automatic segmentation of magnetic resonance (MR) brain images. However, these methods are not robust to the presence of gross pathologies that can alter the brain anatomy and affect the alignment of the atlas image with the target image. In this work, we develop a robust algorithm, MU-Net-R, for automatic segmentation of the normal and injured rat hippocampus based on an ensemble of U-net-like Convolutional Neural Networks (CNNs). MU-Net-R was trained on manually segmented MR images of sham-operated rats and rats with traumatic brain injury (TBI) by lateral fluid percussion. The performance of MU-Net-R was quantitatively compared with methods based on single and multi-atlas registration using MR images from two large preclinical cohorts. Automatic segmentations using MU-Net-R and multi-atlas registration were of excellent quality, achieving cross-validated Dice scores above 0.90 despite the presence of brain lesions, atrophy, and ventricular enlargement. In contrast, the performance of single-atlas segmentation was unsatisfactory (cross-validated Dice scores below 0.85). Interestingly, the registration-based methods were better at segmenting the contralateral than the ipsilateral hippocampus, whereas MU-Net-R segmented the contralateral and ipsilateral hippocampus equally well. We assessed the progression of hippocampal damage after TBI by using our automatic segmentation tool. Our data show that the presence of TBI, time after TBI, and whether the hippocampus was ipsilateral or contralateral to the injury were the parameters that explained hippocampal volume.

An efficient magnetic resonance image data quality screening dashboard

Purpose

Complex data processing and curation for artificial intelligence applications rely on high‐quality data sets for training and analysis. Manually reviewing images and their associated annotations is a very laborious task and existing quality control tools for data review are generally limited to raw images only. The purpose of this work was to develop an imaging informatics dashboard for the easy and fast review of processed magnetic resonance (MR) imaging data sets; we demonstrated its ability in a large‐scale data review.

Methods

We developed a custom R Shiny dashboard that displays key static snapshots of each imaging study and its annotations. A graphical interface allows the structured entry of review data and download of tabulated review results. We evaluated the dashboard using two large data sets: 1380 processed MR imaging studies from our institution and 285 studies from the 2018 MICCAI Brain Tumor Segmentation Challenge (BraTS).

Results

Studies were reviewed at an average rate of 100/h using the dashboard, 10 times faster than using existing data viewers. For data from our institution, 1181 of the 1380 (86%) studies were of acceptable quality. The most commonly identified failure modes were tumor segmentation (9.6% of cases) and image registration (4.6% of cases). Tumor segmentation without visible errors on the dashboard had much better agreement with reference tumor volume measurements (root‐mean‐square error 12.2 cm³) than did segmentations with minor errors (20.5 cm³) or failed segmentations (27.4 cm³). In the BraTS data, 242 of 285 (85%) studies were acceptable quality after processing. Among the 43 cases that failed review, 14 had unacceptable raw image quality.

Conclusion

Our dashboard provides a fast, effective tool for reviewing complex processed MR imaging data sets. It is freely available for download at https://github.com/EGates1/MRDQED.

Cranial Meninges Reconstruction Based on Convolutional Networks and Deformable Models: Applications to Longitudinal Study of Normal Aging

The cranial meninges are membranes enveloping the brain. The space between these membranes contains mainly cerebrospinal fluid. It is of interest to study how the volumes of this space change with respect to normal aging. In this work, we propose to combine convolutional neural networks (CNNs) with nested topology-preserving geometric deformable models (NTGDMs) to reconstruct meningeal surfaces from magnetic resonance (MR) images. We first use CNNs to predict implicit representations of these surfaces then refine them with NTGDMs to achieve sub-voxel accuracy while maintaining spherical topology and the correct anatomical ordering. MR contrast harmonization is used to match the contrasts between training and testing images. We applied our algorithm to a subset of healthy subjects from the Baltimore Longitudinal Study of Aging for demonstration purposes and conducted longitudinal statistical analysis of the intracranial volume (ICV) and subarachnoid space (SAS) volume. We found a statistically significant decrease in the ICV and an increase in the SAS volume with respect to normal aging.

MR Imaging of Human Brain Mechanics In Vivo: New Measurements to Facilitate the Development of Computational Models of Brain Injury

Computational models of the brain and its biomechanical response to skull accelerations are important tools for understanding and predicting traumatic brain injuries (TBIs). However, most models have been developed using experimental data collected on animal models and cadaveric specimens, both of which differ from the living human brain. Here we describe efforts to noninvasively measure the biomechanical response of the human brain with MRI-at non-injurious strain levels-and generate data that can be used to develop, calibrate, and evaluate computational brain biomechanics models. Specifically, this paper reports on a project supported by the National Institute of Neurological Disorders and Stroke to comprehensively image brain anatomy and geometry, mechanical properties, and brain deformations that arise from impulsive and harmonic skull loadings. The outcome of this work will be a publicly available dataset ( http://www.nitrc.org/projects/bbir ) that includes measurements on both males and females across an age range from adolescence to older adulthood. This article describes the rationale and approach for this study, the data available, and how these data may be used to develop new computational models and augment existing approaches; it will serve as a reference to researchers interested in using these data.

Accurate Estimation of Total Intracranial Volume in MRI using a Multi-tasked Image-to-Image Translation Network

Total intracranial volume (TIV) is the volume enclosed inside the cranium, inclusive of the meninges and the brain. TIV is extensively used to correct variations in inter-subject head size for the evaluation of neurodegenerative diseases. In this work, we present an automatic method to generate a TIV mask from MR images while synthesizing a CT image to be used in subsequent analysis. In addition, we propose an alternative way to obtain ground truth TIV masks using a semi-manual approach, which results in significant time savings. We train a conditional generative adversarial network (cGAN) using 2D MR slices to realize our tasks. The quantitative evaluation showed that the model was able to synthesize CT and generate TIV masks that closely approximate the reference images. This study also provides a comparison of the described method against skull stripping tools that output a mask enclosing the cranial volume, using MRI scan. In particular, highlighting the deficiencies in using such tools to approximate the volume using MRI scan.

MTT and Blood-Brain Barrier Disruption within Asymptomatic Vascular WM Lesions

BACKGROUND AND PURPOSE

White matter lesions of presumed ischemic origin are associated with progressive cognitive impairment and impaired BBB function. Studying the longitudinal effects of white matter lesion biomarkers that measure changes in perfusion and BBB patency within white matter lesions is required for long-term studies of lesion progression. We studied perfusion and BBB disruption within white matter lesions in asymptomatic subjects.

MATERIALS AND METHODS

Anatomic imaging was followed by consecutive dynamic contrast-enhanced and DSC imaging. White matter lesions in 21 asymptomatic individuals were determined using a Subject-Specific Sparse Dictionary Learning algorithm with manual correction. Perfusion-related parameters including CBF, MTT, the BBB leakage parameter, and volume transfer constant were determined.

RESULTS

MTT was significantly prolonged (7.88 [SD, 1.03] seconds) within white matter lesions compared with normal-appearing white (7.29 [SD, 1.14] seconds) and gray matter (6.67 [SD, 1.35] seconds). The volume transfer constant, measured by dynamic contrast-enhanced imaging, was significantly elevated (0.013 [SD, 0.017] minutes-1) in white matter lesions compared with normal-appearing white matter (0.007 [SD, 0.011] minutes-1). BBB disruption within white matter lesions was detected relative to normal white and gray matter using the DSC-BBB leakage parameter method so that increasing BBB disruption correlated with increasing white matter lesion volume (Spearman correlation coefficient = 0.44; P < .046).

CONCLUSIONS

A dual-contrast-injection MR imaging protocol combined with a 3D automated segmentation analysis pipeline was used to assess BBB disruption in white matter lesions on the basis of quantitative perfusion measures including the volume transfer constant (dynamic contrast-enhanced imaging), the BBB leakage parameter (DSC), and MTT (DSC). This protocol was able to detect early pathologic changes in otherwise healthy individuals.

Genetic inactivation of SARM1 axon degeneration pathway improves outcome trajectory after experimental traumatic brain injury based on pathological, radiological, and functional measures

Traumatic brain injury (TBI) causes chronic symptoms and increased risk of neurodegeneration. Axons in white matter tracts, such as the corpus callosum (CC), are critical components of neural circuits and particularly vulnerable to TBI. Treatments are needed to protect axons from traumatic injury and mitigate post-traumatic neurodegeneration. SARM1 protein is a central driver of axon degeneration through a conserved molecular pathway. Sarm1−/− mice with knockout (KO) of the Sarm1 gene enable genetic proof-of-concept testing of the SARM1 pathway as a therapeutic target. We evaluated Sarm1 deletion effects after TBI using a concussive model that causes traumatic axonal injury and progresses to CC atrophy at 10 weeks, indicating post-traumatic neurodegeneration. Sarm1 wild-type (WT) mice developed significant CC atrophy that was reduced in Sarm1 KO mice. Ultrastructural classification of pathology of individual axons, using electron microscopy, demonstrated that Sarm1 KO preserved more intact axons and reduced damaged or demyelinated axons. Longitudinal MRI studies in live mice identified significantly reduced CC volume after TBI in Sarm1 WT mice that was attenuated in Sarm1 KO mice. MR diffusion tensor imaging detected reduced fractional anisotropy in both genotypes while axial diffusivity remained higher in Sarm1 KO mice. Immunohistochemistry revealed significant attenuation of CC atrophy, myelin loss, and neuroinflammation in Sarm1 KO mice after TBI. Functionally, Sarm1 KO mice exhibited beneficial effects in motor learning and sleep behavior. Based on these findings, Sarm1 inactivation can protect axons and white matter tracts to improve translational outcomes associated with CC atrophy and post-traumatic neurodegeneration.

Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging

OBJECTIVES

To evaluate whether a deep learning (DL) model using both three-dimensional (3D) black-blood (BB) imaging and 3D gradient echo (GRE) imaging may improve the detection and segmentation performance of brain metastases compared to that using only 3D GRE imaging.

METHODS

A total of 188 patients with brain metastases (917 lesions) who underwent a brain metastasis MRI protocol including contrast-enhanced 3D BB and 3D GRE were included in the training set. DL models based on 3D U-net were constructed. The models were validated in the test set consisting of 45 patients with brain metastases (203 lesions) and 49 patients without brain metastases.

RESULTS

The combined 3D BB and 3D GRE model yielded better performance than the 3D GRE model (sensitivities of 93.1% vs 76.8%, p < 0.001), and this effect was significantly stronger in subgroups with small metastases (p interaction < 0.001). For metastases < 3 mm, ≥ 3 mm and < 10 mm, and ≥ 10 mm, the sensitivities were 82.4%, 93.2%, and 100%, respectively. The combined 3D BB and 3D GRE model showed a false-positive per case of 0.59 in the test set. The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while 3D GRE model showed a lower Dice coefficient of 0.756.

CONCLUSIONS

The combined 3D BB and 3D GRE DL model may improve the detection and segmentation performance of brain metastases, especially in detecting small metastases.

KEY POINTS

• The combined 3D BB and 3D GRE model yielded better performance for the detection of brain metastases than the 3D GRE model (p < 0.001), with sensitivities of 93.1% and 76.8%, respectively. • The combined 3D BB and 3D GRE model showed a false-positive rate per case of 0.59 in the test set. • The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while the 3D GRE model showed a lower Dice coefficient of 0.756.

Improved Segmentation of the Intracranial and Ventricular Volumes in Populations with Cerebrovascular Lesions and Atrophy Using 3D CNNs

Successful segmentation of the total intracranial vault (ICV) and ventricles is of critical importance when studying neurodegeneration through neuroimaging. We present iCVMapper and VentMapper, robust algorithms that use a convolutional neural network (CNN) to segment the ICV and ventricles from both single and multi-contrast MRI data. Our models were trained on a large dataset from two multi-site studies (N = 528 subjects for ICV, N = 501 for ventricular segmentation) consisting of older adults with varying degrees of cerebrovascular lesions and atrophy, which pose significant challenges for most segmentation approaches. The models were tested on 238 participants, including subjects with vascular cognitive impairment and high white matter hyperintensity burden. Two of the three test sets came from studies not used in the training dataset. We assessed our algorithms relative to four state-of-the-art ICV extraction methods (MONSTR, BET, Deep Extraction, FreeSurfer, DeepMedic), as well as two ventricular segmentation tools (FreeSurfer, DeepMedic). Our multi-contrast models outperformed other methods across many of the evaluation metrics, with average Dice coefficients of 0.98 and 0.96 for ICV and ventricular segmentation respectively. Both models were also the most time efficient, segmenting the structures in orders of magnitude faster than some of the other available methods. Our networks showed an increased accuracy with the use of a conditional random field (CRF) as a post-processing step. We further validated both segmentation models, highlighting their robustness to images with lower resolution and signal-to-noise ratio, compared to tested techniques. The pipeline and models are available at: https://icvmapp3r.readthedocs.io and https://ventmapp3r.readthedocs.io to enable further investigation of the roles of ICV and ventricles in relation to normal aging and neurodegeneration in large multi-site studies.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Integrating material properties from magnetic resonance elastography into subject-specific computational models for the human brain

Advances in brain imaging and computational methods have facilitated the creation of subject-specific computational brain models that aid researchers in investigating brain trauma using simulated impacts. The emergence of magnetic resonance elastography (MRE) as a non-invasive mechanical neuroimaging tool has enabled in vivo estimation of material properties at low-strain, harmonic loading. An open question in the field has been how this data can be integrated into computational models. The goals of this study were to use a novel MRI dataset acquired in human volunteers to generate models with subject-specific anatomy and material properties, and then to compare simulated brain deformations to subject-specific brain deformation data under non-injurious loading. Models of five subjects were simulated with linear viscoelastic (LVE) material properties estimated directly from MRE data. Model predictions were compared to experimental brain deformation acquired in the same subjects using tagged MRI. Outcomes from the models matched the spatial distribution and magnitude of the measured peak strain components as well as the 95^th percentile in-plane peak strains within 0.005 mm/mm and maximum principal strain within 0.012 mm/mm. Sensitivity to material heterogeneity was also investigated. Simulated brain deformations from a model with homogenous brain properties and a model with brain properties discretized with up to ten regions were very similar (a mean absolute difference less than 0.0015 mm/mm in peak strains). Incorporating material properties directly from MRE into a biofidelic subject-specific model is an important step toward future investigations of higher-order model features and simulations under more severe loading conditions.

DIKA-Nets: Domain-invariant knowledge-guided attention networks for brain skull stripping of early developing macaques

As non-human primates, macaques have a close phylogenetic relationship to human beings and have been proven to be a valuable and widely used animal model in human neuroscience research. Accurate skull stripping (aka. brain extraction) of brain magnetic resonance imaging (MRI) is a crucial prerequisite in neuroimaging analysis of macaques. Most of the current skull stripping methods can achieve satisfactory results for human brains, but when applied to macaque brains, especially during early brain development, the results are often unsatisfactory. In fact, the early dynamic, regionally-heterogeneous development of macaque brains, accompanied by poor and age-related contrast between different anatomical structures, poses significant challenges for accurate skull stripping. To overcome these challenges, we propose a fully-automated framework to effectively fuse the age-specific intensity information and domain-invariant prior knowledge as important guiding information for robust skull stripping of developing macaques from 0 to 36 months of age. Specifically, we generate Signed Distance Map (SDM) and Center of Gravity Distance Map (CGDM) based on the intermediate segmentation results as guidance. Instead of using local convolution, we fuse all information using the Dual Self-Attention Module (DSAM), which can capture global spatial and channel-dependent information of feature maps. To extensively evaluate the performance, we adopt two relatively-large challenging MRI datasets from rhesus macaques and cynomolgus macaques, respectively, with a total of 361 scans from two different scanners with different imaging protocols. We perform cross-validation by using one dataset for training and the other one for testing. Our method outperforms five popular brain extraction tools and three deep-learning-based methods on cross-source MRI datasets without any transfer learning.

Progressive multifocal leukoencephalopathy lesion and brain parenchymal segmentation from MRI using serial deep convolutional neural networks

•

PML has characteristic dynamic changes in brain and lesion volume on MRI.

•

JCnet is an automated method for brain atrophy and lesion segmentation in PML.

•

JCnet improves PML lesion segmentation accuracy compared to conventional methods.

•

JCnet can accurately track PML lesion changes over time.

Progressive multifocal leukoencephalopathy (PML) is a rare opportunistic brain infection caused by the JC virus and associated with substantial morbidity and mortality. Accurate MRI assessment of PML lesion burden and brain parenchymal atrophy is of decisive value in monitoring the disease course and response to therapy. However, there are currently no validated automatic methods for quantification of PML lesion burden or associated parenchymal volume loss. Furthermore, manual brain or lesion delineations can be tedious, require the use of valuable time resources by radiologists or trained experts, and are often subjective. In this work, we introduce JCnet (named after the causative viral agent), an end-to-end, fully automated method for brain parenchymal and lesion segmentation in PML using consecutive 3D patch-based convolutional neural networks. The network architecture consists of multi-view feature pyramid networks with hierarchical residual learning blocks containing embedded batch normalization and nonlinear activation functions. The feature maps across the bottom-up and top-down pathways of the feature pyramids are merged, and an output probability membership generated through convolutional pathways, thus rendering the method fully convolutional. Our results show that this approach outperforms and improves longitudinal consistency compared to conventional, state-of-the-art methods of healthy brain and multiple sclerosis lesion segmentation, utilized here as comparators given the lack of available methods validated for use in PML. The ability to produce robust and accurate automated measures of brain atrophy and lesion segmentation in PML is not only valuable clinically but holds promise toward including standardized quantitative MRI measures in clinical trials of targeted therapies. Code is available at: https://github.com/omarallouz/JCnet.

Deep learning of brain magnetic resonance images: A brief review

Magnetic resonance imaging (MRI) is one of the most popular techniques in brain science and is important for understanding brain function and neuropsychiatric disorders. However, the processing and analysis of MRI is not a trivial task with lots of challenges. Recently, deep learning has shown superior performance over traditional machine learning approaches in image analysis. In this survey, we give a brief review of the recent popular deep learning approaches and their applications in brain MRI analysis. Furthermore, popular brain MRI databases and deep learning tools are also introduced. The strength and weaknesses of different approaches are addressed, and challenges as well as future directions are also discussed.

In vivo estimates of axonal stretch and 3D brain deformation during mild head impact

The rapid deformation of brain tissue in response to head impact can lead to traumatic brain injury. In vivo measurements of brain deformation during non-injurious head impacts are necessary to understand the underlying mechanisms of traumatic brain injury and compare to computational models of brain biomechanics. Using tagged magnetic resonance imaging (MRI), we obtained measurements of three-dimensional strain tensors that resulted from a mild head impact after neck rotation or neck extension. Measurements of maximum principal strain (MPS) peaked shortly after impact, with maximal values of 0.019-0.053 that correlated strongly with peak angular velocity. Subject-specific patterns of MPS were spatially heterogeneous and consistent across subjects for the same motion, though regions of high deformation differed between motions. The largest MPS values were seen in the cortical gray matter and cerebral white matter for neck rotation and the brainstem and cerebellum for neck extension. Axonal fiber strain (Ef) was estimated by combining the strain tensor with diffusion tensor imaging data. As with MPS, patterns of Ef varied spatially within subjects, were similar across subjects within each motion, and showed group differences between motions. Values were highest and most strongly correlated with peak angular velocity in the corpus callosum for neck rotation and in the brainstem for neck extension. The different patterns of brain deformation between head motions highlight potential areas of greater risk of injury between motions at higher loading conditions. Additionally, these experimental measurements can be directly compared to predictions of generic or subject-specific computational models of traumatic brain injury.

Infant FreeSurfer: An automated segmentation and surface extraction pipeline for T1-weighted neuroimaging data of infants 0-2 years

The development of automated tools for brain morphometric analysis in infants has lagged significantly behind analogous tools for adults. This gap reflects the greater challenges in this domain due to: 1) a smaller-scaled region of interest, 2) increased motion corruption, 3) regional changes in geometry due to heterochronous growth, and 4) regional variations in contrast properties corresponding to ongoing myelination and other maturation processes. Nevertheless, there is a great need for automated image-processing tools to quantify differences between infant groups and other individuals, because aberrant cortical morphologic measurements (including volume, thickness, surface area, and curvature) have been associated with neuropsychiatric, neurologic, and developmental disorders in children. In this paper we present an automated segmentation and surface extraction pipeline designed to accommodate clinical MRI studies of infant brains in a population 0-2 year-olds. The algorithm relies on a single channel of T1-weighted MR images to achieve automated segmentation of cortical and subcortical brain areas, producing volumes of subcortical structures and surface models of the cerebral cortex. We evaluated the algorithm both qualitatively and quantitatively using manually labeled datasets, relevant comparator software solutions cited in the literature, and expert evaluations. The computational tools and atlases described in this paper will be distributed to the research community as part of the FreeSurfer image analysis package.

Neurofilament light as a biomarker in traumatic brain injury

OBJECTIVE

To determine whether serum neurofilament light (NfL) correlates with CSF NfL, traumatic brain injury (TBI) diagnosis, injury severity, brain volume, and diffusion tensor imaging (DTI) estimates of traumatic axonal injury (TAI).

METHODS

Participants were prospectively enrolled in Sweden and the United States between 2011 and 2019. The Swedish cohort included 45 hockey players with acute concussion sampled at 6 days, 31 with repetitive concussion with persistent postconcussive symptoms (PCS) assessed with paired CSF and serum (median 1.3 years after concussion), 28 preseason controls, and 14 nonathletic controls. Our second cohort included 230 clinic-based participants (162 with TBI and 68 controls). Patients with TBI also underwent serum, functional outcome, and imaging assessments at 30 (n = 30), 90 (n = 48), and 180 (n = 59) days and 1 (n = 84), 2 (n = 57), 3 (n = 46), 4 (n = 38), and 5 (n = 29) years after injury.

RESULTS

In athletes with paired specimens, CSF NfL and serum NfL were correlated (r = 0.71, p < 0.0001). CSF and serum NfL distinguished players with PCS >1 year from PCS ≤1 year (area under the receiver operating characteristic curve [AUROC] 0.81 and 0.80). The AUROC for PCS >1 year vs preseason controls was 0.97. In the clinic-based cohort, NfL at enrollment distinguished patients with mild from those with moderate and severe TBI (p < 0.001 and p = 0.048). Serum NfL decreased over the course of 5 years (ß = -0.09 log pg/mL, p < 0.0001) but remained significantly elevated compared to controls. Serum NfL correlated with measures of functional outcome, MRI brain atrophy, and DTI estimates of TAI.

CONCLUSIONS

Serum NfL shows promise as a biomarker for acute and repetitive sports-related concussion and patients with subacute and chronic TBI.

CLASSIFICATION OF EVIDENCE

This study provides Class III evidence that increased concentrations of NfL distinguish patients with TBI from controls.

State-of-the-Art Traditional to the Machine- and Deep-Learning-Based Skull Stripping Techniques, Models, and Algorithms

Several neuroimaging processing applications consider skull stripping as a crucial pre-processing step. Due to complex anatomical brain structure and intensity variations in brain magnetic resonance imaging (MRI), an appropriate skull stripping is an important part. The process of skull stripping basically deals with the removal of the skull region for clinical analysis in brain segmentation tasks, and its accuracy and efficiency are quite crucial for diagnostic purposes. It requires more accurate and detailed methods for differentiating brain regions and the skull regions and is considered as a challenging task. This paper is focused on the transition of the conventional to the machine- and deep-learning-based automated skull stripping methods for brain MRI images. It is observed in this study that deep learning approaches have outperformed conventional and machine learning techniques in many ways, but they have their limitations. It also includes the comparative analysis of the current state-of-the-art skull stripping methods, a critical discussion of some challenges, model of quantifying parameters, and future work directions.

Time course and diagnostic utility of NfL, tau, GFAP, and UCH-L1 in subacute and chronic TBI

OBJECTIVE

To determine whether neurofilament light (NfL), glial fibrillary acidic protein (GFAP), tau, and ubiquitin C-terminal hydrolase-L1 (UCH-L1) measured in serum relate to traumatic brain injury (TBI) diagnosis, injury severity, brain volume, and diffusion tensor imaging (DTI) measures of traumatic axonal injury (TAI) in patients with TBI.

METHODS

Patients with TBI (n = 162) and controls (n = 68) were prospectively enrolled between 2011 and 2019. Patients with TBI also underwent serum, functional outcome, and imaging assessments at 30 (n = 30), 90 (n = 48), and 180 (n = 59) days, and 1 (n = 84), 2 (n = 57), 3 (n = 46), 4 (n = 38), and 5 (n = 29) years after injury.

RESULTS

At enrollment, patients with TBI had increased serum NfL compared to controls (p < 0.0001). Serum NfL decreased over the course of 5 years but remained significantly elevated compared to controls. Serum NfL at 30 days distinguished patients with mild, moderate, and severe TBI from controls with an area under the receiver-operating characteristic curve (AUROC) of 0.84, 0.92, and 0.92, respectively. At enrollment, serum GFAP was elevated in patients with TBI compared to controls (p < 0.001). GFAP showed a biphasic release in serum, with levels decreasing during the first 6 months of injury but increasing over the subsequent study visits. The highest AUROC for GFAP was measured at 30 days, distinguishing patients with moderate and severe TBI from controls (both 0.89). Serum tau and UCH-L1 showed weak associations with TBI severity and neuroimaging measures. Longitudinally, serum NfL was the only biomarker that was associated with the likely rate of MRI brain atrophy and DTI measures of progression of TAI.

CONCLUSIONS

Serum NfL shows greater diagnostic and prognostic utility than GFAP, tau, and UCH-L1 for subacute and chronic TBI.

CLASSIFICATION OF EVIDENCE

This study provides Class III evidence that serum NfL distinguishes patients with mild TBI from healthy controls.

Conventional and Deep Learning Methods for Skull Stripping in Brain MRI

Skull stripping in brain magnetic resonance volume has recently been attracting attention due to an increased demand to develop an efficient, accurate, and general algorithm for diverse datasets of the brain. Accurate skull stripping is a critical step for neuroimaging diagnostic systems because neither the inclusion of non-brain tissues nor removal of brain parts can be corrected in subsequent steps, which results in unfixed error through subsequent analysis. The objective of this review article is to give a comprehensive overview of skull stripping approaches, including recent deep learning-based approaches. In this paper, the current methods of skull stripping have been divided into two distinct groups—conventional or classical approaches, and convolutional neural networks or deep learning approaches. The potentials of several methods are emphasized because they can be applied to standard clinical imaging protocols. Finally, current trends and future developments are addressed giving special attention to recent deep learning algorithms.

Applications of a deep learning method for anti-aliasing and super-resolution in MRI

Magnetic resonance (MR) images with both high resolutions and high signal-to-noise ratios (SNRs) are desired in many clinical and research applications. However, acquiring such images takes a long time, which is both costly and susceptible to motion artifacts. Acquiring MR images with good in-plane resolution and poor through-plane resolution is a common strategy that saves imaging time, preserves SNR, and provides one viewpoint with good resolution in two directions. Unfortunately, this strategy also creates orthogonal viewpoints that have poor resolution in one direction and, for 2D MR acquisition protocols, also creates aliasing artifacts. A deep learning approach called SMORE that carries out both anti-aliasing and super-resolution on these types of acquisitions using no external atlas or exemplars has been previously reported but not extensively validated. This paper reviews the SMORE algorithm and then demonstrates its performance in four applications with the goal to demonstrate its potential for use in both research and clinical scenarios. It is first shown to improve the visualization of brain white matter lesions in FLAIR images acquired from multiple sclerosis patients. Then it is shown to improve the visualization of scarring in cardiac left ventricular remodeling after myocardial infarction. Third, its performance on multi-view images of the tongue is demonstrated and finally it is shown to improve performance in parcellation of the brain ventricular system. Both visual and selected quantitative metrics of resolution enhancement are demonstrated.

Automated brain extraction of multisequence MRI using artificial neural networks

Brain extraction is a critical preprocessing step in the analysis of neuroimaging studies conducted with magnetic resonance imaging (MRI) and influences the accuracy of downstream analyses. The majority of brain extraction algorithms are, however, optimized for processing healthy brains and thus frequently fail in the presence of pathologically altered brain or when applied to heterogeneous MRI datasets. Here we introduce a new, rigorously validated algorithm (termed HD-BET) relying on artificial neural networks that aim to overcome these limitations. We demonstrate that HD-BET outperforms six popular, publicly available brain extraction algorithms in several large-scale neuroimaging datasets, including one from a prospective multicentric trial in neuro-oncology, yielding state-of-the-art performance with median improvements of +1.16 to +2.50 points for the Dice coefficient and -0.66 to -2.51 mm for the Hausdorff distance. Importantly, the HD-BET algorithm, which shows robust performance in the presence of pathology or treatment-induced tissue alterations, is applicable to a broad range of MRI sequence types and is not influenced by variations in MRI hardware and acquisition parameters encountered in both research and clinical practice. For broader accessibility, the HD-BET prediction algorithm is made freely available (www.neuroAI-HD.org) and may become an essential component for robust, automated, high-throughput processing of MRI neuroimaging data.

DeepHarmony: A deep learning approach to contrast harmonization across scanner changes

Magnetic resonance imaging (MRI) is a flexible medical imaging modality that often lacks reproducibility between protocols and scanners. It has been shown that even when care is taken to standardize acquisitions, any changes in hardware, software, or protocol design can lead to differences in quantitative results. This greatly impacts the quantitative utility of MRI in multi-site or long-term studies, where consistency is often valued over image quality. We propose a method of contrast harmonization, called DeepHarmony, which uses a U-Net-based deep learning architecture to produce images with consistent contrast. To provide training data, a small overlap cohort (n = 8) was scanned using two different protocols. Images harmonized with DeepHarmony showed significant improvement in consistency of volume quantification between scanning protocols. A longitudinal MRI dataset of patients with multiple sclerosis was also used to evaluate the effect of a protocol change on atrophy calculations in a clinical research setting. The results show that atrophy calculations were substantially and significantly affected by protocol change, whereas such changes have a less significant effect and substantially reduced overall difference when using DeepHarmony. This establishes that DeepHarmony can be used with an overlap cohort to reduce inconsistencies in segmentation caused by changes in scanner protocol, allowing for modernization of hardware and protocol design in long-term studies without invalidating previously acquired data.