Site- and frequency-specific enhancement of visual search performance with online individual alpha frequency (IAF) repetitive transcranial magnetic stimulation (rTMS) to the inferior frontal junction.

In this study, repetitive transcranial magnetic stimulation was applied to either the right inferior frontal junction or the right inferior parietal cortex during a difficult aerial reconnaissance search task to test its capacity to improve search performance. Two stimulation strategies previously found to enhance cognitive performance were tested: The first is called "addition by subtraction," and the second condition utilizes a direct excitatory approach by applying brief trains of high-frequency repetitive transcranial magnetic stimulation immediately before task trials. In a within-subjects design, participants were given active or sham repetitive transcranial magnetic stimulation at either 1 Hz or at 1 Hz above their individual peak alpha frequency (IAF + 1, mean 11.5 Hz), delivered to either the right inferior frontal junction or the right inferior parietal cortex, both defined with individualized peak functional magnetic resonance imaging (fMRI) activation obtained during the visual search task. Results indicated that among the 13 participants who completed the protocol, only active IAF + 1 stimulation to inferior frontal junction resulted in significant speeding of reaction time compared to sham. This site- and frequency-specific enhancement of performance with IAF + 1 repetitive transcranial magnetic stimulation applied immediately prior to task trials provides evidence for the involvement of inferior frontal junction in guiding difficult visual search, and more generally for the use of online repetitive transcranial magnetic stimulation directed at specific functional networks to enhance visual search performance.

Transcutaneous cervical vagus nerve stimulation enhances second-language vocabulary acquisition while simultaneously mitigating fatigue and promoting focus.

Transcutaneous vagus nerve stimulation (tVNS) is a promising technique for enhancing cognitive performance and skill acquisition. Yet, its efficacy for enhancing learning rate and long-term retention in an ecologically valid learning environment has not been demonstrated. We conducted two double-blind sham-controlled experiments examining the efficacy of auricular tVNS (taVNS: Experiment (1) and cervical tVNS (tcVNS: Experiment (2), on a 5 day second-language vocabulary acquisition protocol among highly selected career linguists at the US Department of Defense's premier language school. tcVNS produced accelerated recall performance during training (Day 2-4), benefits of which were maintained across a 24 h retention interval with no stimulation at the final test. Consistent with prior work, tcVNS also produced fatigue-mitigating and focus-promoting effects as measured by the Air Force Research Laboratory Mood Questionnaire. Based on the current and the previous findings supporting tVNS' efficacy on performance, training enhancement, and fatigue mitigation, we believe tcVNS to be an effective learning acceleration tool that can be utilized at language-teaching and other institutions focused on intensive training of cognitive skills.

Characterization of Polarimetric Properties in Various Brain Tumor Types Using Wide-Field Imaging Mueller Polarimetry.

Neuro-oncological surgery is the primary brain cancer treatment, yet it faces challenges with gliomas due to their invasiveness and the need to preserve neurological function. Hence, radical resection is often unfeasible, highlighting the importance of precise tumor margin delineation to prevent neurological deficits and improve prognosis. Imaging Mueller polarimetry, an effective modality in various organ tissues, seems a promising approach for tumor delineation in neurosurgery. To further assess its use, we characterized the polarimetric properties by analysing 45 polarimetric measurements of 27 fresh brain tumor samples, including different tumor types with a strong focus on gliomas. Our study integrates a wide-field imaging Mueller polarimetric system and a novel neuropathology protocol, correlating polarimetric and histological data for accurate tissue identification. An image processing pipeline facilitated the alignment and overlay of polarimetric images and histological masks. Variations in depolarization values were observed for grey and white matter of brain tumor tissue, while differences in linear retardance were seen only within white matter of brain tumor tissue. Notably, we identified pronounced optical axis azimuth randomization within tumor regions. This study lays the foundation for machine learning-based brain tumor segmentation algorithms using polarimetric data, facilitating intraoperative diagnosis and decision making.

Cortical thickness and grey-matter volume anomaly detection in individual MRI scans: Comparison of two methods.

Over the past decades, morphometric analysis of brain MRI has contributed substantially to the understanding of healthy brain structure, development and aging as well as to improved characterisation of disease related pathologies. Certified commercial tools based on normative modeling of these metrics are meanwhile available for diagnostic purposes, but they are cost intensive and their clinical evaluation is still in its infancy. Here we have compared the performance of "ScanOMetrics", an open-source research-level tool for detection of statistical anomalies in individual MRI scans, depending on whether it is operated on the output of FreeSurfer or of the deep learning based brain morphometry tool DL + DiReCT. When applied to the public OASIS3 dataset, containing patients with Alzheimer's disease (AD) and healthy controls (HC), cortical thickness anomalies in patient scans were mainly detected in regions that are known as predilection areas of cortical atrophy in AD, regardless of the software used for extraction of the metrics. By contrast, anomaly detections in HCs were up to twenty-fold reduced and spatially unspecific using both DL + DiReCT and FreeSurfer. Progression of the atrophy pattern with clinical dementia rating (CDR) was clearly observable with both methods. DL + DiReCT provided results in less than 25 min, more than 15 times faster than FreeSurfer. This difference in computation time might be relevant when considering application of this or similar methodology as diagnostic decision support for neuroradiologists.

Transient brain structure changes after high phenylalanine exposure in adults with phenylketonuria.

Phenylketonuria is a rare metabolic disease resulting from a deficiency of the enzyme phenylalanine hydroxylase. Recent cross-sectional evidence suggests that early-treated adults with phenylketonuria exhibit alterations in cortical grey matter compared to healthy peers. However, the effects of high phenylalanine exposure on brain structure in adulthood need to be further elucidated. In this double-blind, randomised, placebo-controlled crossover trial, we investigated the impact of a four-week high phenylalanine exposure on the brain structure and its relationship to cognitive performance and metabolic parameters in early-treated adults with phenylketonuria. Twenty-eight adult patients with early-treated classical phenylketonuria (19-48 years) underwent magnetic resonance imaging before and after the four-week phenylalanine and placebo interventions (four timepoints). Structural T1-weighted images were preprocessed and evaluated using DL+DiReCT, a deep-learning-based tool for brain morphometric analysis. Cortical thickness, white matter volume, and ventricular volume were compared between the phenylalanine and placebo periods. Brain phenylalanine levels were measured using 1H spectroscopy. Blood levels of phenylalanine, tyrosine, and tryptophan were assessed at each of the four timepoints, along with performance in executive functions and attention. Blood phenylalanine levels were significantly higher after the phenylalanine period (1441µmol/L) than after the placebo period (873µmol/L, P<0.001). Morphometric analyses revealed a statistically significant decrease in cortical thickness in 17 out of 60 brain regions after the phenylalanine period compared to placebo. The largest decreases were observed in the right pars orbitalis (point estimate=-0.095mm, P<0.001) and the left lingual gyrus (point estimate=-0.070mm, P<0.001). Bilateral white matter and ventricular volumes were significantly increased after the phenylalanine period. However, the structural alterations in the Phe-placebo group returned to baseline measures following the washout and placebo period. Additionally, elevated blood and brain phenylalanine levels were related to increased bilateral white matter volume (rs=0.43 to 0.51, P≤0.036) and decreased cortical thickness (rs=-0.62 to -0.39, not surviving FDR correction) after the phenylalanine and placebo periods. Moreover, decreased cortical thickness was correlated with worse cognitive performance after both periods (rs=-0.54 to -0.40, not surviving FDR correction). These findings provide evidence that a four-week high phenylalanine exposure in adults with phenylketonuria results in transient reductions of the cortical grey matter and increases in white matter volume. Further research is needed to determine the potential long-term impact of high phenylalanine levels on brain structure and function in adults with phenylketonuria.

Near-real-time Mueller polarimetric image processing for neurosurgical intervention.

PURPOSE: Wide-field imaging Mueller polarimetry is a revolutionary, label-free, and non-invasive modality for computer-aided intervention; in neurosurgery, it aims to provide visual feedback of white matter fibre bundle orientation from derived parameters. Conventionally, robust polarimetric parameters are estimated after averaging multiple measurements of intensity for each pair of probing and detected polarised light. Long multi-shot averaging, however, is not compatible with real-time in vivo imaging, and the current performance of polarimetric data processing hinders the translation to clinical practice. METHODS: A learning-based denoising framework is tailored for fast, single-shot, noisy acquisitions of polarimetric intensities. Also, performance-optimised image processing tools are devised for the derivation of clinically relevant parameters. The combination recovers accurate polarimetric parameters from fast acquisitions with near-real-time performance, under the assumption of pseudo-Gaussian polarimetric acquisition noise. RESULTS: The denoising framework is trained, validated, and tested on experimental data comprising tumour-free and diseased human brain samples in different conditions. Accuracy and image quality indices showed significant ( p < 0.05 ) improvements on testing data for a fast single-pass denoising versus the state-of-the-art and high polarimetric image quality standards. The computational time is reported for the end-to-end processing. CONCLUSION: The end-to-end image processing achieved real-time performance for a localised field of view ( ≈ 6.5 mm 2 ). The denoised polarimetric intensities produced visibly clear directional patterns of neuronal fibre tracts in line with reference polarimetric image quality standards; directional disruption was kept in case of neoplastic lesions. The presented advances pave the way towards feasible oncological neurosurgical translations of novel, label-free, interventional feedback.

Recommendations for a Military Health System Auditory Blast Injury Prevention Standard.

INTRODUCTION: Although existing auditory injury prevention standards benefit warfighters, the Department of Defense could do more to understand and address auditory injuries (e.g., hearing loss, tinnitus, and central processing deficits) among service members. The Blast Injury Prevention Standards Recommendation (BIPSR) Process is designed to address the needs of all the Military Services for biomedically valid Military Health System (MHS) Blast Injury Prevention Standards. MATERIALS AND METHODS: Through the BIPSR Process, stakeholders provided their intended uses and requested functionalities for an MHS Blast Injury Prevention Standard. The BIPSR Process established a broad-based, non-advocacy panel of auditory injury Subject Matter Expert (SME) Panel with members drawn from industry, academia, and government. The SME Panel selected evaluation factors, weighted priorities, and then evaluated the resulting candidate MHS Auditory Blast Injury Prevention Standards against the evaluation criteria. The SME Panel members provided rationales for their decisions, documented discussions, and used iterative rounds of feedback to promote consensus building among members. The BIPSR Process used multi-attribute utility theory to combine members' evaluations and compare the candidate standards. RESULTS: The SME Panel identified and collated information about existing auditory injury datasets to identify gaps and promote data sharing and comprehensive evaluations of standards for preventing auditory blast injury. The panel evaluated the candidate standards and developed recommendations for an MHS Blast Injury Prevention Standard. CONCLUSIONS: The BIPSR Process illuminated important characteristics, capabilities, and limitations of candidate standards and existing datasets (e.g., limited human exposure data to evaluate the validity of injury prediction) for auditory blast injury prevention. The evaluation resulted in the recommendation to use the 8-hour Equivalent Level (LAeq8hr) as the interim MHS Auditory Blast Injury Prevention Standard while the community performs additional research to fill critical knowledge gaps.

Effects of formalin fixation on polarimetric properties of brain tissue: fresh or fixed?

Significance: Imaging Mueller polarimetry (IMP) appears as a promising technique for real-time delineation of healthy and neoplastic tissue during neurosurgery. The training of machine learning algorithms used for the image post-processing requires large data sets typically derived from the measurements of formalin-fixed brain sections. However, the success of the transfer of such algorithms from fixed to fresh brain tissue depends on the degree of alterations of polarimetric properties induced by formalin fixation (FF). Aim: Comprehensive studies were performed on the FF induced changes in fresh pig brain tissue polarimetric properties. Approach: Polarimetric properties of pig brain were assessed in 30 coronal thick sections before and after FF using a wide-field IMP system. The width of the uncertainty region between gray and white matter was also estimated. Results: The depolarization increased by 5% in gray matter and remained constant in white matter following FF, whereas the linear retardance decreased by 27% in gray matter and by 28% in white matter after FF. The visual contrast between gray and white matter and fiber tracking remained preserved after FF. Tissue shrinkage induced by FF did not have a significant effect on the uncertainty region width. Conclusions: Similar polarimetric properties were observed in both fresh and fixed brain tissues, indicating a high potential for transfer learning.

Robustness of the wide-field imaging Mueller polarimetry for brain tissue differentiation and white matter fiber tract identification in a surgery-like environment: an ex vivo study.

During neurooncological surgery, the visual differentiation of healthy and diseased tissue is often challenging. Wide-field imaging Muller polarimetry (IMP) is a promising technique for tissue discrimination and in-plane brain fiber tracking in an interventional setup. However, the intraoperative implementation of IMP requires realizing imaging in the presence of remanent blood, and complex surface topography resulting from the use of an ultrasonic cavitation device. We report on the impact of both factors on the quality of polarimetric images of the surgical resection cavities reproduced in fresh animal cadaveric brains. The robustness of IMP is observed under adverse experimental conditions, suggesting a feasible translation of IMP for in vivo neurosurgical applications.

Reliable brain morphometry from contrast-enhanced T1w-MRI in patients with multiple sclerosis.

Brain morphometry is usually based on non-enhanced (pre-contrast) T1-weighted MRI. However, such dedicated protocols are sometimes missing in clinical examinations. Instead, an image with a contrast agent is often available. Existing tools such as FreeSurfer yield unreliable results when applied to contrast-enhanced (CE) images. Consequently, these acquisitions are excluded from retrospective morphometry studies, which reduces the sample size. We hypothesize that deep learning (DL)-based morphometry methods can extract morphometric measures also from contrast-enhanced MRI. We have extended DL+DiReCT to cope with contrast-enhanced MRI. Training data for our DL-based model were enriched with non-enhanced and CE image pairs from the same session. The segmentations were derived with FreeSurfer from the non-enhanced image and used as ground truth for the coregistered CE image. A longitudinal dataset of patients with multiple sclerosis (MS), comprising relapsing remitting (RRMS) and primary progressive (PPMS) subgroups, was used for the evaluation. Global and regional cortical thickness derived from non-enhanced and CE images were contrasted to results from FreeSurfer. Correlation coefficients of global mean cortical thickness between non-enhanced and CE images were significantly larger with DL+DiReCT (r = 0.92) than with FreeSurfer (r = 0.75). When comparing the longitudinal atrophy rates between the two MS subgroups, the effect sizes between PPMS and RRMS were higher with DL+DiReCT both for non-enhanced (d = -0.304) and CE images (d = -0.169) than for FreeSurfer (non-enhanced d = -0.111, CE d = 0.085). In conclusion, brain morphometry can be derived reliably from contrast-enhanced MRI using DL-based morphometry tools, making additional cases available for analysis and potential future diagnostic morphometry tools.

What Is Targeted When We Train Working Memory? Evidence From a Meta-Analysis of the Neural Correlates of Working Memory Training Using Activation Likelihood Estimation.

Working memory (WM) is the system responsible for maintaining and manipulating information, in the face of ongoing distraction. In turn, WM span is perceived to be an individual-differences construct reflecting the limited capacity of this system. Recently, however, there has been some evidence to suggest that WM capacity can increase through training, raising the possibility that training can functionally alter the neural structures supporting WM. To address the hypothesis that the neural substrates underlying WM are targeted by training, we conducted a meta-analysis of functional magnetic resonance imaging (fMRI) studies of WM training using Activation Likelihood Estimation (ALE). Our results demonstrate that WM training is associated exclusively with decreases in blood oxygenation level-dependent (BOLD) responses in clusters within the fronto-parietal system that underlie WM, including the bilateral inferior parietal lobule (BA 39/40), middle (BA 9) and superior (BA 6) frontal gyri, and medial frontal gyrus bordering on the cingulate gyrus (BA 8/32). We discuss the various psychological and physiological mechanisms that could be responsible for the observed reductions in the BOLD signal in relation to WM training, and consider their implications for the construct of WM span as a limited resource.

A Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis Derived From Deep Learning-Based Segmentation of T1w-MRI.

PURPOSE: Hippocampal volumetry is an important biomarker to quantify atrophy in patients with mesial temporal lobe epilepsy. We investigate the sensitivity of automated segmentation methods to support radiological assessments of hippocampal sclerosis (HS). Results from FreeSurfer and FSL-FIRST are contrasted to a deep learning (DL)-based segmentation method. MATERIALS AND METHODS: We used T1-weighted MRI scans from 105 patients with epilepsy and 354 healthy controls. FreeSurfer, FSL, and a DL-based method were applied for brain anatomy segmentation. We calculated effect sizes (Cohen's d) between left/right HS and healthy controls based on the asymmetry of hippocampal volumes. Additionally, we derived 14 shape features from the segmentations and determined the most discriminating feature to identify patients with hippocampal sclerosis by a support vector machine (SVM). RESULTS: Deep learning-based segmentation of the hippocampus was the most sensitive to detecting HS. The effect sizes of the volume asymmetries were larger with the DL-based segmentations (HS left d= -4.2, right = 4.2) than with FreeSurfer (left= -3.1, right = 3.7) and FSL (left= -2.3, right = 2.5). For the classification based on the shape features, the surface-to-volume ratio was identified as the most important feature. Its absolute asymmetry yielded a higher area under the curve (AUC) for the deep learning-based segmentation (AUC = 0.87) than for FreeSurfer (0.85) and FSL (0.78) to dichotomize HS from other epilepsy cases. The robustness estimated from repeated scans was statistically significantly higher with DL than all other methods. CONCLUSION: Our findings suggest that deep learning-based segmentation methods yield a higher sensitivity to quantify hippocampal sclerosis than atlas-based methods and derived shape features are more robust. We propose an increased asymmetry in the surface-to-volume ratio of the hippocampus as an easy-to-interpret quantitative imaging biomarker for HS.

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.

Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks.

Segmentation of white matter lesions and deep grey matter structures is an important task in the quantification of magnetic resonance imaging in multiple sclerosis. In this paper we explore segmentation solutions based on convolutional neural networks (CNNs) for providing fast, reliable segmentations of lesions and grey-matter structures in multi-modal MR imaging, and the performance of these methods when applied to out-of-centre data. We trained two state-of-the-art fully convolutional CNN architectures on the 2016 MSSEG training dataset, which was annotated by seven independent human raters: a reference implementation of a 3D Unet, and a more recently proposed 3D-to-2D architecture (DeepSCAN). We then retrained those methods on a larger dataset from a single centre, with and without labels for other brain structures. We quantified changes in performance owing to dataset shift, and changes in performance by adding the additional brain-structure labels. We also compared performance with freely available reference methods. Both fully-convolutional CNN methods substantially outperform other approaches in the literature when trained and evaluated in cross-validation on the MSSEG dataset, showing agreement with human raters in the range of human inter-rater variability. Both architectures showed drops in performance when trained on single-centre data and tested on the MSSEG dataset. When trained with the addition of weak anatomical labels derived from Freesurfer, the performance of the 3D Unet degraded, while the performance of the DeepSCAN net improved. Overall, the DeepSCAN network predicting both lesion and anatomical labels was the best-performing network examined.

Direct cortical thickness estimation using deep learning-based anatomy segmentation and cortex parcellation.

Accurate and reliable measures of cortical thickness from magnetic resonance imaging are an important biomarker to study neurodegenerative and neurological disorders. Diffeomorphic registration-based cortical thickness (DiReCT) is a known technique to derive such measures from non-surface-based volumetric tissue maps. ANTs provides an open-source method for estimating cortical thickness, derived by applying DiReCT to an atlas-based segmentation. In this paper, we propose DL+DiReCT, a method using high-quality deep learning-based neuroanatomy segmentations followed by DiReCT, yielding accurate and reliable cortical thickness measures in a short time. We evaluate the methods on two independent datasets and compare the results against surface-based measures from FreeSurfer. Good correlation of DL+DiReCT with FreeSurfer was observed (r = .887) for global mean cortical thickness compared to ANTs versus FreeSurfer (r = .608). Experiments suggest that both DiReCT-based methods had higher sensitivity to changes in cortical thickness than Freesurfer. However, while ANTs showed low scan-rescan robustness, DL+DiReCT showed similar robustness to Freesurfer. Effect-sizes for group-wise differences of healthy controls compared to individuals with dementia were highest with the deep learning-based segmentation. DL+DiReCT is a promising combination of a deep learning-based method with a traditional registration technique to detect subtle changes in cortical thickness.

TDCS to the right anterior temporal lobe facilitates insight problem-solving.

Problem-solving is essential for advances in cultural, social, and scientific knowledge. It is also one of the most challenging cognitive processes to facilitate. Some problem-solving is deliberate, but frequently people solve problems with a sudden insight, also known as a Eureka or "Aha!" moment. The advantage of solving problems via insight is that these solutions are more accurate, relying on a unique pattern of neural activity, compared to deliberative strategies. The right Anterior Temporal Lobe (rATL), putatively involved in semantic integration, is distinctively activated when people experience an insight. The rATL may contribute to the recognition of distant semantic relations that support insight solutions, although fMRI and EEG evidence for its involvement is, by nature, correlational. In this study, we investigate if focal sub-threshold neuromodulation to the rATL facilitates insight problem-solving. In three different groups, using a within- and between-subjects design, we tested the causal role of this brain region in problem-solving, by applying High Definition Transcranial Direct Current Stimulation to the rATL (active and sham condition) or the left frontopolar region while participants attempted to solve Compound Remote Associates problems before, during and after stimulation. Participants solved a higher percentage of problems, overall, and specifically by insight when they received rATL stimulation, compared to pre-stimulation, and compared to sham and left frontopolar stimulation. These results confirm the crucial role played by the rATL in insight problem-solving.

Automatic detection of lesion load change in Multiple Sclerosis using convolutional neural networks with segmentation confidence.

The detection of new or enlarged white-matter lesions is a vital task in the monitoring of patients undergoing disease-modifying treatment for multiple sclerosis. However, the definition of 'new or enlarged' is not fixed, and it is known that lesion-counting is highly subjective, with high degree of inter- and intra-rater variability. Automated methods for lesion quantification, if accurate enough, hold the potential to make the detection of new and enlarged lesions consistent and repeatable. However, the majority of lesion segmentation algorithms are not evaluated for their ability to separate radiologically progressive from radiologically stable patients, despite this being a pressing clinical use-case. In this paper, we explore the ability of a deep learning segmentation classifier to separate stable from progressive patients by lesion volume and lesion count, and find that neither measure provides a good separation. Instead, we propose a method for identifying lesion changes of high certainty, and establish on an internal dataset of longitudinal multiple sclerosis cases that this method is able to separate progressive from stable time-points with a very high level of discrimination (AUC = 0.999), while changes in lesion volume are much less able to perform this separation (AUC = 0.71). Validation of the method on two external datasets confirms that the method is able to generalize beyond the setting in which it was trained, achieving an accuracies of 75 % and 85 % in separating stable and progressive time-points.

Divide and Conquer: Stratifying Training Data by Tumor Grade Improves Deep Learning-Based Brain Tumor Segmentation.

It is a general assumption in deep learning that more training data leads to better performance, and that models will learn to generalize well across heterogeneous input data as long as that variety is represented in the training set. Segmentation of brain tumors is a well-investigated topic in medical image computing, owing primarily to the availability of a large publicly-available dataset arising from the long-running yearly Multimodal Brain Tumor Segmentation (BraTS) challenge. Research efforts and publications addressing this dataset focus predominantly on technical improvements of model architectures and less on properties of the underlying data. Using the dataset and the method ranked third in the BraTS 2018 challenge, we performed experiments to examine the impact of tumor type on segmentation performance. We propose to stratify the training dataset into high-grade glioma (HGG) and low-grade glioma (LGG) subjects and train two separate models. Although we observed only minor gains in overall mean dice scores by this stratification, examining case-wise rankings of individual subjects revealed statistically significant improvements. Compared to a baseline model trained on both HGG and LGG cases, two separately trained models led to better performance in 64.9% of cases (p < 0.0001) for the tumor core. An analysis of subjects which did not profit from stratified training revealed that cases were missegmented which had poor image quality, or which presented clinically particularly challenging cases (e.g., underrepresented subtypes such as IDH1-mutant tumors), underlining the importance of such latent variables in the context of tumor segmentation. In summary, we found that segmentation models trained on the BraTS 2018 dataset, stratified according to tumor type, lead to a significant increase in segmentation performance. Furthermore, we demonstrated that this gain in segmentation performance is evident in the case-wise ranking of individual subjects but not in summary statistics. We conclude that it may be useful to consider the segmentation of brain tumors of different types or grades as separate tasks, rather than developing one tool to segment them all. Consequently, making this information available for the test data should be considered, potentially leading to a more clinically relevant BraTS competition.

Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge.

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. The automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their methods on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge. Sixty T1 + FLAIR images from three MR scanners were released with the manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. The segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: 1) Dice similarity coefficient; 2) modified Hausdorff distance (95th percentile); 3) absolute log-transformed volume difference; 4) sensitivity for detecting individual lesions; and 5) F1-score for individual lesions. In addition, the methods were ranked on their inter-scanner robustness; 20 participants submitted their methods for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all the methods generalize to unseen scanners. The challenge remains open for future submissions and provides a public platform for method evaluation.