Bayesian model selection for pathological neuroimaging data applied to white matter lesion segmentation

Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions

Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.

White matter hyperintensities are seen only in GRN mutation carriers in the GENFI cohort

Genetic frontotemporal dementia is most commonly caused by mutations in the progranulin (GRN), microtubule-associated protein tau (MAPT) and chromosome 9 open reading frame 72 (C9orf72) genes. Previous small studies have reported the presence of cerebral white matter hyperintensities (WMH) in genetic FTD but this has not been systematically studied across the different mutations. In this study WMH were assessed in 180 participants from the Genetic FTD Initiative (GENFI) with 3D T1- and T2-weighed magnetic resonance images: 43 symptomatic (7 GRN, 13 MAPT and 23 C9orf72), 61 presymptomatic mutation carriers (25 GRN, 8 MAPT and 28 C9orf72) and 76 mutation negative non-carrier family members. An automatic detection and quantification algorithm was developed for determining load, location and appearance of WMH. Significant differences were seen only in the symptomatic GRN group compared with the other groups with no differences in the MAPT or C9orf72 groups: increased global load of WMH was seen, with WMH located in the frontal and occipital lobes more so than the parietal lobes, and nearer to the ventricles rather than juxtacortical. Although no differences were seen in the presymptomatic group as a whole, in the GRN cohort only there was an association of increased WMH volume with expected years from symptom onset. The appearance of the WMH was also different in the GRN group compared with the other groups, with the lesions in the GRN group being more similar to each other. The presence of WMH in those with progranulin deficiency may be related to the known role of progranulin in neuroinflammation, although other roles are also proposed including an effect on blood-brain barrier permeability and the cerebral vasculature. Future studies will be useful to investigate the longitudinal evolution of WMH and their potential use as a biomarker as well as post-mortem studies investigating the histopathological nature of the lesions.

•

In genetic FTD white matter hyperintensities (WMH) are found most prominently in symptomatic patients with GRN mutations.

•

Frontal and occipital lobes are the most affected regions.

•

WMH are more likely to occur close to the ventricles.

•

WMH have a more homogenous appearance possibly suggestive of inflammatory rather than vascular lesions.

Longitudinal multiple sclerosis lesion segmentation: Resource and challenge

In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time-points, and test data of fourteen subjects with a mean of 4.4 time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state-of-the-art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: (1) the sharing of a rich data set; (2) collaboration and comparison of the various avenues of research being pursued in the community; and (3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website2 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters.

Longitudinal segmentation of age-related white matter hyperintensities

Although white matter hyperintensities evolve in the course of ageing, few solutions exist to consider the lesion segmentation problem longitudinally. Based on an existing automatic lesion segmentation algorithm, a longitudinal extension is proposed. For evaluation purposes, a longitudinal lesion simulator is created allowing for the comparison between the longitudinal and the cross-sectional version in various situations of lesion load progression. Finally, applied to clinical data, the proposed framework demonstrates an increased robustness compared to available cross-sectional methods and findings are aligned with previously reported clinical patterns.

APOE ε4 status is associated with white matter hyperintensities volume accumulation rate independent of AD diagnosis

To assess the relationship between carriage of APOE ε4 allele and evolution of white matter hyperintensities (WMHs) volume, we longitudinally studied 339 subjects from the Alzheimer's Disease Neuroimaging Initiative cohort with diagnoses ranging from normal controls to probable Alzheimer's disease (AD). A purpose-built longitudinal automatic method was used to segment WMH using constraints derived from an atlas-based model selection applied to a time-averaged image. Linear mixed models were used to evaluate the differences in rate of change across diagnosis and genetic groups. After adjustment for covariates (age, sex, and total intracranial volume), homozygous APOE ε4ε4 subjects had a significantly higher rate of WMH accumulation (22.5% per year 95% CI [14.4, 31.2] for a standardized population having typical values of covariates) compared with the heterozygous (ε4ε3) subjects (10.0% per year [6.7, 13.4]) and homozygous ε3ε3 (6.6% per year [4.1, 9.3]) subjects. Rates of accumulation increased with diagnostic severity; controls accumulated 5.8% per year 95% CI: [2.2, 9.6] for the standardized population, early mild cognitive impairment 6.6% per year [3.9, 9.4], late mild cognitive impairment 12.5% per year [8.2, 17.0] and AD subjects 14.7% per year [6.0, 24.0]. Following adjustment for APOE status, these differences became nonstatistically significant suggesting that APOE ε4 genotype is the major driver of accumulation of WMH volume rather than diagnosis of AD.

Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation

We propose a novel segmentation approach based on deep 3D convolutional encoder networks with shortcut connections and apply it to the segmentation of multiple sclerosis (MS) lesions in magnetic resonance images. Our model is a neural network that consists of two interconnected pathways, a convolutional pathway, which learns increasingly more abstract and higher-level image features, and a deconvolutional pathway, which predicts the final segmentation at the voxel level. The joint training of the feature extraction and prediction pathways allows for the automatic learning of features at different scales that are optimized for accuracy for any given combination of image types and segmentation task. In addition, shortcut connections between the two pathways allow high- and low-level features to be integrated, which enables the segmentation of lesions across a wide range of sizes. We have evaluated our method on two publicly available data sets (MICCAI 2008 and ISBI 2015 challenges) with the results showing that our method performs comparably to the top-ranked state-of-the-art methods, even when only relatively small data sets are available for training. In addition, we have compared our method with five freely available and widely used MS lesion segmentation methods (EMS, LST-LPA, LST-LGA, Lesion-TOADS, and SLS) on a large data set from an MS clinical trial. The results show that our method consistently outperforms these other methods across a wide range of lesion sizes.