White Matter Hyperintensities Segmentation Research Articles

Correlation between spatial navigation disorder and white matter hyperintensity in patients with mild cognitive impairment

Objective: To investigate the relationship between white matter lesions and spatial navigation ability in patients with mild cognitive impairment (MCI). Methods: A total of 32 MCI patients [age (66±11) years, 16 males and 16 females] who were treated in the Affiliated Drum Tower Hospital of Nanjing University Medical School from January 2015 to February 2018 were selected, and matched with age, gender and education level of 28 healthy controls (NC) [age (70±11) years, 19 males and 9 females] underwent spatial navigation ability test and neuropsychology scale evaluation. In the cross-sectional study, all subjects simultaneously underwent 3.0T magnetic resonance three-dimensional liquid inversion recovery sequence and high-resolution T(1) weighted imaging scan. The Wisconsin White Matter Hyperintensities Segmentation Toolbox (W2MHS) was used to automatically mark and extract the volume of the white matter hyperintensity. Results: The average error distances of egocentric virtual (P=0.002) and allocentric virtual (P=0.039) of MCI patients are greater than that of the control group, but the average error distance of mixed (allocentric-egocentric virtual) navigation had no statistic difference between two groups (P=0.070). The volume of the whole white matter hyperintensity, periventricular white matter hyperintensity, and deep white matter hyperintensity showed no significant differences between two groups (all P>0.05). Partial correlation analysis showed that after controlling for age, gender, education level and whole brain volume, the average error distance of mixed (allocentric-egocentric virtual) navigation in MCI patients was positively correlated to the volume of the whole white matter hyperintensity, deep white matter intensity, and periventricular white matter hyperintensity (r=0.469, 0.434, 0.512, all P<0.05). The average error distance of allocentric virtual navigation is positively correlated with the volume of periventricular white matter hyperintensity (r=0.403, P=0.033). There is no correlation between the average error distance of egocentric virtual navigation and the hyperintensity of white matter. Conclusions: The spatial navigation ability of patients with MCI is related to white matter lesions, which is of great significance for further research on the potential biological mechanisms affecting human spatial navigation ability.

Effects of White Matter Hyperintensities on 90-Day Functional Outcome after Large Vessel and Non-Large Vessel Stroke

Introduction: White matter hyperintensity (WMH) burden is a critically important cerebrovascular phenotype related to the diagnosis and prognosis of acute ischemic stroke. The effect of WMH burden on functional outcome in large vessel occlusion (LVO) stroke has only been sparsely assessed, and direct LVO and non-LVO comparisons are currently lacking. Material and Methods: We reviewed acute ischemic stroke patients admitted between 2009 and 2017 at a large healthcare system in the USA. Patients with LVO were identified and clinical characteristics, including 90-day functional outcomes, were assessed. Clinical brain MRIs obtained at the time of the stroke underwent quantification of WMH using a fully automated algorithm. The pipeline incorporated automated brain extraction, intensity normalization, and WMH segmentation. Results: A total of 1,601 acute ischemic strokes with documented 90-day mRS were identified, including 353 (22%) with LVO. Among those strokes, WMH volume was available in 1,285 (80.3%) who had a brain MRI suitable for WMH quantification. Increasing WMH volume from 0 to 4 mL, age, female gender, a number of stroke risk factors, presence of LVO, and higher NIHSS at presentation all decreased the odds for a favorable outcome. Increasing WMH above 4 mL, however, was not associated with decreasing odds of favorable outcome. While WMH volume was associated with functional outcome in non-LVO stroke (p = 0.0009), this association between WMH and functional status was not statistically significant in the complete case multivariable model of LVO stroke (p = 0.0637). Conclusion: The burden of WMH has effects on 90-day functional outcome after LVO and non-LVO strokes. Particularly, increases from no measurable WMH to 4 mL of WMH correlate strongly with the outcome. Whether this relationship of increasing WMH to worse outcome is more pronounced in non-LVO than LVO strokes deserves additional investigation.

U-net combined with CRF and anatomical based spatial features to segment white matter hyperintensities.

White matter hyperintensities (WMH) are important biomarkers for cerebral small vessel disease and closely associated with other neurodegenerative process. In this paper, we proposed a fully automatic WMH segmentation method based on U-net architecture. CRF were combined with U-net to refine segmentation results. We used a new anatomical based spatial feature produced by brain tissue segmentation based on T1 image, along with intensities of T1 and T2-FLAIR images to train our neural network. We compared 8 forms of automated WMH segmentation methods, range from traditional statistical learnng methods to deep learning based methods, with different architecture and used different features. Results showed our proposed method achieved best performance in terms of most metrics, and the inclusion of anatomical based spatial features strongly increase the segmentation performance.

Automated White Matter Hyperintensity Segmentation Using Bayesian Model Selection: Assessment and Correlations with Cognitive Change

Accurate, automated white matter hyperintensity (WMH) segmentations are needed for large-scale studies to understand contributions of WMH to neurological diseases. We evaluated Bayesian Model Selection (BaMoS), a hierarchical fully-unsupervised model selection framework for WMH segmentation. We compared BaMoS segmentations to semi-automated segmentations, and assessed whether they predicted longitudinal cognitive change in control, early Mild Cognitive Impairment (EMCI), late Mild Cognitive Impairment (LMCI), subjective/significant memory concern (SMC) and Alzheimer’s (AD) participants. Data were downloaded from the Alzheimer’s disease Neuroimaging Initiative (ADNI). Magnetic resonance images from 30 control and 30 AD participants were selected to incorporate multiple scanners, and were semi-automatically segmented by 4 raters and BaMoS. Segmentations were assessed using volume correlation, Dice score, and other spatial metrics. Linear mixed-effect models were fitted to 180 control, 107 SMC, 320 EMCI, 171 LMCI and 151 AD participants separately in each group, with the outcomes being cognitive change (e.g. mini-mental state examination; MMSE), and BaMoS WMH, age, sex, race and education used as predictors. There was a high level of agreement between BaMoS’ WMH segmentation volumes and a consensus of rater segmentations, with a median Dice score of 0.74 and correlation coefficient of 0.96. BaMoS WMH predicted cognitive change in: control, EMCI, and SMC groups using MMSE; LMCI using clinical dementia rating scale; and EMCI using Alzheimer’s disease assessment scale-cognitive subscale (p < 0.05, all tests). BaMoS compares well to semi-automated segmentation, is robust to different WMH loads and scanners, and can generate volumes which predict decline. BaMoS can be applicable to further large-scale studies.

Abstract TMP96: Automated Segmentation of White Matter Hyperintensities and Enlarged Perivascular Spaces in a Cohort of Patients With Acute Ischemic Stroke or Transient Ischemic Attack

Introduction: Cerebral Small Vessel Disease (CSVD) is a major cause of acute ischemic stroke (AIS), intracerebral hemorrhage and cognitive impairment. Methods to quantify the disease burden have been largely limited to white matter hyperintensities (WMH) as the disease surrogate and focused mainly on MRI sequences acquired for research purposes. We develop here novel methods to quantify WMH and enlarged perivascular spaces (EPVs) based on clinically acquired MRI sequences in patients with transient ischemic attack (TIA) or AIS. Methods: Subjects presenting with TIA or AIS and had brain MRI within 24 hour of hospital admission were selected for this study. Preprocessing pipeline was developed locally that included bias correction, image rescaling, rigid body registration to the Montreal Neurological Institute (MNI) space, skull stripping and intensity normalization. WMH segmentation was performed using a combination of global thresholding of FLAIR sequences that was spatially restricted to the white matter regions which were defined using a population-based atlas of age matched controls. EPVs in the basal ganglia were segmented on T2 sequences using adaptive thresholding of basal ganglia mask that was created from the ICBM template image and age-matched population average atlas. Segmented objects less than 3 mm in diameter were labelled as EPVs. Validation of the accuracy of EPVs segmentation was performed by expert counting of EPVs and WMH was validated using volume similarity against expert manual segmentation of WMH. Results: 41 patients (age 61.2±16.1, 65% males, 19.5% had TIAs, and 79.5% had AIS) were included. WMH volume was (manual: 21.34±20.48 mls vs automated: 15.74±14.56 mls) achieving a volume similarity of 0.92±0.01. EPVs in the basal ganglia counts were 16.32±5.4 using the automated method. Validation through comparison with manual segmentation of the axial slice with the highest EPVs (Doubal Method) showed significant correlation (Spearman’s rho=0.53, P = 0.0004). Conclusions: We describe successful segmentation of WMH and EPVs on clinically acquired MRI sequences in patients with TIA or AIS. This method will have applications to quantify CSVD burden in large clinical trials and clinical practice.

Abstract 28: Genetic Variants From Lysine-Specific Demethylase 4C (KDM4C) Associated With White Matter Hyperintensity Burden in Ischemic Stroke Patients

Introduction: Although white matter hyperintensities (WMH) have been linked to cerebrovascular disease, the exact pathogenesis is not known. The purpose of this study was to identify common variants associated with WMH burden among patients with an acute ischemic stroke (AIS) through a genome-wide association study (GWAS). Methods: A total of 946 AIS patients with validated European ancestry and MRI data were included in this study. WMH volume (WMHv), as a quantitative trait, was calculated by a fully-automated quantification process, which integrates the automated brain extraction, intensity normalization, and WMH segmentation using spatial priors. The GWAS was carried out by a linear mixed regression model (GEMMA), adjusted for covariates, to account for the potential population structure and relatedness. The WMHv ranked in top and bottom quantile were converted to a binary trait which represent high and low WMHv subgroups. Results: The rs10815506 (MAF = 0.043; β=3.89; p=6.66E-09), at an intronic region of KDM4C , which encodes Lysine-specific demethylase 4C , was the top signal associated with WMHv. This SNP is in high linkage disequilibrium (LD) (R 2 = 0.79; D’ = 0.93) with rs35389625, a nonsynonymous variant (Asn&gt;Ser), predicted to be pathogenic by SIFT and Polyphen. The rs35389625 was also associated with WMHv but at a lower significance level (MAF=0.040; β=3.19; p=3.21E-06). Patients with homozygous mutant alleles (GG) of rs35389625 showed significantly increased WMHv (14.93±10.15) than GA (7.94±8.48) and AA (5.09±5.85) carriers. Both rs10815506 and rs35389625 also predicted a subset of high and low WMHv group (OR=2.81, p=0.005; OR=2.42, p=0.016, respectively). No significant interaction between the top SNPs at KDM4C and other risk factors was identified in their association with WMHv. We also conducted a candidate-gene analysis by including several known SNPs, gathered from a reported meta-analysis for WMH. The frequency of MTHFR677 cytosine/thymine (rs1801133) showed difference between lower and upper quantile groups with OR=2.18 for T allele (p=0.030), the direction of which was consistent with previous studies. Conclusion: This study provides the first evidence that genetic variants at KDM4C are associated with WMH in AIS patients.

Hybrid Attention Densely Connected Ensemble Framework for Lesion Segmentation From Magnetic Resonance Images

White matter hyperintensities (WMHs) are associated with various neurological and aging diseases, and morphological analysis plays a crucial role in the assessment of disease progression. In this article, a novel hybrid attention densely connected ensemble framework is deployed for WMH segmentation from multi-modality magnetic resonance imaging (MRI). On the one hand, hybrid attention densely convolutional network (HA-DCN) is designed with a novel hybrid attention module embedded. The hybrid attention module can further improve the precision of lesion localization by extracting the complementary information of high-level features and low-level features from the spatial domain and channel domain. On the other hand, the focal Tversky loss function and generalized dice loss function derived from dice similarity coefficient are ensembled into the proposed framework, which achieves a trade-off between specificity and sensitivity. As a result, the volume of automation lesion segmentation is more agreeable to the manual lesion segmentation by experts. The proposed framework was evaluated online and offline in the MICCAI 2017 WMH segmentation challenge. A quantitative experiment has further demonstrated the effect of multi-modality and the effectiveness of the proposed hybrid attention densely connected ensemble framework. Furthermore, the challenge dataset consists of three scanners, reflecting the flexibility and robustness of the model. It also exhibits its potential for real-world clinical practice.

Fully automated segmentation on brain ischemic and white matter hyperintensities lesions using semantic segmentation networks with squeeze-and-excitation blocks in MRI

Abstract Ischemic stroke, a common disease in the elderly, can cause long-term disability and death. Quantitative measurement of brain ischemic lesions at the acute stage is vital for accurate diagnosis and treatment decisions for stroke patients. Currently, the manual segmentation of ischemic lesions is time-consuming, and it is difficult to extract potentially quantifiable information. These limitations can be overcome via deep learning, which has recently become a popular method to segment brain ischemic lesions in MRI. Fully automatic segmentation methods using deep learning quantitatively evaluate the infarct lesions and accurately identify lesions, localize fast lesions, and improve treatment planning. The state-of-the-art methods are variants of U-Net and are fully convolutional networks (FCN); however, these methods have a few limitations, including their inability to capture global features because of the encoder- and decoder-networks. To overcome this limitation, a semantic segmentation method using U-Net with squeeze-and-excitation (SE) blocks is proposed in this study. This method can improve channel-wise information with feature maps compared to a conventional network, to enhance the accuracy of brain lesion segmentation. Patients with acute infarction (N = 429) were retrospectively enrolled in this study with the approval of IRB. Various types of semantic segmentation networks with or without SE blocks were developed, and the accuracies were compared with conventional in-house and commercial software. The Dice similarity coefficient (DSC) of U-Net and Dense U-Net with SE blocks was 85.39 ± 0.84 and 84.23 ± 1.60, respectively. The DSCs increase by 3.5% and 0.9% on average. Accuracies of basic U-Net and Dense U-Net with SE blocks were significantly better than those of conventional image processing methods and those without SE blocks (p-values: 1.0e-08, 2.272e-05, and 0.0003, respectively). To additionally evaluate the methods, a public dataset of white matter hyperintensities (WMHs) segmentation challenge at MICCAI 2017 was used. In the WMH dataset, the DSCs of U-Net with or without SE blocks were 74.64 ± 1.11 and 76.92 ± 0.78, respectively. The DSC increases by 2.3% on average. The semantic segmentation with SE blocks exhibited significantly better performances than those without SE blocks. The solution can be applied to measure various brain segmentation problems, including infarct volume (at the acute stage of stroke patients) and WMH volume.

Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients

BackgroundManual segmentation is currently the gold standard to assess white matter hyperintensities (WMH), but it is time consuming and subject to intra and inter-operator variability. PurposeTo compare automatic methods to segment white matter hyperintensities (WMH) in the elderly in order to assist radiologist and researchers in selecting the most relevant method for application on clinical or research data. Material and MethodsWe studied a research dataset composed of 147 patients, including 97 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) 2 database and 50 patients from ADNI 3 and a clinical routine dataset comprising 60 patients referred for cognitive impairment at the Pitié-Salpêtrière hospital (imaged using four different MRI machines). We used manual segmentation as the gold standard reference. Both manual and automatic segmentations were performed using FLAIR MRI. We compared seven freely available methods that produce segmentation mask and are usable by a radiologist without a strong knowledge of computer programming: LGA (Schmidt et al., 2012), LPA (Schmidt, 2017), BIANCA (Griffanti et al., 2016), UBO detector (Jiang et al., 2018), W2MHS (Ithapu et al., 2014), nicMSlesion (with and without retraining) (Valverde et al., 2019, 2017). The primary outcome for assessing segmentation accuracy was the Dice similarity coefficient (DSC) between the manual and the automatic segmentation software. Secondary outcomes included five other metrics. ResultsA deep learning approach, NicMSlesion, retrained on data from the research dataset ADNI, performed best on this research dataset (DSC: 0.595) and its DSC was significantly higher than that of all others. However, it ranked fifth on the clinical routine dataset and its performance severely dropped on data with artifacts. On the clinical routine dataset, the three top-ranked methods were LPA, SLS and BIANCA. Their performance did not differ significantly but was significantly higher than that of other methods. ConclusionThis work provides an objective comparison of methods for WMH segmentation. Results can be used by radiologists to select a tool.

An improved algorithm of white matter hyperintensity detection in elderly adults.

Automated segmentation of the aging brain raises significant challenges because of the prevalence, extent, and heterogeneity of white matter hyperintensities. White matter hyperintensities can be frequently identified in magnetic resonance imaging (MRI) scans of older individuals and among those who have Alzheimer's disease. We propose OASIS-AD, a method for automatic segmentation of white matter hyperintensities in older adults using structural brain MRIs. OASIS-AD is an approach evolved from OASIS, which was developed for automatic lesion segmentation in multiple sclerosis. OASIS-AD is a major refinement of OASIS that takes into account the specific challenges raised by white matter hyperintensities in Alzheimer's disease. In particular, OASIS-AD combines three processing steps: 1) using an eroding procedure on the skull stripped mask; 2) adding a nearest neighbor feature construction approach; and 3) applying a Gaussian filter to refine segmentation results, creating a novel process for WMH detection in aging population. We show that OASIS-AD performs better than existing automatic white matter hyperintensity segmentation approaches.

Multi-Disease Segmentation of Gliomas and White Matter Hyperintensities in the BraTS Data Using a 3D Convolutional Neural Network

An important challenge in segmenting real-world biomedical imaging data is the presence of multiple disease processes within individual subjects. Most adults above age 60 exhibit a variable degree of small vessel ischemic disease, as well as chronic infarcts, which will manifest as white matter hyperintensities (WMH) on brain MRIs. Subjects diagnosed with gliomas will also typically exhibit some degree of abnormal T2 signal due to WMH, rather than just due to tumor. We sought to develop a fully automated algorithm to distinguish and quantify these distinct disease processes within individual subjects’ brain MRIs. To address this multi-disease problem, we trained a 3D U-Net to distinguish between abnormal signal arising from tumors vs. WMH in the 3D multi-parametric MRI (mpMRI, i.e., native T1-weighted, T1-post-contrast, T2, T2-FLAIR) scans of the International Brain Tumor Segmentation (BraTS) 2018 dataset (ntraining = 285, nvalidation = 66). Our trained neuroradiologist manually annotated WMH on the BraTS training subjects, finding that 69% of subjects had WMH. Our 3D U-Net model had a 4-channel 3D input patch (80 × 80 × 80) from mpMRI, four encoding and decoding layers, and an output of either four [background, active tumor (AT), necrotic core (NCR), peritumoral edematous/infiltrated tissue (ED)] or five classes (adding WMH as the fifth class). For both the four- and five-class output models, the median Dice for whole tumor (WT) extent (i.e., union of AT, ED, NCR) was 0.92 in both training and validation sets. Notably, the five-class model achieved significantly (p = 0.002) lower/better Hausdorff distances for WT extent in the training subjects. There was strong positive correlation between manually segmented and predicted volumes for WT (r = 0.96) and WMH (r = 0.89). Larger lesion volumes were positively correlated with higher/better Dice scores for WT (r = 0.33), WMH (r = 0.34), and across all lesions (r = 0.89) on a log(10) transformed scale. While the median Dice for WMH was 0.42 across training subjects with WMH, the median Dice was 0.62 for those with at least 5 cm3 of WMH. We anticipate the development of computational algorithms that are able to model multiple diseases within a single subject will be a critical step toward translating and integrating artificial intelligence systems into the heterogeneous real-world clinical workflow.

Deep convolutional neural network for accurate segmentation and quantification of white matter hyperintensities

White matter hyperintensities (WMHs) appear as regions of abnormally signal intensity on magnetic resonance imaging (MRI) images, that can be identified in MRI images of elderly people and ischemic stroke patients. However, manual segmentation and quantification of images with WMHs is laborious and time-consuming. Moreover, ischemic stroke lesion and WMHs appear as similar signals in MRI images, making it difficult to accurately segment the WMHs. Analysis of WMH-containing images is important for clinical diagnosis, and thus several segmentation methods have been proposed. However, these methods cannot accurately differentiate WMH and ischemic stroke lesions. We propose a deep convolutional neural network, M2DCNN, that can accurately segment WMHs and distinguish them from ischemic stroke lesions. M2DCNN consists of two subnets that rely on a set of novel multi-scale features and a novel architecture (inclusion of dense and dilated blocks). Our model is trained and evaluated on two public segmentation challenges with multi-modality MRI images. Empirical tests demonstrate that M2DCNN outperforms current segmentation methods. We empirically demonstrate that M2DCNN effectively separates WMHs from stroke lesions. Finally, ablation experiments reveal that both multi-scale features and architectural elements in our method contribute to the improved predictive performance.

Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images

We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered ”normal”. Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the state-of-the-art unsupervised lesions’ segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.

Performance of five automated white matter hyperintensity segmentation methods in a multicenter dataset

White matter hyperintensities (WMHs) are a common manifestation of cerebral small vessel disease, that is increasingly studied with large, pooled multicenter datasets. This data pooling increases statistical power, but poses challenges for automated WMH segmentation. Although there is extensive literature on the evaluation of automated WMH segmentation methods, such evaluations in a multicenter setting are lacking. We performed WMH segmentations in sixty patients scanned on six different magnetic resonance imaging (MRI) scanners (10 patients per scanner) using five freely available and fully-automated WMH segmentation methods (Cascade, kNN-TTP, Lesion-TOADS, LST-LGA and LST-LPA). Different MRI scanner vendors and field strengths were included. We compared these automated WMH segmentations with manual WMH segmentations as a reference. Performance of each method both within and across scanners was assessed using spatial and volumetric correspondence with the reference segmentations by Dice’s similarity coefficient (DSC) and intra-class correlation coefficient (ICC) respectively. We found the best performance, both within and across scanners, for kNN-TTP, followed by LST-LPA and LST-LGA, with worse performance for Lesion-TOADS and Cascade. Our findings can serve as a guide for choosing a method and also highlight the importance to further improve and evaluate consistency of methods in a multicenter setting.

White matter hyperintensities and their relationship to cognition: Effects of segmentation algorithm

White matter hyperintensities (WMHs) are brain white matter lesions that are hyperintense on fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) scans. Larger WMH volumes have been associated with Alzheimer’s disease (AD) and with cognitive decline. However, the relationship between WMH volumes and cross-sectional cognitive measures has been inconsistent. We hypothesize that this inconsistency may arise from 1) the presence of AD-specific neuropathology that may obscure any WMH effects on cognition, and 2) varying criteria for creating a WMH segmentation. Manual and automated programs are typically used to determine segmentation boundaries, but criteria for those boundaries can differ. It remains unclear whether WMH volumes are associated with cognitive deficits, and which segmentation criteria influence the relationships between WMH volumes and clinical outcomes.In a sample of 260 non-demented participants (ages 55–90, 141 males, 119 females) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), we compared the performance of five WMH segmentation methods, by relating the WMH volumes derived using each method to both clinical diagnosis and composite measures of executive function and memory. To separate WMH effects on cognition from effects related to AD-specific processes, we performed analyses separately in people with and without abnormal cerebrospinal fluid amyloid levels.WMH volume estimates that excluded more diffuse, lower-intensity lesions were more strongly correlated with clinical diagnosis and cognitive performance, and only in those without abnormal amyloid levels. These findings may inform best practices for WMH segmentation, and suggest that AD neuropathology may mask WMH effects on clinical diagnosis and cognition.

Two-step deep neural network for segmentation of deep white matter hyperintensities in migraineurs

Background and ObjectivePatients with migraine show an increased presence of white matter hyperintensities (WMHs), especially deep WMHs. Segmentation of small, deep WMHs is a critical issue in managing migraine care. Here, we aim to develop a novel approach to segmenting deep WMHs using deep neural networks based on the U-Net. Methods148 non-elderly subjects with migraine were recruited for this study. Our model consists of two networks: the first identifies potential deep WMH candidates, and the second reduces the false positives within the candidates. The first network for initial segmentation includes four down-sampling layers and four up-sampling layers to sort the candidates. The second network for false positive reduction uses a smaller field-of-view and depth than the first network to increase utilization of local information. ResultsOur proposed model segments deep WMHs with a high true positive rate of 0.88, a low false discovery rate of 0.13, and F1 score of 0.88 tested with ten-fold cross-validation. Our model was automatic and performed better than existing models based on conventional machine learning. ConclusionWe developed a novel segmentation framework tailored for deep WMHs using U-Net. Our algorithm is open-access to promote future research in quantifying deep WMHs and might contribute to the effective management of WMHs in migraineurs.

Automated lesion segmentation with BIANCA: Impact of population-level features, classification algorithm and locally adaptive thresholding

White matter hyperintensities (WMH) or white matter lesions exhibit high variability in their characteristics both at population- and subject-level, making their detection a challenging task. Population-level factors such as age, vascular risk factors and neurodegenerative diseases affect lesion load and spatial distribution. At the individual level, WMH vary in contrast, amount and distribution in different white matter regions.In this work, we aimed to improve BIANCA, the FSL tool for WMH segmentation, in order to better deal with these sources of variability. We worked on two stages of BIANCA by improving the lesion probability map estimation (classification stage) and making the lesion probability map thresholding stage automated and adaptive to local lesion probabilities. Firstly, in order to take into account the effect of population-level factors, we included population-level lesion probabilities, modelled with respect to a parametric factor (e.g. age), in the classification stage. Secondly, we tested BIANCA performance when using four alternative classifiers commonly used in the literature with respect to K-nearest neighbour algorithm (currently used for lesion probability map estimation in BIANCA). Finally, we propose LOCally Adaptive Threshold Estimation (LOCATE), a supervised method for determining optimal local thresholds to apply to the estimated lesion probability map, as an alternative option to global thresholding (i.e. applying the same threshold to the entire lesion probability map). For these experiments we used data from a neurodegenerative cohort, a vascular cohort and the cohorts available publicly as a part of a segmentation challenge.We observed that including population-level parametric lesion probabilities with respect to age and using alternative machine learning techniques provided negligible improvement. However, LOCATE provided a substantial improvement in the lesion segmentation performance, when compared to the global thresholding. It allowed to detect more deep lesions and provided better segmentation of periventricular lesion boundaries, despite the differences in the lesion spatial distribution and load across datasets. We further validated LOCATE on a cohort of CADASIL (Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy) patients, a genetic form of cerebral small vessel disease, and healthy controls, showing that LOCATE adapts well to wide variations in lesion load and spatial distribution.

Intra-Scanner and Inter-Scanner Reproducibility of Automatic White Matter Hyperintensities Quantification.

Objectives: To evaluate white matter hyperintensities (WMH) quantification reproducibility from multiple aspects of view and examine the effects of scan–rescan procedure, types of scanner, imaging protocols, scanner software upgrade, and automatic segmentation tools on WMH quantification results using magnetic resonance imaging (MRI).Methods: Six post-stroke subjects (4 males; mean age = 62.8, range = 58–72 years) were scanned and rescanned with both 3D T1-weighted, 2D and 3D T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) MRI across four different MRI scanners within 12 h. Two automated WMH segmentation and quantification tools were used to measure WMH volume based on each MR scan. Robustness was assessed using the coefficient of variation (CV), Dice similarity coefficient (DSC), and intra-class correlation (ICC).Results: Experimental results show that the best reproducibility was achieved by using 3D T2-FLAIR MRI under intra-scanner setting with CV ranging from 2.69 to 2.97%, while the largest variability resulted from comparing WMH volumes measured based on 2D T2-FLAIR MRI with those of 3D T2-FLAIR MRI, with CV values in the range of 15.62%–29.33%. The WMH quantification variability based on 2D MRIs is larger than 3D MRIs due to their large slice thickness. The DSC of WMH segmentation labels between intra-scanner MRIs ranges from 0.63 to 0.77, while that for inter-scanner MRIs is in the range of 0.63–0.65. In addition to image acquisition, the choice of automatic WMH segmentation tool also has a large impact on WMH quantification.Conclusion: WMH reproducibility is one of the primary issues to be considered in multicenter and longitudinal studies. The study provides solid guidance in assisting multicenter and longitudinal study design to achieve meaningful results with enough power.

P2‐410: A RISK FACTOR PROFILE OF INCREASED WHITE MATTER HYPERINTENSITY BURDEN IN THE ABERDEEN CHILDREN OF THE NINETEEN FIFTIES COHORT

The Aberdeen Children of the Nineteen Fifties (ACONF) is a well-characterised cohort of healthy, community-dwelling individuals, born in Aberdeen, Scotland (UK) between 1950 and 1956. This rich source of data allows us to investigate early- and mid-life risk factors for poor health in later life. Recently, subgroup of this cohort underwent brain magnetic resonance imaging (MRI), as well as health and neuropsychological assessments. Here, we aimed to utilise these life-course data to identify risk-factors for increased brain white matter hyperintensity (WMH) burden: a common MRI finding in older adults, associated with cognitive decline, dementia, stroke and death. We calculated the relative risk (RR) of certain factors on increased global WMH burden in 277 cognitively healthy ACONF participants (mean age = 62.3). Global WMH burden was measured as total WMH volume (ml) using an automated WMH segmentation algorithm. We investigated potential risk factors within the domains of demographics, early-life, medical history, socioeconomic circumstance, late-life objective health, and late-life cognition. We identified elevated risk factors for increased global WMH burden among each domain mentioned above. The most significant risk factors for increased WMH burden in this cohort included medical histories of stroke (RR = 2.642, 95% CI = 1.59 – 4.39), heart disease (RR = 1.864, 95% CI = 1.098 – 3.165), diabetes (RR = 1.903, 95% CI = 1.194 – 3.032), and high cholesterol (RR = 1.566, 95% CI = 1.077 – 2.277). Notable early- and mid-life risk factors approaching significance included birth weight of less than 5.5lbs (RR = 1.697, 95% CI = .913 – 3.153) and working in lower-income occupations (RR = 1.049, 95% CI = .715 – 1.538). We were able to confirm age and cardiometabolic risk factors for increased WMH burden in a relatively young cohort of older adults, and add contributions of emerging early and mid-life risk factors. Many of these cardiometabolic risk factors have their origins in early life and are greatest in those with the least resilience. Future work will involve developing a robust model of risk- and protective determinants of WMH burden.

Dilated Saliency U-Net for White Matter Hyperintensities Segmentation Using Irregularity Age Map.

White matter hyperintensities (WMH) appear as regions of abnormally high signal intensity on T2-weighted magnetic resonance image (MRI) sequences. In particular, WMH have been noteworthy in age-related neuroscience for being a crucial biomarker for all types of dementia and brain aging processes. The automatic WMH segmentation is challenging because of their variable intensity range, size and shape. U-Net tackles this problem through the dense prediction and has shown competitive performances not only on WMH segmentation/detection but also on varied image segmentation tasks. However, its network architecture is high complex. In this study, we propose the use of Saliency U-Net and Irregularity map (IAM) to decrease the U-Net architectural complexity without performance loss. We trained Saliency U-Net using both: a T2-FLAIR MRI sequence and its correspondent IAM. Since IAM guides locating image intensity irregularities, in which WMH are possibly included, in the MRI slice, Saliency U-Net performs better than the original U-Net trained only using T2-FLAIR. The best performance was achieved with fewer parameters and shorter training time. Moreover, the application of dilated convolution enhanced Saliency U-Net by recognizing the shape of large WMH more accurately through multi-context learning. This network named Dilated Saliency U-Net improved Dice coefficient score to 0.5588 which was the best score among our experimental models, and recorded a relatively good sensitivity of 0.4747 with the shortest training time and the least number of parameters. In conclusion, based on our experimental results, incorporating IAM through Dilated Saliency U-Net resulted an appropriate approach for WMH segmentation.