DEWS (DEep White matter hyperintensity Segmentation framework): A fully automated pipeline for detecting small deep white matter hyperintensities in migraineurs

Abstract

Migraineurs show an increased load of white matter hyperintensities (WMHs) and more rapid deep WMH progression. Previous methods for WMH segmentation have limited efficacy to detect small deep WMHs. We developed a new fully automated detection pipeline, DEWS (DEep White matter hyperintensity Segmentation framework), for small and superficially-located deep WMHs. A total of 148 non-elderly subjects with migraine were included in this study. The pipeline consists of three components: 1) white matter (WM) extraction, 2) WMH detection, and 3) false positive reduction. In WM extraction, we adjusted the WM mask to re-assign misclassified WMHs back to WM using many sequential low-level image processing steps. In WMH detection, the potential WMH clusters were detected using an intensity based threshold and region growing approach. For false positive reduction, the detected WMH clusters were classified into final WMHs and non-WMHs using the random forest (RF) classifier. Size, texture, and multi-scale deep features were used to train the RF classifier. DEWS successfully detected small deep WMHs with a high positive predictive value (PPV) of 0.98 and true positive rate (TPR) of 0.70 in the training and test sets. Similar performance of PPV (0.96) and TPR (0.68) was attained in the validation set. DEWS showed a superior performance in comparison with other methods. Our proposed pipeline is freely available online to help the research community in quantifying deep WMHs in non-elderly adults.

White matter hyperintensities in migraine: a review

“…Thus, we have developed a fully automated, machine learning-based, segmentation method for detecting small deep WMH in migraineurs and showed its superiority compared to pre-existing segmentation tools (Fig. 1) [64]. Recently, we also developed a deep learning-based detection method for the detection of small deep WMHs in migraineurs and obtained a slightly better result [65].…”

“…However, this method is less applicable for larger studies as it has an inter-rater/intra-rater reliability issue and lacks quanti- We compared several preexisting segmentation methods for detecting small deep WMHs in migraineurs aged 18 to 50 years, and their performance were poor in sensitivity and specificity [64]. Thus, we have developed a fully automated, machine learning-based, segmentation method for detecting small deep WMH in migraineurs and showed its superiority compared to pre-existing segmentation tools (Fig.…”

“…1st row, the fluid-attenuated inversion recovery (FLAIR) image corrected for magnetic field bias; 2nd row, manually drawn deep white matter hyperintensity (WMH) clusters (in yellow); 3rd row, deep WMH clusters segmented using our new pipeline (DEep White matter hyperintensity Segmentation framework [DEWS]), 4th to 6th rows, deep WMH clusters segmented using pre-existing segmentation pipelines: Wisconsin WMH Segmentation Toolbox (W2MHS), Brain Intensity AbNormality Classification Algorithm (BIANCA), and Lesion-TOpology-preserving Anatomical Segmentation (Lesion-TOADS), respectively. Adapted from Park et al [64].…”

Automatic Segmentation of White Matter Hyperintensities from Brain Magnetic Resonance Images in the Era of Deep Learning and Big Data – A Systematic Review

“…Nine of them also used additional datasets or patient data from clinics. Out of 37, twelve studies reported using data from prospective studies or clinics (Atlason et al, 2019;Bowles et al, 2017;Guerrero et al, 2017;Hong et al, 2020;Moeskops et al, 2018;Ling et al, 2018;Park et al, 2018;Qin et al, 2018;Rincón et al, 2017;Roy et al, 2015;Sundaresan et al, 2019;Wang et al, 2015). Four studies used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (Sudre et al, 2017;Dadar et al, 2017a;Rachmadi et al, 2018Rachmadi et al, , 2020, of which only two declared the subset used (Rachmadi et al, 2018(Rachmadi et al, , 2020.…”

Silent brain infarction: a quiet predictor of future stroke

“…Applications of artificial intelligence to stroke are increasing, and include diagnosis of acute ischemic stroke [36], prediction of stroke [37], predicting outcome after endovascular therapy [38], and pervasive health monitoring using smart monitoring devices [39]. Several studies of machine learning techniques to measure the severity of subclinical white matter changes have recently been reported [40], such as automated white matter segmentation algorithms to measure the severity of white matter hyperintensities in lacunar stroke [41,42], support vector machine techniques to classify the burden of perivascular space in the basal ganglia region [43], and cortical and subcortical volumetric segmentation of diffusion tensor imaging feature vectors [44].…”