White Matter Hyperintensities Segmentation Research Articles

Artificial intelligence for volumetric measurement of cerebral white matter hyperintensities on thick-slice fluid-attenuated inversion recovery (FLAIR) magnetic resonance images from multiple centers

We aimed to develop a new artificial intelligence software that can automatically extract and measure the volume of white matter hyperintensities (WMHs) in head magnetic resonance imaging (MRI) using only thick-slice fluid-attenuated inversion recovery (FLAIR) sequences from multiple centers. We enrolled 1092 participants in Japan, comprising the thick-slice Private Dataset. Based on 207 randomly selected participants, neuroradiologists annotated WMHs using predefined guidelines. The annotated images of participants were divided into training (n = 138) and test (n = 69) datasets. The WMH segmentation model comprised a U-Net ensemble and was trained using the Private Dataset. Two other models were trained for validation using either both thin- and thick-slice MRI datasets or the thin-slice dataset alone. The voxel-wise Dice similarity coefficient (DSC) was used as the evaluation metric. The model trained using only thick-slice MRI showed a DSC of 0.820 for the test dataset, which is comparable to the accuracy of human readers. The model trained with the additional thin-slice dataset showed only a slightly improved DSC of 0.822. This automatic WMH segmentation model comprising a U-Net ensemble trained on a thick-slice FLAIR MRI dataset is a promising new method. Despite some limitations, this model may be applicable in clinical practice.

Abstract TP25: Model-Free Dynamic Contrast-Enhanced MRI in Cerebral Small Vessel Disease: Test-Retest Reliability and Association With WMH Lesion Burden

Introduction: Dynamic contrast enhanced (DCE)-MRI has been used to study blood-brain barrier (BBB) disruption in cerebral small vessel disease (CSVD), but complex kinetic modeling of DCE MRI is sensitive to noise and is not robust in detecting subtle BBB impairments. In contrast, model-free DCE is simple and does not require arterial input function and complex computation. In this study, we aimed to evaluate the test-retest repeatability of model-free DCE and its association with white matter hyperintensity (WMH) burden. Methods: Patients with CSVD were recruited. DCE-MRI, FLAIR, and T1 MPRage scans were acquired. A subgroup of patients had two repeated DCE MRI scans with an average interval of 41 days. WMH segmentation was performed to obtain the relative volume of WMH (rVwmh). Ten subjects had DCE-MRI data in two sessions for test-retest repeatability analysis. DCE-MRI were acquired using a Siemens volumetric interpolated breath-hold examination (VIBE) gradient echo sequence with a temporal resolution of 49 seconds and an acquisition time of ~20 minutes. The wash-out slope (WOS), which indicates the rate of contrast agent leaving the tissue, was computed. Results: 64 patients (mean (SD) age = 68.6 (8.51), 37 females) with CSVD were studied. WOS demonstrated good test-retest repeatability for WM and GM with an intra-class correlation coefficient (ICC) of 0.626 and 0.671 in cerebrum WM and GM, respectively. WMH WOS has a significant negative correlation with rVwmh (r=-0.31; p<0.02). Conclusions: A slow contrast wash-out (small WOS) is expected in the presence of BBB impairment. WMH burdens are associated with BBB impairments manifested by decreased WOS. WOS is computationally less intense and demonstrates good repeatability. It may offer an alternative to model-based DCE in evaluating BBB dysfunction in patients with CSVD.

End-to-end volumetric segmentation of white matter hyperintensities using deep learning

Background and objectivesReliable detection of white matter hyperintensities (WMH) is crucial for studying the impact of diffuse white-matter pathology on brain health and monitoring changes in WMH load over time. However, manual annotation of 3D high-dimensional neuroimages is laborious and can be prone to biases and errors in the annotation procedure. In this study, we evaluate the performance of deep learning (DL) segmentation tools and propose a novel volumetric segmentation model incorporating self-attention via a transformer-based architecture. Ultimately, we aim to evaluate diverse factors that influence WMH segmentation, aiming for a comprehensive analysis of the state-of-the-art algorithms in a broader context. MethodsWe trained state-of-the-art DL algorithms, and incorporated advanced attention mechanisms, using structural fluid-attenuated inversion recovery (FLAIR) image acquisitions. The anatomical MRI data utilized for model training was obtained from healthy individuals aged 62–70 years in the Live active Successful Aging (LISA) project. Given the potential sparsity of lesion volume among healthy aging individuals, we explored the impact of incorporating a weighted loss function and ensemble models. To assess the generalizability of the studied DL models, we applied the trained algorithm to an independent subset of data sourced from the MICCAI WMH challenge (MWSC). Notably, this subset had vastly different acquisition parameters compared to the LISA dataset used for training. ResultsConsistently, DL approaches exhibited commendable segmentation performance, achieving the level of inter-rater agreement comparable to expert performance, ensuring superior quality segmentation outcomes. On the out of sample dataset, the ensemble models exhibited the most outstanding performance. ConclusionsDL methods generally surpassed conventional approaches in our study. While all DL methods performed comparably, incorporating attention mechanisms could prove advantageous in future applications with a wider availability of training data. As expected, our experiments indicate that the use of ensemble-based models enables the superior generalization in out-of-distribution settings. We believe that introducing DL methods in the WHM annotation workflow in heathy aging cohorts is promising, not only for reducing the annotation time required, but also for eventually improving accuracy and robustness via incorporating the automatic segmentations in the evaluation procedure.

2.5D transfer deep learning model for segmentation of contrast-enhancing lesions on brain magnetic resonance imaging of multiple sclerosis and neuromyelitis optica spectrum disorder.

Multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD) are the two mimic autoimmune diseases of the central nervous system, which are rare in East Asia. Quantitative detection of contrast-enhancing lesions (CELs) on contrast-enhancing T1-weighted magnetic resonance (MR) images is of great significance for assessing the disease activity of MS and NMOSD. However, it is challenging to develop automatic segmentation algorithms due to the lack of data. In this work, we present an automatic segmentation model of CELs based on Fully Convolutional with Attention DenseNet (FCA-DenseNet) and transfer learning strategy to address the challenge of CEL quantification in small-scale datasets. A transfer learning approach was employed in this study, whereby pretraining was conducted using 77 MS subjects from the open access datasets (MICCAI 2016, MICCAI 2017, ISBI 2015) for white matter hyperintensity segmentation, followed by fine-tuning using 24 MS and NMOSD subjects from the local dataset for CEL segmentation. The proposed FCA-DenseNet combined the Fully Convolutional DenseNet and Convolutional Block Attention Module in order to improve the learning capability. A 2.5D data slicing strategy was used to process complex 3D MR images. U-Net, ResUNet, TransUNet, and Attention-UNet are used as comparison models to FCA-DenseNet. Dice similarity coefficient (DSC), positive predictive value (PPV), true positive rate (TPR), and volume difference (VD) are used as evaluation metrics to evaluate the performances of different models. FCA-DenseNet outperforms all other models in terms of all evaluation metrics, with a DSC of 0.661±0.187, PPV of 0.719±0.201, TPR of 0.680±0.254, and VD of 0.388±0.334. Transfer learning strategy has achieved success in building segmentation models on a small-scale local dataset where traditional deep learning approaches fail to train effectively. The improved FCA-DenseNet, combined with transfer learning strategy and 2.5D data slicing strategy, has successfully addressed the challenges in constructing deep learning models on small-scale datasets, making it conducive to clinical quantification of brain CELs and diagnosis of MS and NMOSD.

Accuracy of TrUE-Net in comparison to established white matter hyperintensity segmentation methods: An independent validation study

White matter hyperintensities (WMH) are nearly ubiquitous in the aging brain, and their topography and overall burden are associated with cognitive decline. Given their numerosity, accurate methods to automatically segment WMH are needed. Recent developments, including the availability of challenge data sets and improved deep learning algorithms, have led to a new promising deep-learning based automated segmentation model called TrUE-Net, which has yet to undergo rigorous independent validation. Here, we compare TrUE-Net to six established automated WMH segmentation tools, including a semi-manual method. We evaluated the techniques at both global and regional level to compare their ability to detect the established relationship between WMH burden and age. We found that TrUE-Net was highly reliable at identifying WMH regions with low false positive rates, when compared to semi-manual segmentation as the reference standard. TrUE-Net performed similarly or favorably when compared to the other automated techniques. Moreover, TrUE-Net was able to detect relationships between WMH and age to a similar degree as the reference standard semi-manual segmentation at both the global and regional level. These results support the use of TrUE-Net for identifying WMH at the global or regional level, including in large, combined datasets.

Early detection of white matter hyperintensities using SHIVA-WMH detector.

White matter hyperintensities (WMHs) are well-established markers of cerebral small vessel disease, and are associated with an increased risk of stroke, dementia, and mortality. Although their prevalence increases with age, small and punctate WMHs have been reported with surprisingly high frequency even in young, neurologically asymptomatic adults. However, most automated methods to segment WMH published to date are not optimized for detecting small and sparse WMH. Here we present the SHIVA-WMH tool, a deep-learning (DL)-based automatic WMH segmentation tool that has been trained with manual segmentations of WMH in a wide range of WMH severity. We show that it is able to detect WMH with high efficiency in subjects with only small punctate WMH as well as in subjects with large WMHs (i.e., with confluency) in evaluation datasets from three distinct databases: magnetic resonance imaging-Share consisting of young university students, MICCAI 2017 WMH challenge dataset consisting of older patients from memory clinics, and UK Biobank with community-dwelling middle-aged and older adults. Across these three cohorts with a wide-ranging WMH load, our tool achieved voxel-level and individual lesion cluster-level Dice scores of 0.66 and 0.71, respectively, which were higher than for three reference tools tested: the lesion prediction algorithm implemented in the lesion segmentation toolbox (LPA: Schmidt), PGS tool, a DL-based algorithm and the current winner of the MICCAI 2017 WMH challenge (Park et al.), and HyperMapper tool (Mojiri Forooshani et al.), another DL-based method with high reported performance in subjects with mild WMH burden. Our tool is publicly and openly available to the research community to facilitate investigations of WMH across a wide range of severity in other cohorts, and to contribute to our understanding of the emergence and progression of WMH.

The Neuropathological Correlates of White Matter Hyperintensities in Cerebral Amyloid Angiopathy

AbstractBackgroundCerebral amyloid angiopathy (CAA) is a common cause of intracerebral hemorrhage and cognitive impairment in older individuals. Hallmark manifestations of CAA on MRI include cortical hemorrhages, as well as perivascular spaces (PVS) in the white matter centrum semiovale and white matter hyperintensities (WMH) in a subcortical multi‐spot pattern. We performed an ex vivo MRI‐neuropathological study to: 1) determine the relationship between WMH volume and CAA severity, and 2) assess the histopathological substrate of confluent WMH, WMH in a multi‐spot pattern (WM_MS), and normal‐appearing white matter (NAWM).MethodNineteen autopsy cases with pathologically confirmed CAA (age 75±8y; 7F) and five non‐CAA controls (age 88±5y; 3F) were included. Formalin‐fixed hemispheres underwent 3T MRI, including a T2‐weighted (500µm isotropic resolution, to obtain manual WMH segmentations) and a T2*‐weighted sequence (1mm isotropic resolution, to automatically segment hemisphere volume using SynthSeg). After scanning, five pre‐defined standard areas were sampled from each brain, then processed to obtain manually assessed arteriolosclerosis scores and AI‐derived cortical and leptomeningeal CAA area measurements. In the CAA cases, specific areas with ex vivo MRI‐observed WM_MS (n = 7), confluent WMH (n = 9), and NAWM (n = 9) were sampled. Sections were stained with LH&E (to determine WM rarefaction, % PVS area, and degree of arteriolosclerosis), and CD68 (a marker of activated microglia, to assess density of CD68‐positive cells).ResultTotal normalized WMH volume did not differ between CAA cases (0.037±0.024) and non‐CAA controls (0.027±0.026) (Mann‐Whitney U test 36, p = 0.31). Within the CAA cases, a multivariable regression model corrected for age at death revealed that normalized WMH volume was associated with cortical CAA area (p = 0.010) and arteriolosclerosis (p = 0.066), but not leptomeningeal CAA area (p = 0.94). Targeted neuropathological assessment revealed that WM rarefaction, arteriolosclerosis score, and density of CD68‐positive cells were higher in areas with WMH compared to WM_MS and NAWM. In contrast, % PVS area was higher in WM_MS compared to WMH and NAWM.ConclusionThe observed differences in neuropathological correlates between WMH in a multi‐spot pattern and confluent WMH in CAA suggest different pathophysiological mechanisms. Future studies are needed to determine these mechanisms as well as the causal relationship between cortical CAA severity and WMH burden.

Associations of white matter hyperintensities with cerebrovascular architecture in Alzheimer’s disease and related dementias

AbstractBackgroundMRI‐detected white matter hyperintensities (WMHs), a marker of cerebrovascular‐pathology, are common in Alzheimer’s disease (AD) and related dementias (ADRDs). In stroke, WMH‐volume was found to correlate most with stroke risk‐factors in the anterior cerebral arterial‐territory. Since the relationship between WMHs and arterial‐territories remains unexplored in the ADRDs, we systematically investigated WMHs’ spatial distribution (1) in 8 ADRDs relative to cognitively unimpaired (CU), and (2) across arterial‐territories per ADRD.MethodsThe extensive CCNA‐COMPASS‐ND cohort (N = 927) allowed us to investigate 9 clinical categories: CU, subjective (SCI) and mild (MCI) cognitive impairment, vascular MCI (V‐MCI), AD, vascular AD (V‐AD), Lewy‐body dementia (LBD), fronto‐temporal dementia (FTD), and Parkinson’s disease (PD) (Fig.1A). FLAIR and T1w MRI‐scans were used to segment WMHs (Dadar et al.,2017). Following registration to standard space, an arterial‐territory atlas (Schirmer et al.,2019) was used to calculate WMH‐volumes in 10 regions (Fig.1B). Statistical analyses were run on whole‐brain‐WMH‐volume and regional‐WMH‐ratios (region‐size‐normalized‐WMH‐volume/whole‐brain‐WMH‐volume). Data‐analyses used a series of linear models accounting for clinical category, age, and sex – followed by pairwise group‐comparisons corrected for multiple comparisons.Results 1) Relative to CU: Whole‐brain‐WMH‐volumes were higher for V‐MCI, V‐AD, and FTD. WMH‐ratios were higher in MCA and LMCA for 2 ADRDs (SCI;V‐MCI) and lower in PCA, LPCA, and RPCA for SCI. WMH‐ratios were higher in ACA or LACA and lower in PCA, LPCA, or RPCA for 4 ADRDs (V‐MCI;V‐AD;FTD;PD) (Fig.1C). Sex‐analyses: Men’s WMH‐volumes were higher in whole‐brain (CU;V‐MCI;FTD), while their WMH‐ratios were higherin LMCA (CU), but lower in ACA (SCI;MCI), LACA (MCI), and RACA (SCI). 2) MCA contained higher WMH‐ratios than ACA and PCA in all clinical categories. Relative to PCA, ACA’s WMH‐ratio was higher in 2 ADRDs (V‐MCI;V‐AD) and lower in 4 (CU;MCI;AD;PD). Pairwise‐group comparisons between all left/right arterial‐territories demonstrated consistent results (Fig.2). Asymmetry‐analyses: The right arterial side had higher WMH‐ratios in ACA (CU;V‐MCI), MCA (CU;SCI;MCI;V‐MCI;AD;V‐AD;PD), and PCA (MCI;AD).ConclusionWe identified arterial‐territories of increased susceptibility to WMH‐formation per ADRD. The two most prevalent ADRDs (AD;V‐AD) were found to accumulate WMHs in a territory‐specific manner – higher WMH‐ratios in ACA for V‐AD and PCA for AD. Overall, the arterial‐territory‐specific WMH‐signatures identified may improve ADRD‐diagnosis accuracy.

Automatic segmentation of white matter hyperintensities in T2-FLAIR with AQUA: A comparative validation study against conventional methods

White matter hyperintensities (WMHs) are lesions in the white matter of the brain that are associated with cognitive decline and an increased risk of dementia. The manual segmentation of WMHs is highly time-consuming and prone to intra- and inter-variability. Therefore, automatic segmentation approaches are gaining attention as a more efficient and objective means to detect and monitor WMHs. In this study, we propose AQUA, a deep learning model designed for fully automatic segmentation of WMHs from T2-FLAIR scans, which improves upon our previous study for small lesion detection and incorporating a multicenter approach. AQUA implements a two-dimensional U-Net architecture and uses patch-based training. Additionally, the network was modified to include Bottleneck Attention Module on each convolutional block of both the encoder and decoder to enhance performance for small-sized WMH. We evaluated the performance and robustness of AQUA by comparing it with five well-known supervised and unsupervised methods for automatic segmentation of WMHs (LGA, LPA, SLS, UBO, and BIANCA). To accomplish this, we tested these six methods on the MICCAI 2017 WMH Segmentation Challenge dataset, which contains MRI images from 170 elderly participants with WMHs of presumed vascular origin, and assessed their robustness across multiple sites and scanner types. The results showed that AQUA achieved superior performance in terms of spatial (Dice = 0.72) and volumetric (logAVD = 0.10) agreement with the manual segmentation compared to the other methods. While the recall and F1-score were moderate at 0.49 and 0.59, respectively, they improved to 0.75 and 0.82 when excluding small lesions (≤ 6 voxels). Remarkably, despite being trained on a different dataset with different ethnic backgrounds, lesion loads, and scanners, AQUA's results were comparable to the top 10 ranked methods of the MICCAI challenge. The findings suggest that AQUA is effective and practical for automatic segmentation of WMHs from T2-FLAIR scans, which could help identify individuals at risk of cognitive decline and dementia and allow for early intervention and management.

White matter hyperintensity longitudinal morphometric analysis in association with Alzheimer disease.

Vascular damage in Alzheimer's disease (AD) has shown conflicting findings particularly when analyzing longitudinal data. We introduce white matter hyperintensity (WMH) longitudinal morphometric analysis (WLMA) that quantifies WMH expansion as the distance from lesion voxels to a region of interest boundary. WMH segmentation maps were derived from 270 longitudinal fluid-attenuated inversion recovery (FLAIR) ADNI images. WLMA was performed on five data-driven WMH patterns with distinct spatial distributions. Amyloid accumulation was evaluated with WMH expansion across the five WMH patterns. The preclinical group had significantly greater expansion in the posterior ventricular WM compared to controls. Amyloid significantly associated with frontal WMH expansion primarily within AD individuals. WLMA outperformed WMH volume changes for classifying AD from controls primarily in periventricular and posterior WMH. These data support the concept that localized WMH expansion continues to proliferate with amyloid accumulation throughout the entirety of the disease in distinct spatial locations.

Segmenting white matter hyperintensities in brain magnetic resonance images using convolution neural networks

White matter hyperintensities (WMHs) are found on magnetic resonance (MR) images of older individuals and are associated with many neurodegenerative disorders, although the exactrole of WMHs in Alzheimer’s disease and other dementias remains an open area of research. Fluid-attenuated inversion recovery (FLAIR) MR imaging sequences show WMHs with good image contrast. Manual segmentation of WMHs on FLAIR images is the widely accepted “gold standard”, however, this step is often time-consuming and has a high inter-rater variability. The absence of an automated, robust and accurate approach to segment WMHs remains a processing bottleneck. We explored convolutional neural networks (CNNs) for performing semantic segmentation of WMHs in FLAIR images. Two sets of experiments were conducted: (1) Variations of U-shaped CNNs (U-Nets) were evaluated in 186 individuals, specifically, four architectures (VGG16, VGG19, ResNet152 and EfficientNetB0) having three dimensionalities (2D, 2.5D and 3D). (2) New data from 60 individuals were added to test the generalizability of U-Net, LinkNet and Feature-Pyramid Network (FPN) variants. The first experiment showed that the 2.5D implementation with VGG16 or VGG19 was the most suitable configuration when segmenting WMH (F-measure > 95% and intersection-over-union > 90%). The second experiment confirmed generalizability of these variants when using unprocessed FLAIR images.

Automatic segmentation of white matter hyperintensities and correlation analysis for cerebral small vessel disease.

Cerebral white matter hyperintensity can lead to cerebral small vessel disease, MRI images in the brain are used to assess the degree of pathological changes in white matter regions. In this paper, we propose a framework for automatic 3D segmentation of brain white matter hyperintensity based on MRI images to address the problems of low accuracy and segmentation inhomogeneity in 3D segmentation. We explored correlation analyses of cognitive assessment parameters and multiple comparison analyses to investigate differences in brain white matter hyperintensity volume among three cognitive states, Dementia, MCI and NCI. The study explored the correlation between cognitive assessment coefficients and brain white matter hyperintensity volume. This paper proposes an automatic 3D segmentation framework for white matter hyperintensity using a deep multi-mapping encoder-decoder structure. The method introduces a 3D residual mapping structure for the encoder and decoder. Multi-layer Cross-connected Residual Mapping Module (MCRCM) is proposed in the encoding stage to enhance the expressiveness of model and perception of detailed features. Spatial Attention Weighted Enhanced Supervision Module (SAWESM) is proposed in the decoding stage to adjust the supervision strategy through a spatial attention weighting mechanism. This helps guide the decoder to perform feature reconstruction and detail recovery more effectively. Experimental data was obtained from a privately owned independent brain white matter dataset. The results of the automatic 3D segmentation framework showed a higher segmentation accuracy compared to nnunet and nnunet-resnet, with a p-value of <0.001 for the two cognitive assessment parameters MMSE and MoCA. This indicates that larger brain white matter are associated with lower scores of MMSE and MoCA, which in turn indicates poorer cognitive function. The order of volume size of white matter hyperintensity in the three groups of cognitive states is dementia, MCI and NCI, respectively. The paper proposes an automatic 3D segmentation framework for brain white matter that achieves high-precision segmentation. The experimental results show that larger volumes of segmented regions have a negative correlation with lower scoring coefficients of MMSE and MoCA. This correlation analysis provides promising treatment prospects for the treatment of cerebral small vessel diseases in the brain through 3D segmentation analysis of brain white matter. The differences in the volume of white matter hyperintensity regions in subjects with three different cognitive states can help to better understand the mechanism of cognitive decline in clinical research.

ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI

Deep artificial neural networks (DNNs) have moved to the forefront of medical image analysis due to their success in classification, segmentation, and detection challenges. A principal challenge in large-scale deployment of DNNs in neuroimage analysis is the potential for shifts in signal-to-noise ratio, contrast, resolution, and presence of artifacts from site to site due to variances in scanners and acquisition protocols. DNNs are famously susceptible to these distribution shifts in computer vision. Currently, there are no benchmarking platforms or frameworks to assess the robustness of new and existing models to specific distribution shifts in MRI, and accessible multi-site benchmarking datasets are still scarce or task-specific. To address these limitations, we propose ROOD-MRI: a novel platform for benchmarking the Robustness of DNNs to Out-Of-Distribution (OOD) data, corruptions, and artifacts in MRI. This flexible platform provides modules for generating benchmarking datasets using transforms that model distribution shifts in MRI, implementations of newly derived benchmarking metrics for image segmentation, and examples for using the methodology with new models and tasks. We apply our methodology to hippocampus, ventricle, and white matter hyperintensity segmentation in several large studies, providing the hippocampus dataset as a publicly available benchmark. By evaluating modern DNNs on these datasets, we demonstrate that they are highly susceptible to distribution shifts and corruptions in MRI. We show that while data augmentation strategies can substantially improve robustness to OOD data for anatomical segmentation tasks, modern DNNs using augmentation still lack robustness in more challenging lesion-based segmentation tasks. We finally benchmark U-Nets and vision transformers, finding robustness susceptibility to particular classes of transforms across architectures. The presented open-source platform enables generating new benchmarking datasets and comparing across models to study model design that results in improved robustness to OOD data and corruptions in MRI.

Association between periodontal disease and microstructural brain alterations in the Hamburg City Health Study.

The aim of the PAROBRAIN study was to examine the association of periodontal health with microstructural white matter integrity and cerebral small vessel disease (CSVD) in the Hamburg City Health Study, a large population-based cohort with dental examination and brain magnetic resonance imaging (MRI). Periodontal health was determined by measuring clinical attachment loss (CAL) and plaque index. Additionally, the decayed/missing/filled teeth (DMFT) index was quantified. 3D-FLAIR and 3D-T1-weighted images were used for white matter hyperintensity (WMH) segmentation. Diffusion-weighted MRI was used to quantify peak width of skeletonized mean diffusivity (PSMD). Data from 2030 participants were included in the analysis. Median age was 65 years, with 43% female participants. After adjusting for age and sex, an increase in WMH load was significantly associated with more CAL, higher plaque index and higher DMFT index. PSMD was significantly associated with the plaque index and DMFT. Additional adjustment for education and cardiovascular risk factors revealed a significant association of PSMD with plaque index (p < .001) and DMFT (p < .01), whereas effects of WMH load were attenuated (p > .05). These findings suggest an adverse effect of periodontal health on CSVD and white matter integrity. Further research is necessary to examine whether early treatment of periodontal disease can prevent microstructural brain damage.

YKL-40 as a novel biomarker related to white matter damage and cognitive impairment in patients with cerebral small vessel disease.

YKL-40 is a novel neuroinflammatory marker associated with white matter damage and cognitive dysfunction. 110 CSVD patients, including 54 with mild cognitive impairment (CSVD-MCI), 56 with no cognitive impairment (CSVD-NCI), and 40 healthy controls (HCs) underwent multimodal magnetic resonance examination, serum YKL-40 level detection and cognitive function assessment to investigate the association between YKL-40 and white matter damage and cognitive impairment in cerebral small vessel disease (CSVD) patients. White matter hyperintensities volume was calculated using the Wisconsin White Matter Hyperintensity Segmentation Toolbox (W2MHS) for white matter macrostructural damage evaluation. For white matter microstructural damage evaluation, fractional anisotropy (FA) and mean diffusivity (MD) indices of the region of interest were analyzed based on diffusion tensor imaging (DTI) images using the Tract-Based Spatial Statistics (TBSS) pipeline. The serum YKL-40 level of CSVD was significantly higher than those of HCs, and the CSVD-MCI was higher than in HCs and CSVD-NCI. Furthermore, serum YKL-40 provided high diagnostic accuracy for CSVD and CSVD-MCI. The macroscopic and microstructure of white matter in CSVD-NCI and CSVD-MCI patients indicated different degrees of damage. Disruption of white matter macroscopic and microstructure was significantly associated with YKL-40 levels and cognition deficits. Moreover, the white matter damage mediated the associations between the increased serum YKL-40 levels and cognitive impairment. Our findings demonstrated that YKL-40 might be a potential biomarker of white matter damage in CSVD, whereas white matter damage was associated with cognitive impairment. Serum YKL-40 measurement provides complementary information regarding the neural mechanism of CSVD and its associated cognitive impairment.

Optimizing automated white matter hyperintensity segmentation in individuals with stroke.

White matter hyperintensities (WMHs) are a risk factor for stroke. Consequently, many individuals who suffer a stroke have comorbid WMHs. The impact of WMHs on stroke recovery is an active area of research. Automated WMH segmentation methods are often employed as they require minimal user input and reduce risk of rater bias; however, these automated methods have not been specifically validated for use in individuals with stroke. Here, we present methodological validation of automated WMH segmentation methods in individuals with stroke. We first optimized parameters for FSL's publicly available WMH segmentation software BIANCA in two independent (multi-site) datasets. Our optimized BIANCA protocol achieved good performance within each independent dataset, when the BIANCA model was trained and tested in the same dataset or trained on mixed-sample data. BIANCA segmentation failed when generalizing a trained model to a new testing dataset. We therefore contrasted BIANCA's performance with SAMSEG, an unsupervised WMH segmentation tool available through FreeSurfer. SAMSEG does not require prior WMH masks for model training and was more robust to handling multi-site data. However, SAMSEG performance was slightly lower than BIANCA when data from a single site were tested. This manuscript will serve as a guide for the development and utilization of WMH analysis pipelines for individuals with stroke.

Performance evaluation of automated white matter hyperintensity segmentation algorithms in a multicenter cohort on cognitive impairment and dementia.

White matter hyperintensities (WMH), a biomarker of small vessel disease, are often found in Alzheimer's disease (AD) and their advanced detection and quantification can be beneficial for research and clinical applications. To investigate WMH in large-scale multicenter studies on cognitive impairment and AD, appropriate automated WMH segmentation algorithms are required. This study aimed to compare the performance of segmentation tools and provide information on their application in multicenter research. We used a pseudo-randomly selected dataset (n = 50) from the DZNE-multicenter observational Longitudinal Cognitive Impairment and Dementia Study (DELCODE) that included 3D fluid-attenuated inversion recovery (FLAIR) images from participants across the cognitive continuum. Performances of top-rated algorithms for automated WMH segmentation [Brain Intensity Abnormality Classification Algorithm (BIANCA), lesion segmentation toolbox (LST), lesion growth algorithm (LGA), LST lesion prediction algorithm (LPA), pgs, and sysu_media] were compared to manual reference segmentation (RS). Across tools, segmentation performance was moderate for global WMH volume and number of detected lesions. After retraining on a DELCODE subset, the deep learning algorithm sysu_media showed the highest performances with an average Dice's coefficient of 0.702 (±0.109 SD) for volume and a mean F1-score of 0.642 (±0.109 SD) for the number of lesions. The intra-class correlation was excellent for all algorithms (>0.9) but BIANCA (0.835). Performance improved with high WMH burden and varied across brain regions. To conclude, the deep learning algorithm, when retrained, performed well in the multicenter context. Nevertheless, the performance was close to traditional methods. We provide methodological recommendations for future studies using automated WMH segmentation to quantify and assess WMH along the continuum of cognitive impairment and AD dementia.

Spatial distributions of white matter hyperintensities on brain MRI: A pooled analysis of individual participant data from 11 memory clinic cohorts

IntroductionThe spatial distribution of white matter hyperintensities (WMH) on MRI is often considered in the diagnostic evaluation of patients with cognitive problems. In some patients, clinicians may classify WMH patterns as “unusual”, but this is largely based on expert opinion, because detailed quantitative information about WMH distribution frequencies in a memory clinic setting is lacking. Here we report voxel wise 3D WMH distribution frequencies in a large multicenter dataset and also aimed to identify individuals with unusual WMH patterns. MethodsIndividual participant data (N = 3525, including 777 participants with subjective cognitive decline, 1389 participants with mild cognitive impairment and 1359 patients with dementia) from eleven memory clinic cohorts, recruited through the Meta VCI Map Consortium, were used. WMH segmentations were provided by participating centers or performed in Utrecht and registered to the Montreal Neurological Institute (MNI)-152 brain template for spatial normalization. To determine WMH distribution frequencies, we calculated WMH probability maps at voxel level. To identify individuals with unusual WMH patterns, region-of-interest (ROI) based WMH probability maps, rule-based scores, and a machine learning method (Local Outlier Factor (LOF)), were implemented. ResultsWMH occurred in 82% of voxels from the white matter template with large variation between subjects. Only a small proportion of the white matter (1.7%), mainly in the periventricular areas, was affected by WMH in at least 20% of participants. A large portion of the total white matter was affected infrequently. Nevertheless, 93.8% of individual participants had lesions in voxels that were affected in less than 2% of the population, mainly located in subcortical areas. Only the machine learning method effectively identified individuals with unusual patterns, in particular subjects with asymmetric WMH distribution or with WMH at relatively rarely affected locations despite common locations not being affected. DiscussionAggregating data from several memory clinic cohorts, we provide a detailed 3D map of WMH lesion distribution frequencies, that informs on common as well as rare localizations. The use of data-driven analysis with LOF can be used to identify unusual patterns, which might serve as an alert that rare causes of WMH should be considered.

A Nested Attention Guided UNet++ Architecture for White Matter Hyperintensity Segmentation

White Matter Hyperintensity (WMH) is a common finding in Magnetic Resonance Imaging (MRI) of patients with cerebral infarction and is associated with poor prognosis. Accurate and rapid segmentation of WMH lesions is critical for clinicians to assess the risk of rebleeding and the long-term prognosis of thrombolytic patients. However, segmentation can be challenging due to the erratic signals of WMH in MRI, leading to imprecise results. Deep learning-based approaches have been proposed, but the dice similarity coefficient remains low. Atlas images are navigation maps that integrate various medical information expressions. In this study, we propose a nested attention-guided UNet++ framework that employs attention mechanisms to capture local and global features of WMH lesions using atlas images for segmentation. The framework consists of two modules, the atlas attention module, and the nested attention-guided nested U-Net module. The atlas attention module generates the atlas attention map, which is used as the input for the nested attention-guided nested U-Net module that generates the segmentation map of the FLAIR image. Experimental results demonstrate that the proposed NAUNet++ framework converges faster than conventional UNet and UNet++ approaches. Moreover, the nested architecture enhances recall and f1 scores of the segmentation results compared to the attention-guided approach.

Tract-based white matter hyperintensity patterns in patients with systemic lupus erythematosus using an unsupervised machine learning approach.

Currently, little is known about the spatial distribution of white matter hyperintensities (WMH) in the brain of patients with Systemic Lupus erythematosus (SLE). Previous lesion markers, such as number and volume, ignore the strategic location of WMH. The goal of this work was to develop a fully-automated method to identify predominant patterns of WMH across WM tracts based on cluster analysis. A total of 221 SLE patients with and without neuropsychiatric symptoms from two different sites were included in this study. WMH segmentations and lesion locations were acquired automatically. Cluster analysis was performed on the WMH distribution in 20 WM tracts. Our pipeline identified five distinct clusters with predominant involvement of the forceps major, forceps minor, as well as right and left anterior thalamic radiations and the right inferior fronto-occipital fasciculus. The patterns of the affected WM tracts were consistent over the SLE subtypes and sites. Our approach revealed distinct and robust tract-based WMH patterns within SLE patients. This method could provide a basis, to link the location of WMH with clinical symptoms. Furthermore, it could be used for other diseases characterized by presence of WMH to investigate both the clinical relevance of WMH and underlying pathomechanism in the brain.