Performance of three freely available methods for extracting white matter hyperintensities: FreeSurfer, UBO Detector, and BIANCA

Decoding the best automated segmentation tools for vascular white matter hyperintensities in the aging brain: a clinician's guide to precision and purpose

White matter hyperintensities of vascular origin (WMH) are commonly found in individuals over 60 and increase in prevalence with age. The significance of WMH is well-documented, with strong associations with cognitive impairment, risk of stroke, mental health, and brain structure deterioration. Consequently, careful monitoring is crucial for the early identification and management of individuals at risk. Luckily, WMH are detectable and quantifiable on standard MRI through visual assessment scales, but it is time-consuming and has high rater variability. Addressing this issue, the main aim of our study is to decipher the utility of quantitative measures of WMH, assessed with automatic tools, in establishing risk profiles for cerebrovascular deterioration. For this purpose, first, we work to determine the most precise WMH segmentation open access tool compared to clinician manual segmentations (LST-LPA, LST-LGA, SAMSEG, and BIANCA), offering insights into methodology and usability to balance clinical precision with practical application. The results indicated that supervised algorithms (LST-LPA and BIANCA) were superior, particularly in detecting small WMH, and can improve their consistency when used in parallel with unsupervised tools (LST-LGA and SAMSEG). Additionally, to investigate the behavior and real clinical utility of these tools, we tested them in a real-world scenario (N = 300; age > 50 y.o. and MMSE > 26), proposing an imaging biomarker for moderate vascular damage. The results confirmed its capacity to effectively identify individuals at risk comparing the cognitive and brain structural profiles of cognitively healthy adults above and below the resulted threshold.

Decoding the Best Automated Segmentation Tools for Vascular White Matter Hyperintensities in the Aging Brain: A Clinician's Guide to Precision and Purpose

Cerebrovascular damage from small vessel disease (SVD) occurs in healthy and pathological aging. SVD markers, such as white matter hyperintensities (WMH), are commonly found in individuals over 60 and increase in prevalence with age. WMHs are detectable on standard MRI by adhering to the STRIVE criteria. Currently, visual assessment scales are used in clinical and research scenarios but is time-consuming and has rater variability, limiting its practicality. Addressing this issue, our study aimed to determine the most precise WMH segmentation software, offering insights into methodology and usability to balance clinical precision with practical application. This study employed a dataset comprising T1, FLAIR, and DWI images from 300 cognitively healthy older adults. WMHs in this cohort were evaluated using four automated neuroimaging tools: Lesion Prediction Algorithm (LPA) and Lesion Growth Algorithm (LGA) from Lesion Segmentation Tool (LST), Sequence Adaptive Multimodal Segmentation (SAMSEG), and Brain Intensity Abnormalities Classification Algorithm (BIANCA). Additionally, clinicians manually segmented WMHs in a subsample of 45 participants to establish a gold standard. The study assessed correlations with the Fazekas scale, algorithm performance, and the influence of WMH volume on reliability. Results indicated that supervised algorithms were superior, particularly in detecting small WMHs, and can improve their consistency when used in parallel with unsupervised tools. The research also proposed a biomarker for moderate vascular damage, derived from the top 95th percentile of WMH volume in healthy individuals aged 50 to 60. This biomarker effectively differentiated subgroups within the cohort, correlating with variations in brain structure and behavior.

The association between glymphatic system dysfunction and alterations in cerebral function and structure in patients with white matter hyperintensities

The objective of this study is to explore the relationship between the glymphatic system and alterations in the structure and function of the brain in white matter hyperintensity (WMH) patients. MRI data were collected from 27 WMH patients and 23 healthy controls. We calculated the along perivascular space (ALPS) indices, the anterior corner distance of the lateral ventricle, and the width of the third ventricle for each subject. The DPABISurf tool was used to calculate the cortical thickness and cortical area. In addition, data processing assistant for resting-state fMRI was used to calculate regional homogeneity, degree centrality, amplitude low-frequency fluctuation (ALFF), fractional amplitude of low-frequency fluctuation (fALFF), and voxel-mirrored homotopic connectivity (VMHC). In addition, each WMH patient was evaluated on the Fazekas scale. Finally, the correlation analysis of structural indicators and functional indicators with bilateral ALPS indices was investigated using Spearman correlation analysis. The ALPS indices of WMH patients were lower than those of healthy controls (left: t = -4.949, P < 0.001; right: t = -3.840, P < 0.001). This study found that ALFF, fALFF, regional homogeneity, degree centrality, and VMHC values in some brain regions of WMH patients were alternated (AlphaSim corrected, P < 0.005, cluster size > 26 voxel, rmm value = 5), and the cortical thickness and cortical area of WMH patients showed trend changes (P < 0.01, cluster size > 20 mm2, uncorrected). Interestingly, we found significantly positive correlations between the left ALPS indices and degree centrality values in the superior temporal gyrus (r = 0.494, P = 0.009, P × 5 < 0.05, Bonferroni correction). Our results suggest that glymphatic system impairment is related to the functional centrality of local connections in patients with WMH. This provides a new perspective for understanding the pathological mechanisms of cognitive impairment in the WMH population.

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

BACKGROUND AND OBJECTIVES

Reliable 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.

METHODS

We 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.

RESULTS

Consistently, 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.

CONCLUSIONS

DL 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.

Cerebral arterial stiffness is linked to white matter hyperintensities and perivascular spaces in older adults - A 4D flow MRI study

White matter hyperintensities (WMH), perivascular spaces (PVS) and lacunes are common MRI features of small vessel disease (SVD). However, no shared underlying pathological mechanism has been identified. We investigated whether SVD burden, in terms of WMH, PVS and lacune status, was related to changes in the cerebral arterial wall by applying global cerebral pulse wave velocity (gcPWV) measurements, a newly described marker of cerebral vascular stiffness. In a population-based cohort of 190 individuals, 66-85 years old, SVD features were estimated from T1-weighted and FLAIR images while gcPWV was estimated from 4D flow MRI data. Additionally, the gcPWV's stability to variations in field-of-view was analyzed. The gcPWV was 10.82 (3.94) m/s and displayed a significant correlation to WMH and white matter PVS volume (r = 0.29, p < 0.001; r = 0.21, p = 0.004 respectively from nonparametric tests) that persisted after adjusting for age, blood pressure variables, body mass index, ApoB/A1 ratio, smoking as well as cerebral pulsatility index, a previously suggested early marker of SVD. The gcPWV displayed satisfactory stability to field-of-view variations. Our results suggest that SVD is accompanied by changes in the cerebral arterial wall that can be captured by considering the velocity of the pulse wave transmission through the cerebral arterial network.

Associations between white matter hyperintensities, lacunes, entorhinal cortex thickness, declarative memory and leisure activity in cognitively healthy older adults: A 7-year study

INTRODUCTION

Cerebral small vessel disease (cSVD) is a growing epidemic that affects brain health and cognition. Therefore, a more profound understanding of the interplay between cSVD, brain atrophy, and cognition in healthy aging is of great importance. In this study, we examined the association between white matter hyperintensities (WMH) volume, number of lacunes, entorhinal cortex (EC) thickness, and declarative memory in cognitively healthy older adults over a seven-year period, controlling for possible confounding factors. Because there is no cure for cSVD to date, the neuroprotective potential of an active lifestyle has been suggested. Supporting evidence, however, is scarce. Therefore, a second objective of this study is to examine the relationship between leisure activities, cSVD, EC thickness, and declarative memory.

METHODS

We used a longitudinal dataset, which consisted of five measurement time points of structural MRI and psychometric cognitive ability and survey data, collected from a sample of healthy older adults (baseline N = 231, age range: 64-87 years, age M = 70.8 years), to investigate associations between cSVD MRI markers, EC thickness and verbal and figural memory performance. Further, we computed physical, social, and cognitive leisure activity scores from survey-based assessments and examined their associations with brain structure and declarative memory. To provide more accurate estimates of the trajectories and cross-domain correlations, we applied latent growth curve models controlling for potential confounders.

RESULTS

Less age-related thinning of the right (β = 0.92, p<.05) and left EC (β = 0.82, p<.05) was related to less declarative memory decline; and a thicker EC at baseline predicted less declarative memory loss (β = 0.54, p<.05). Higher baseline levels of physical (β = 0.24, p<.05), and social leisure activity (β = 0.27, p<.01) predicted less thinning of right EC. No relation was found between WMH or lacunes and declarative memory or between leisure activity and declarative memory. Higher education was initially related to more physical activity (β = 0.16, p<.05) and better declarative memory (β = 0.23, p<.001), which, however, declined steeper in participants with higher education (β = -.35, p<.05). Obese participants were less physically (β = -.18, p<.01) and socially active (β = -.13, p<.05) and had thinner left EC (β = -.14, p<.05) at baseline. Antihypertensive medication use (β = -.26, p<.05), and light-to-moderate alcohol consumption (β = -.40, p<.001) were associated with a smaller increase in the number of lacunes whereas a larger increase in the number of lacunes was observed in current smokers (β = 0.30, p<.05).

CONCLUSIONS

Our results suggest complex relationships between cSVD MRI markers (total WMH, number of lacunes, right and left EC thickness), declarative memory, and confounding factors such as antihypertensive medication, obesity, and leisure activitiy. Thus, leisure activities and having good cognitive reserve counteracting this neurodegeneration. Several confounding factors seem to contribute to the extent or progression/decline of cSVD, which needs further investigation in the future. Since there is still no cure for cSVD, modifiable confounding factors should be studied more intensively in the future to maintain or promote brain health and thus cognitive abilities in older adults.

Using a semi-automated approach to quantify Unidentified Bright Objects in Neurofibromatosis type 1 and linkages to cognitive and academic outcomes

Neurofibromatosis type 1 (NF1) is an autosomal dominant neurocutaneous syndrome that affects multiple organ systems resulting in widespread symptoms, including cognitive deficits. In addition to the criteria required for an NF1 diagnosis, approximately 70% of children with NF1 present with Unidentified Bright Objects (UBOs) or Focal Areas of Signal Intensity, which are hyperintense bright spots seen on T2-weighted magnetic resonance images and seen more prominently on FLAIR magnetic resonance images (Sabol et al., 2011). Current findings relating the presence/absence, quantities, sizes, and locations of these bright spots to cognitive abilities are mixed. To contribute to and hopefully disentangle some of these mixed findings, we explored potential relationships between metrics related to UBOs and cognitive abilities in a sample of 28 children and adolescents with NF1 (M=12.52 years; SD=3.18 years; 16 male). We used the Lesion Segmentation Tool (LST) to automatically detect and segment the UBOs. The LST was able to qualitatively and quantitatively reliably detect UBOs in images of children with NF1. Using these automatically detected and segmented lesions, we found that while controlling for age, biological sex, perceptual IQ, study, and scanner, "total UBO volume", defined as the sum of all the voxels representing all of the UBOs for each participant, helped explain differences in word reading, phonological awareness, and visuospatial skills. These findings contribute to the emerging NF1 literature and help parse the specific deficits that children with NF1 have, to then help improve the efficacy of reading interventions for children with NF1.

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.

Higher-resolution quantification of white matter hypointensities by large-scale transfer learning from 2D images on the JPSC-AD cohort

White matter lesions (WML) commonly occur in older brains and are quantifiable on MRI, often used as a biomarker in Aging research. Although algorithms are regularly proposed that identify these lesions from T2‐fluid‐attenuated inversion recovery (FLAIR) sequences, none so far can estimate lesions directly from T1‐weighted images with acceptable accuracy. Since 3D T1 is a polyvalent and higher‐resolution sequence, it could be beneficial to obtain the distribution of WML directly from it. However a serious difficulty, both for algorithms and human, can be found in the ambiguities of brain signal intensity in T1 images. This manuscript shows that a cross‐domain ConvNet (Convolutional Neural Network) approach can help solve this problem. Still, this is non‐trivial, as it would appear to require a large and varied dataset (for robustness) labelled at the same high resolution (for spatial accuracy). Instead, our model was taught from two‐dimensional FLAIR images with a loss function designed to handle the super‐resolution need. And crucially, we leveraged a very large training set for this task, the recently assembled, multi‐sites Japan Prospective Studies Collaboration for Aging and Dementia (JPSC‐AD) cohort. We describe the two‐step procedure that we followed to handle such a large number of imperfectly labeled samples. A large‐scale accuracy evaluation conducted against FreeSurfer 7, and a further visual expert rating revealed that WML segmentation from our ConvNet was consistently better. Finally, we made a directly usable software program based on that trained ConvNet model, available at https://github.com/bthyreau/deep-T1-WMH.