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

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.

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.

More Similar than Different: Memory, Executive Functions, Cortical Thickness, and Glucose Metabolism in Biomarker-Positive Alzheimer's Disease and Behavioral Variant Frontotemporal Dementia

Background

Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD) are typically associated with very different clinical and neuroanatomical presentations; however, there is increasing recognition of similarities.

Objective

To examine memory and executive functions, as well as cortical thickness, and glucose metabolism in AD and bvFTD signature brain regions.

Methods

We compared differences in a group of biomarker-defined participants with Alzheimer's disease and a group of clinically diagnosed participants with bvFTD. These groups were also contrasted with healthy controls (HC).

Results

As expected, memory functions were generally more impaired in AD, followed by bvFTD, and both clinical groups performed more poorly than the HC group. Executive function measures were similar in AD compared to bvFTD for motor sequencing and go/no-go, but bvFTD had more difficulty with a set shifting task. Participants with AD showed thinner cortex and lower glucose metabolism in the angular gyrus compared to bvFTD. Participants with bvFTD had thinner cortex in the insula and temporal pole relative to AD and healthy controls, but otherwise the two clinical groups were similar for other frontal and temporal signature regions.

Conclusions

Overall, the results of this study highlight more similarities than differences between AD and bvFTD in terms of cognitive functions, cortical thickness, and glucose metabolism. Further research is needed to better understand the mechanisms mediating this overlap and how these relationships evolve longitudinally.

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.

BIANCA-MS: An optimized tool for automated multiple sclerosis lesion segmentation

In this work we present BIANCA-MS, a novel tool for brain white matter lesion segmentation in multiple sclerosis (MS), able to generalize across both the wide spectrum of MRI acquisition protocols and the heterogeneity of manually labeled data. BIANCA-MS is based on the original version of BIANCA and implements two innovative elements: a harmonized setting, tested under different MRI protocols, which avoids the need to further tune algorithm parameters to each dataset; and a cleaning step developed to improve consistency in automated and manual segmentations, thus reducing unwanted variability in output segmentations and validation data. BIANCA-MS was tested on three datasets, acquired with different MRI protocols. First, we compared BIANCA-MS to other widely used tools. Second, we tested how BIANCA-MS performs in separate datasets. Finally, we evaluated BIANCA-MS performance on a pooled dataset where all MRI data were merged. We calculated the overlap using the DICE spatial similarity index (SI) as well as the number of false positive/negative clusters (nFPC/nFNC) in comparison to the manual masks processed with the cleaning step. BIANCA-MS clearly outperformed other available tools in both high- and low-resolution images and provided comparable performance across different scanning protocols, sets of modalities and image resolutions. BIANCA-MS performance on the pooled dataset (SI: 0.72 ± 0.25, nFPC: 13 ± 11, nFNC: 4 ± 8) were comparable to those achieved on each individual dataset (median across datasets SI: 0.72 ± 0.28, nFPC: 14 ± 11, nFNC: 4 ± 8). Our findings suggest that BIANCA-MS is a robust and accurate approach for automated MS lesion segmentation.

Frontal and temporal lobe correlates of verbal learning and memory in aMCI and suspected Alzheimer's disease dementia

Alzheimer's disease is primarily known for deficits in learning and retaining new information. This has long been associated with pathological changes in the mesial temporal lobes. The role of the frontal lobes in memory in Alzheimer's disease is less well understood. In this study, we examined the role of the frontal lobes in learning, recognition, and retention of new verbal information, as well as the presence of specific errors (i.e., intrusions and false-positive errors). Participants included one hundred sixty-seven patients clinically diagnosed with amnestic mild cognitive impairment or suspected Alzheimer's disease dementia who were administered the California Verbal Learning Test and completed high-resolution MRI. We confirmed the role of the mesial temporal lobes in learning and retention, including the volumes of the hippocampus, entorhinal cortex, and parahippocampal gyrus. In addition, false-positive errors were associated with all volumes of the mesial temporal lobes and widespread areas within the frontal lobes. Errors of intrusion were related to the supplementary motor cortex and hippocampus. Most importantly, the mesial temporal lobes interacted with the frontal lobes for learning, recognition, and memory errors. Lower volumes in both regions explained more performance variance than any single structure. This study supports the interaction of the frontal lobes with the temporal lobes in many aspects of memory in Alzheimer's disease.

Toward Automated Detection of Silent Cerebral Infarcts in Children and Young Adults With Sickle Cell Anemia

BACKGROUND

Silent cerebral infarcts (SCI) in sickle cell anemia (SCA) are associated with future strokes and cognitive impairment, warranting early diagnosis and treatment. Detection of SCI, however, is limited by their small size, especially when neuroradiologists are unavailable. We hypothesized that deep learning may permit automated SCI detection in children and young adults with SCA as a tool to identify the presence and extent of SCI in clinical and research settings.

METHODS

We utilized UNet-a deep learning model-for fully automated SCI segmentation. We trained and optimized UNet using brain magnetic resonance imaging from the SIT trial (Silent Infarct Transfusion). Neuroradiologists provided the ground truth for SCI diagnosis, while a vascular neurologist manually delineated SCI on fluid-attenuated inversion recovery and provided the ground truth for SCI segmentation. UNet was optimized for the highest spatial overlap between automatic and manual delineation (dice similarity coefficient). The optimized UNet was externally validated using an independent single-center prospective cohort of SCA participants. Model performance was evaluated through sensitivity and accuracy (%correct cases) for SCI diagnosis, dice similarity coefficient, intraclass correlation coefficient (metric of volumetric agreement), and Spearman correlation.

RESULTS

The SIT trial (n=926; 31% with SCI; median age, 8.9 years) and external validation (n=80; 50% with SCI; age, 11.5 years) cohorts had small median lesion volumes of 0.40 and 0.25 mL, respectively. Compared with the neuroradiology diagnosis, UNet predicted SCI presence with 100% sensitivity and 74% accuracy. In magnetic resonance imaging with SCI, UNet reached a moderate spatial agreement (dice similarity coefficient, 0.48) and high volumetric agreement (intraclass correlation coefficient, 0.76; ρ=0.72; P<0.001) between automatic and manual segmentations.

CONCLUSIONS

UNet, trained using a large pediatric SCA magnetic resonance imaging data set, sensitively detected small SCI in children and young adults with SCA. While additional training is needed, UNet may be integrated into the clinical workflow as a screening tool, aiding in SCI diagnosis.

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.

Mediterranean diet and structural neuroimaging biomarkers of Alzheimer's and cerebrovascular disease: A systematic review

Previous studies have demonstrated an association between adherence to the Mediterranean diet (MedDiet) and better cognitive performance, lower incidence of dementia and lower Alzheimer's disease biomarker burden. The aim of this systematic review was to evaluate the evidence base for MedDiet associations with hippocampal volume and white matter hyperintensity volume (WMHV). We searched systematically for studies reporting on MedDiet and hippocampal volume or WMHV in MedLine, EMBASE, CINAHL and PsycInfo. Searches were initially carried out on 21st July 2021 with final searches run on 23rd November 2022. Risk of bias was assessed using the NIH Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies. Of an initial 112 papers identified, seven papers were eligible for inclusion in the review reporting on 21,933 participants. Four studies reported on hippocampal volume, with inconclusive or no associations seen with MedDiet adherence. Two studies found a significant association between higher MedDiet adherence and lower WMHV, while two other studies found no significant associations. Overall these results highlight a gap in our knowledge about the associations between the MedDiet and AD and cerebrovascular related structural neuroimaging findings.

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.

Structural retinal changes in cerebral small vessel disease

Cerebral small vessel disease (CSVD) is an important contributor to cognitive impairment and stroke. Previous research has suggested associations with alterations in single retinal layers. We have assessed changes of all individual retinal layers in CSVD using high-resolution optical coherence tomography (OCT) for the first time. Subjects with recent magnetic resonance imaging (MRI) underwent macular and peripapillary retinal imaging using OCT for this case-control study. Number and volume ratio index (WMRI) of white matter lesions (WML) were determined on MRI. Data were analyzed using multiple linear regression models. 27 CSVD patients and 9 control participants were included. Ganglion cell layer (GCL) volume was significantly reduced in patients with CSVD compared to age-matched controls (p = 0.008). In patients with CSVD, larger foveal outer plexiform layer (OPL) volume and decreased temporal peripapillary retinal nerve fiber layer (RNFL) thickness were significantly associated with a higher WMRI in linear regression when controlling for age (p ≤ 0.033). Decreased foveal GCL volume and temporal-inferior RNFL thickness at Bruch's membrane opening (MRW), and increased temporal MRW were associated with a higher WML burden (p ≤ 0.037). Thus, we identified alterations in several OCT layers in individuals with CSVD (GCL, OPL, MRW and RNFL). Their potential diagnostic value merits further study.

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.

Longitudinal white matter hyperintensity changes and cognitive decline in patients with minor stroke

Background and objective

As reported, both minor stroke and white matter hyperintensities (WMHs) are associated with an increased risk of cognitive impairment and dementia. The underlying factors for dynamic changes in WMH volume and cognitive performances in patients with minor stroke remain poorly understood. A 2-year longitudinal study was designed to investigate the factors associated with the changes in white matter hyperintensity (WMH) volume on brain MRI and cognitive decline in patients with minor stroke.

Methods

A group of eligible patients with minor ischemic stroke was recruited in a row. At the initial and 2-year follow-up visits, all the participants underwent routine examinations, multimodal MRI, and cognitive assessment. Using a lesion prediction algorithm tool, we were able to automate the measurement of the change in WMH volume. During the 2-year follow-up, cognitive function was evaluated using Telephone Interview for Cognitive Status-Modified (TICS-m). Participants’ demographic, clinical, and therapeutic data were collected and statistically analyzed. Regression analyses were used to test the relationships between risk factors and changes in WMH volume and cognitive decline.

Results

Finally, we followed up with 225/261 participants for 2 years, with a mean age of 65.67 ± 10.73 years (65.6% men). WMH volume was observed to be increased in 113 patients, decreased in 74 patients, and remained stable in 58 patients. Patients with WMH progression were more often had a history of hypertension (p = 0.006) and a higher CSVD burden both at baseline and follow-up visit (p < 0.05). Longitudinally, the proportion of patients taking antihypertension medications on a regular basis in the regression group was higher than in the stable group (p = 0.01). When compared to the stable group, the presence of lacunes (OR 9.931, 95% CI 1.597–61.77, p = 0.014) was a stronger predictor of progression in WMH volume. 87 subjects (38.6%) displayed incident cognitive impairment. The progression of WMH volume was a significant risk factor for cognitive decline (p < 0.001).

Conclusions

The longitudinal change of WMH is dynamic. The regressive WMH volume was associated with the use of antihypertensive medications on a regular basis. The presence of lacunes at the initial visit of the study was a stronger predictor of WMH progression. The progression of WMH volume could be useful in predicting cognitive decline in patients with minor stroke.

A scoping review of resting-state brain functional alterations in Type 2 diabetes

Resting-state functional magnetic resonance imaging (rs-fMRI) has been actively used in the last decade to investigate brain functional connectivity alterations in Type 2 Diabetes Mellitus (T2DM) to understand the neuropathophysiology of T2DM in cognitive degeneration. Given the emergence of new analysis techniques, this scoping review aims to map the rs-fMRI analysis techniques that have been applied in the literature and reports the latest rs-fMRI findings that have not been covered in previous reviews. Graph theory, the contemporary rs-fMRI analysis, has been used to demonstrate altered brain topological organisations in people with T2DM, which included altered degree centrality, functional connectivity strength, the small-world architecture and network-based statistics. These alterations were correlated with T2DM patients' cognitive performances. Graph theory also contributes to identify unbiased seeds for seed-based analysis. The expanding rs-fMRI analytical approaches continue to provide new evidence that helps to understand the mechanisms of T2DM-related cognitive degeneration.

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

White matter hyperintensities (WMH) of presumed vascular origin are frequently found in MRIs of healthy older adults. WMH are also associated with aging and cognitive decline. Here, we compared and validated three algorithms for WMH extraction: FreeSurfer (T1w), UBO Detector (T1w + FLAIR), and FSL's Brain Intensity AbNormality Classification Algorithm (BIANCA; T1w + FLAIR) using a longitudinal dataset comprising MRI data of cognitively healthy older adults (baseline N = 231, age range 64-87 years). As reference we manually segmented WMH in T1w, three-dimensional (3D) FLAIR, and two-dimensional (2D) FLAIR images which were used to assess the segmentation accuracy of the different automated algorithms. Further, we assessed the relationships of WMH volumes provided by the algorithms with Fazekas scores and age. FreeSurfer underestimated the WMH volumes and scored worst in Dice Similarity Coefficient (DSC = 0.434) but its WMH volumes strongly correlated with the Fazekas scores (rs  = 0.73). BIANCA accomplished the highest DSC (0.602) in 3D FLAIR images. However, the relations with the Fazekas scores were only moderate, especially in the 2D FLAIR images (rs  = 0.41), and many outlier WMH volumes were detected when exploring within-person trajectories (2D FLAIR: ~30%). UBO Detector performed similarly to BIANCA in DSC with both modalities and reached the best DSC in 2D FLAIR (0.531) without requiring a tailored training dataset. In addition, it achieved very high associations with the Fazekas scores (2D FLAIR: rs  = 0.80). In summary, our results emphasize the importance of carefully contemplating the choice of the WMH segmentation algorithm and MR-modality.

Changes of the retinal and choroidal vasculature in cerebral small vessel disease

Cerebral small vessel disease (CSVD) is associated with changes in the retinal vasculature which can be assessed non-invasively with much higher resolution than the cerebral vasculature. To detect changes at a microvascular level, we used optical coherence tomography angiography which resolves retinal and choroidal vasculature. Participants with CSVD and controls were included. White matter lesions were determined on magnetic resonance imaging (MRI). The retinal and choroidal vasculature were quantified using swept-source optical coherence tomography angiography. Data were analysed using linear regression. We included 30 participants (18 females; patients, n = 20; controls, n = 10) with a mean age of 61 ± 10 years. Patients had a higher mean white matter lesion index and number of lesions than controls (p ≤ 0.002). The intraindividual deviation of choriocapillaris reflectivity differed significantly between age-matched patients (0.234 ± 0.012) and controls (0.247 ± 0.011; p = 0.029). Skeleton density of the deep retinal capillaries was significantly associated with the number of lesions on MRI (β = − 5.3 × 10⁸, 95%-confidence interval [− 10.3 × 10⁸; − 0.2 × 10⁸]) when controlling for age. The choroidal microvasculature and the deep retinal vascular plexus, as quantified by optical coherence tomography angiography, are significantly altered in CSVD. The value of these findings in diagnosing or monitoring CSVD need to be assessed in future studies.

The Effect of Training Sample Size on the Prediction of White Matter Hyperintensity Volume in a Healthy Population Using BIANCA

Introduction: White matter hyperintensities of presumed vascular origin (WMH) are an important magnetic resonance imaging marker of cerebral small vessel disease and are associated with cognitive decline, stroke, and mortality. Their relevance in healthy individuals, however, is less clear. This is partly due to the methodological challenge of accurately measuring rare and small WMH with automated segmentation programs. In this study, we tested whether WMH volumetry with FMRIB software library v6.0 (FSL; https://fsl.fmrib.ox.ac.uk/fsl/fslwiki) Brain Intensity AbNormality Classification Algorithm (BIANCA), a customizable and trainable algorithm that quantifies WMH volume based on individual data training sets, can be optimized for a normal aging population.

Methods: We evaluated the effect of varying training sample sizes on the accuracy and the robustness of the predicted white matter hyperintensity volume in a population (n = 201) with a low prevalence of confluent WMH and a substantial proportion of participants without WMH. BIANCA was trained with seven different sample sizes between 10 and 40 with increments of 5. For each sample size, 100 random samples of T1w and FLAIR images were drawn and trained with manually delineated masks. For validation, we defined an internal and external validation set and compared the mean absolute error, resulting from the difference between manually delineated and predicted WMH volumes for each set. For spatial overlap, we calculated the Dice similarity index (SI) for the external validation cohort.

Results: The study population had a median WMH volume of 0.34 ml (IQR of 1.6 ml) and included n = 28 (18%) participants without any WMH. The mean absolute error of the difference between BIANCA prediction and manually delineated masks was minimized and became more robust with an increasing number of training participants. The lowest mean absolute error of 0.05 ml (SD of 0.24 ml) was identified in the external validation set with a training sample size of 35. Compared to the volumetric overlap, the spatial overlap was poor with an average Dice similarity index of 0.14 (SD 0.16) in the external cohort, driven by subjects with very low lesion volumes.

Discussion: We found that the performance of BIANCA, particularly the robustness of predictions, could be optimized for use in populations with a low WMH load by enlargement of the training sample size. Further work is needed to evaluate and potentially improve the prediction accuracy for low lesion volumes. These findings are important for current and future population-based studies with the majority of participants being normal aging people.

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

BACKGROUND

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.

METHODS

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).

RESULTS

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.

CONCLUSION

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.

Neuropsychiatric systemic lupus erythematosus is associated with a distinct type and shape of cerebral white matter hyperintensities

Objectives

Advanced white matter hyperintensity (WMH) markers on brain MRI may help reveal underlying mechanisms and aid in the diagnosis of different phenotypes of SLE patients experiencing neuropsychiatric (NP) manifestations.

Methods

In this prospective cohort study, we included a clinically well-defined cohort of 155 patients consisting of 38 patients with NPSLE (26 inflammatory and 12 ischaemic phenotype) and 117 non-NPSLE patients. Differences in 3 T MRI WMH markers (volume, type and shape) were compared between patients with NPSLE and non-NPSLE and between patients with inflammatory and ischaemic NPSLE by linear and logistic regression analyses corrected for age, sex and intracranial volume.

Results

Compared with non-NPSLE [92% female; mean age 42 (13) years], patients with NPSLE [87% female; mean age 40 (14) years] showed a higher total WMH volume [B (95%-CI)]: 0.46 (0.0 7 ↔ 0.86); P = 0.021], a higher periventricular/confluent WMH volume [0.46 (0.0 6 ↔ 0.86); P = 0.024], a higher occurrence of periventricular with deep WMH type [0.32 (0.1 3 ↔ 0.77); P = 0.011], a higher number of deep WMH lesions [3.06 (1.2 1 ↔ 4.90); P = 0.001] and a more complex WMH shape [convexity: ‒0.07 (‒0.12 ↔ ‒0.02); P = 0.011, concavity index: 0.05 (0.0 1 ↔ 0.08); P = 0.007]. WMH shape was more complex in inflammatory NPSLE patients [89% female; mean age 39 (15) years] compared with patients with the ischaemic phenotype [83% female; mean age 41 (11) years] [concavity index: 0.08 (0.0 1 ↔ 0.15); P = 0.034].

Conclusion

We demonstrated that patients with NPSLE showed a higher periventricular/confluent WMH volume and more complex shape of WMH compared with non-NPSLE patients. This finding was particularly significant in inflammatory NPLSE patients, suggesting different or more severe underlying pathophysiological abnormalities.

A deep learning algorithm for white matter hyperintensity lesion detection and segmentation

PURPOSE

White matter hyperintensity (WMHI) lesions on MR images are an important indication of various types of brain diseases that involve inflammation and blood vessel abnormalities. Automated quantification of the WMHI can be valuable for the clinical management of patients, but existing automated software is often developed for a single type of disease and may not be applicable for clinical scans with thick slices and different scanning protocols. The purpose of the study is to develop and validate an algorithm for automatic quantification of white matter hyperintensity suitable for heterogeneous MRI data with different disease types.

METHODS

We developed and evaluated "DeepWML", a deep learning method for fully automated white matter lesion (WML) segmentation of multicentre FLAIR images. We used MRI from 507 patients, including three distinct white matter diseases, obtained in 9 centres, with a wide range of scanners and acquisition protocols. The automated delineation tool was evaluated through quantitative parameters of Dice similarity, sensitivity and precision compared to manual delineation (gold standard).

RESULTS

The overall median Dice similarity coefficient was 0.78 (range 0.64 ~ 0.86) across the three disease types and multiple centres. The median sensitivity and precision were 0.84 (range 0.67 ~ 0.94) and 0.81 (range 0.64 ~ 0.92), respectively. The tool's performance increased with larger lesion volumes.

CONCLUSION

DeepWML was successfully applied to a wide spectrum of MRI data in the three white matter disease types, which has the potential to improve the practical workflow of white matter lesion delineation.

Cardiac Hypertrophy Is Associated With Advanced Brain Aging in the General Population

Background

Hypertrophy of the left ventricle (LV) has recently been associated with adverse changes of brain structure in older adults, notably increased burden of white matter hyperintensities (WMHs). Whether greater LV size or mass is also related to WMH burden in middle‐aged adults is currently unclear. In addition, its relation with alterations in cortical thickness (CT) has not been studied to date.

Methods and Results

Data from 1602 participants of the population‐based SHIP (Study of Health in Pomerania) with LV ejection fraction >40% and no history of myocardial infarction were included (aged 21–82 years; median age, 49 years; 53% women). Participants underwent both echocardiography and magnetic resonance imaging of the head. Imaging markers of brain aging (ie, CT and WMH volume) were determined from magnetic resonance imaging scans. LV mass and diameter were associated with lower global CT and greater WMH volume, while adjusting for age, sex, body height, fat‐free body mass, and intracranial volume. Moreover, thicknesses of the interventricular septum and posterior wall were also associated with lower global CT. These associations could not be explained by cardiovascular risk factors (including hypertension), inflammatory markers, or sociodemographic factors. Regional analyses showed distinct spatial patterns of lower CT in association with LV diameter and posterior wall thickness.

Conclusions

LV diameter and mass are associated with lower global and regional CT as well as greater WMH burden in the general population. These findings highlight the brain structural underpinnings of the associations of LV hypertrophy with cognitive decline and dementia.

White matter hyperintensities associate with cognitive slowing in patients with systemic lupus erythematosus and neuropsychiatric symptoms

Objective

To compare cognitive function between patients with different phenotypes of neuropsychiatric systemic lupus erythematosus (NPSLE) and assess its association with brain and white matter hyperintensity (WMH) volumes.

Methods

Patients attending the Leiden University Medical Centre NPSLE clinic between 2007 and 2015 without large brain infarcts were included (n=151; 42±13 years, 91% women). In a multidisciplinary consensus meeting, neuropsychiatric symptoms were attributed to systemic lupus erythematosus (SLE) (NPSLE, inflammatory (n=24) or ischaemic (n=12)) or to minor/non-NPSLE (n=115). Multiple regression analyses were performed to compare cognitive function between NPSLE phenotypes and to assess associations between brain and WMH volumes and cognitive function cross-sectionally.

Results

Global cognitive function was impaired in 5%, learning and memory (LM) in 46%, executive function and complex attention (EFCA) in 39% and psychomotor speed (PS) in 46% of all patients. Patients with inflammatory NPSLE showed the most cognitive impairment in all domains (p≤0.05).

Higher WMH volume associated with lower PS in the total group (B: −0.14 (95% CI −0.32 to −0.02)); especially in inflammatory NPSLE (B: −0.36 (95% CI −0.60 to −0.12). In the total group, lower total brain volume and grey matter volume associated with lower cognitive functioning in all domains (all: 0.00/0.01 (0.00;0.01)) and lower white matter volume associated with lower LM, EFCA and PS (all: 0.00/0.01 (0.00;0.01)).

Conclusion

We demonstrated that an association between brain and WMH volumes and cognitive function is present in patients with SLE, but differs between (NP)SLE phenotypes. WMHs associated with PS especially in inflammatory NPSLE, which suggests a different, potentially more severe underlying pathophysiological mechanism of cognitive impairment in this phenotype.

Emerging role of white matter lesions in cerebrovascular disease

White matter lesions have been implicated in the setting of stroke, dementia, intracerebral haemorrhage, several other cerebrovascular conditions, migraine, various neuroimmunological diseases like multiple sclerosis, disorders of metabolism, mitochondrial diseases and others. While much is understood vis a vis neuroimmunological conditions, our knowledge of the pathophysiology of these lesions, and their role in, and implications to, management of cerebrovascular diseases or stroke, especially in the elderly, are limited. Several clinical assessment tools are available for delineating white matter lesions in clinical practice. However, their incorporation into clinical decision-making and specifically prognosis and management of patients is suboptimal for use in standards of care. This article sought to provide an overview of the current knowledge and recent advances on pathophysiology, as well as clinical and radiological assessment, of white matter lesions with a focus on its development, progression and clinical implications in cerebrovascular diseases. Key indications for clinical practice and recommendations on future areas of research are also discussed. Finally, a conceptual proposal on putative mechanisms underlying pathogenesis of white matter lesions in cerebrovascular disease has been presented. Understanding of pathophysiology of white matter lesions and how they mediate outcomes is important to develop therapeutic strategies.

Different phenotypes of neuropsychiatric systemic lupus erythematosus are related to a distinct pattern of structural changes on brain MRI

Objectives

The underlying structural brain correlates of neuropsychiatric involvement in systemic lupus erythematosus (NPSLE) remain unclear, thus hindering correct diagnosis.

We compared brain tissue volumes between a clinically well-defined cohort of patients with NPSLE and SLE patients with neuropsychiatric syndromes not attributed to SLE (non-NPSLE). Within the NPSLE patients, we also examined differences between patients with two distinct disease phenotypes: ischemic and inflammatory.

Methods

In this prospective (May 2007 to April 2015) cohort study, we included 38 NPSLE patients (26 inflammatory and 12 ischemic) and 117 non-NPSLE patients. All patients underwent a 3-T brain MRI scan that was used to automatically determine white matter, grey matter, white matter hyperintensities (WMH) and total brain volumes. Group differences in brain tissue volumes were studied with linear regression analyses corrected for age, gender, and total intracranial volume and expressed as B values and 95% confidence intervals.

Results

NPSLE patients showed higher WMH volume compared to non-NPSLE patients (p = 0.004). NPSLE inflammatory patients showed lower total brain (p = 0.014) and white matter volumes (p = 0.020), and higher WMH volume (p = 0.002) compared to non-NPSLE patients. Additionally, NPSLE inflammatory patients showed lower white matter (p = 0.020) and total brain volumes (p = 0.038) compared to NPSLE ischemic patients.

Conclusion

We showed that different phenotypes of NPSLE were related to distinct patterns of underlying structural brain MRI changes. Especially the inflammatory phenotype of NPSLE was associated with the most pronounced brain volume changes, which might facilitate the diagnostic process in SLE patients with neuropsychiatric symptoms.

Key Points

• Neuropsychiatric systemic lupus erythematosus (NPSLE) patients showed a higher WMH volume compared to SLE patients with neuropsychiatric syndromes not attributed to SLE (non-NPSLE).

• NPSLE patients with inflammatory phenotype showed a lower total brain and white matter volume, and a higher volume of white matter hyperintensities, compared to non-NPSLE patients.

• NPSLE patients with inflammatory phenotype showed lower white matter and total brain volumes compared to NPSLE patients with ischemic phenotype.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-07970-2.

Topographic patterns of white matter hyperintensities are associated with multimodal neuroimaging biomarkers of Alzheimer's disease

Background

White matter hyperintensities (WMH) are frequently found in Alzheimer’s disease (AD). Commonly considered as a marker of cerebrovascular disease, regional WMH may be related to pathological hallmarks of AD, including beta-amyloid (Aβ) plaques and neurodegeneration. The aim of this study was to examine the regional distribution of WMH associated with Aβ burden, glucose hypometabolism, and gray matter volume reduction.

Methods

In a total of 155 participants (IMAP+ cohort) across the cognitive continuum from normal cognition to AD dementia, FLAIR MRI, AV45-PET, FDG-PET, and T1 MRI were acquired. WMH were automatically segmented from FLAIR images. Mean levels of neocortical Aβ deposition (AV45-PET), temporo-parietal glucose metabolism (FDG-PET), and medial-temporal gray matter volume (GMV) were extracted from processed images using established AD meta-signature templates. Associations between AD brain biomarkers and WMH, as assessed in region-of-interest and voxel-wise, were examined, adjusting for age, sex, education, and systolic blood pressure.

Results

There were no significant associations between global Aβ burden and region-specific WMH. Voxel-wise WMH in the splenium of the corpus callosum correlated with greater Aβ deposition at a more liberal threshold. Region- and voxel-based WMH in the posterior corpus callosum, along with parietal, occipital, and frontal areas, were associated with lower temporo-parietal glucose metabolism. Similarly, lower medial-temporal GMV correlated with WMH in the posterior corpus callosum in addition to parietal, occipital, and fontal areas.

Conclusions

This study demonstrates that local white matter damage is correlated with multimodal brain biomarkers of AD. Our results highlight modality-specific topographic patterns of WMH, which converged in the posterior white matter. Overall, these cross-sectional findings corroborate associations of regional WMH with AD-typical Aß deposition and neurodegeneration.

White Matter Hyperintensities Quantification in Healthy Adults: A Systematic Review and Meta-Analysis

BACKGROUND

Although white matter hyperintensities (WMH) volumetric assessment is now customary in research studies, inconsistent WMH measures among homogenous populations may prevent the clinical usability of this biomarker.

PURPOSE

To determine whether a point estimate and reference standard for WMH volume in the healthy aging population could be determined.

STUDY TYPE

Systematic review and meta-analysis.

POPULATION

In all, 9716 adult subjects from 38 studies reporting WMH volume were retrieved following a systematic search on EMBASE.

FIELD STRENGTH/SEQUENCE

1.0T, 1.5T, or 3.0T/fluid-attenuated inversion recovery (FLAIR) and/or proton density/T₂ -weighted fast spin echo sequences or gradient echo T₁ -weighted sequences.

ASSESSMENT

After a literature search, sample size, demographics, magnetic field strength, MRI sequences, level of automation in WMH assessment, study population, and WMH volume were extracted.

STATISTICAL TESTS

The pooled WMH volume with 95% confidence interval (CI) was calculated using the random-effect model. The I² statistic was calculated as a measure of heterogeneity across studies. Meta-regression analysis of WMH volume on age was performed.

RESULTS

Of the 38 studies analyzed, 17 reported WMH volume as the mean and standard deviation (SD) and were included in the meta-analysis. Mean and SD of age was 66.11 ± 10.92 years (percentage of men 50.45% ± 21.48%). Heterogeneity was very high (I²  = 99%). The pooled WMH volume was 4.70 cm³ (95% CI: 3.88-5.53 cm³ ). At meta-regression analysis, WMH volume was positively associated with subjects' age (β = 0.358 cm³ per year, P < 0.05, R²  = 0.27).

DATA CONCLUSION

The lack of standardization in the definition of WMH together with the high technical variability in assessment may explain a large component of the observed heterogeneity. Currently, volumes of WMH in healthy subjects are not comparable between studies and an estimate and reference interval could not be determined.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY STAGE: 1.

Cortical Thickness Estimation in Individuals With Cerebral Small Vessel Disease, Focal Atrophy, and Chronic Stroke Lesions

BACKGROUND

Regional changes to cortical thickness in individuals with neurodegenerative and cerebrovascular diseases (CVD) can be estimated using specialized neuroimaging software. However, the presence of cerebral small vessel disease, focal atrophy, and cortico-subcortical stroke lesions, pose significant challenges that increase the likelihood of misclassification errors and segmentation failures.

PURPOSE

The main goal of this study was to examine a correction procedure developed for enhancing FreeSurfer's (FS's) cortical thickness estimation tool, particularly when applied to the most challenging MRI obtained from participants with chronic stroke and CVD, with varying degrees of neurovascular lesions and brain atrophy.

METHODS

In 155 CVD participants enrolled in the Ontario Neurodegenerative Disease Research Initiative (ONDRI), FS outputs were compared between a fully automated, unmodified procedure and a corrected procedure that accounted for potential sources of error due to atrophy and neurovascular lesions. Quality control (QC) measures were obtained from both procedures. Association between cortical thickness and global cognitive status as assessed by the Montreal Cognitive Assessment (MoCA) score was also investigated from both procedures.

RESULTS

Corrected procedures increased "Acceptable" QC ratings from 18 to 76% for the cortical ribbon and from 38 to 92% for tissue segmentation. Corrected procedures reduced "Fail" ratings from 11 to 0% for the cortical ribbon and 62 to 8% for tissue segmentation. FS-based segmentation of T1-weighted white matter hypointensities were significantly greater in the corrected procedure (5.8 mL vs. 15.9 mL, p < 0.001). The unmodified procedure yielded no significant associations with global cognitive status, whereas the corrected procedure yielded positive associations between MoCA total score and clusters of cortical thickness in the left superior parietal (p = 0.018) and left insula (p = 0.04) regions. Further analyses with the corrected cortical thickness results and MoCA subscores showed a positive association between left superior parietal cortical thickness and Attention (p < 0.001).

CONCLUSION

These findings suggest that correction procedures which account for brain atrophy and neurovascular lesions can significantly improve FS's segmentation results and reduce failure rates, thus maximizing power by preventing the loss of our important study participants. Future work will examine relationships between cortical thickness, cerebral small vessel disease, and cognitive dysfunction due to neurodegenerative disease in the ONDRI study.

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

•

The comparison used 207 images from both research and clinical datasets.

•

When retrained, NicMSlesion, a convolutional network, was the most accurate.

•

Performance of this deep learning method severely dropped on clinical routine data.

•

On clinical routine data, regression and clustering methods were the top-ranked methods.

•

SLS was the most robust to artifacted images, and BIANCA to scanners variability.

Background

Manual 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.

Purpose

To 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 Methods

We 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, Valverde et al., 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.

Results

A 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.

Conclusion

This work provides an objective comparison of methods for WMH segmentation. Results can be used by radiologists to select a tool.

Small vessel disease lesion type and brain atrophy: The role of co-occurring amyloid

INTRODUCTION

It is unknown whether different types of small vessel disease (SVD), differentially relate to brain atrophy and if co-occurring Alzheimer's disease pathology affects this relation.

METHODS

In 725 memory clinic patients with SVD (mean age 67 ± 8 years, 48% female) we compared brain volumes of those with moderate/severe white matter hyperintensities (WMHs; n = 326), lacunes (n = 132) and cerebral microbleeds (n = 321) to a reference group with mild WMHs (n = 197), also considering cerebrospinal fluid (CSF) amyloid status in a subset of patients (n = 488).

RESULTS

WMHs and lacunes, but not cerebral microbleeds, were associated with smaller gray matter (GM) volumes. In analyses stratified by CSF amyloid status, WMHs and lacunes were associated with smaller total brain and GM volumes only in amyloid-negative patients. SVD-related atrophy was most evident in frontal (cortical) GM, again predominantly in amyloid-negative patients.

DISCUSSION

Amyloid status modifies the differential relation between SVD lesion type and brain atrophy in memory clinic patients.