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

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.

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.

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.

Distinct characteristics and severity of brain magnetic resonance imaging lesions in women and men with multiple sclerosis assessed using verified texture analysis measures

Background and goal

In vivo characterization of brain lesion types in multiple sclerosis (MS) has been an ongoing challenge. Based on verified texture analysis measures from clinical magnetic resonance imaging (MRI), this study aimed to develop a method to identify two extremes of brain MS lesions that were approximately severely demyelinated (sDEM) and highly remyelinated (hREM), and compare them in terms of common clinical variables.

Method

Texture analysis used an optimized gray-level co-occurrence matrix (GLCM) method based on FLAIR MRI from 200 relapsing-remitting MS participants. Two top-performing metrics were calculated: texture contrast and dissimilarity. Lesion identification applied a percentile approach according to texture values calculated: ≤ 25 percentile for hREM and ≥75 percentile for sDEM.

Results

The sDEM had a greater total normalized volume yet smaller average size, and worse MRI texture than hREM. In lesion distribution mapping, the two lesion types appeared to overlap largely in location and were present the most in the corpus callosum and periventricular regions. Further, in sDEM, the normalized volume was greater and in hREM, the average size was smaller in men than women. There were no other significant results in clinical variable-associated analyses.

Conclusion

Percentile statistics of competitive MRI texture measures may be a promising method for probing select types of brain MS lesion pathology. Associated findings can provide another useful dimension for improved measurement and monitoring of disease activity in MS. The different characteristics of sDEM and hREM between men and women likely adds new information to the literature, deserving further confirmation.

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.

Adapting UK Biobank imaging for use in a routine memory clinic setting: The Oxford Brain Health Clinic

The Oxford Brain Health Clinic (BHC) is a joint clinical-research service that provides memory clinic patients and clinicians access to high-quality assessments not routinely available, including brain MRI aligned with the UK Biobank imaging study (UKB). In this work we present how we 1) adapted the UKB MRI acquisition protocol to be suitable for memory clinic patients, 2) modified the imaging analysis pipeline to extract measures that are in line with radiology reports and 3) explored the alignment of measures from BHC patients to the largest brain MRI study in the world (ultimately 100,000 participants). Adaptations of the UKB acquisition protocol for BHC patients include dividing the scan into core and optional sequences (i.e., additional imaging modalities) to improve patients' tolerance for the MRI assessment. We adapted the UKB structural MRI analysis pipeline to take into account the characteristics of a memory clinic population (e.g., high amount of white matter hyperintensities and hippocampal atrophy). We then compared the imaging derived phenotypes (IDPs) extracted from the structural scans to visual ratings from radiology reports, non-imaging factors (age, cognition) and to reference distributions derived from UKB data. Of the first 108 BHC attendees (August 2020-November 2021), 92.5 % completed the clinical scans, 88.0 % consented to use of data for research, and 43.5 % completed the additional research sequences, demonstrating that the protocol is well tolerated. The high rates of consent to research makes this a valuable real-world quality research dataset routinely captured in a clinical service. Modified tissue-type segmentation with lesion masking greatly improved grey matter volume estimation. CSF-masking marginally improved hippocampal segmentation. The IDPs were in line with radiology reports and showed significant associations with age and cognitive performance, in line with the literature. Due to the age difference between memory clinic patients of the BHC (age range 65-101 years, average 78.3 years) and UKB participants (44-82 years, average 64 years), additional scans on elderly healthy controls are needed to improve reference distributions. Current and future work aims to integrate automated quantitative measures in the radiology reports and evaluate their clinical utility.

Cerebrovascular reactivity and deep white matter hyperintensities in migraine: A prospective CO2 targeting study

Several studies suggested the association of migraine with deep white matter hyperintensities (WMHs). We aimed to explore the cerebrovascular reactivity (CVR), deep WMH burden, and their association in patients with migraine using a state-of-the-art methodology. A total of 31 patients with migraine without aura and 31 age/sex-matched controls underwent 3T MRI with prospective end-tidal carbon dioxide (CO₂) targeting. We quantified deep WMH clusters using an automated segmentation tool and measured voxel-wise CVR by changes in blood oxygen level-dependent signal fitted to subjects' end-tidal CO₂. The association of migraine and CVR with the presence of WMH in each voxel and interaction of migraine and CVR on WMH were analysed. Patients had a higher number of deep WMHs than controls (p = 0.015). Migraine and reduced CVR were associated with increased probability of having WMHs in each voxel (adjusted OR 30.78 [95% CI 1.89-500.53], p = 0.016 and adjusted OR 0.30 [0.29-0.32], p < 0.001, respectively). Migraine had an effect modification on CVR on deep WMHs (p for interaction <0.001): i.e. the association between CVR and WMH was greater in patients than in controls. We suggest that the migraine-WMH association can be explained by the effect modification on the CVR.

Automatic segmentation of white matter hyperintensities in routine clinical brain MRI by 2D VB-Net: A large-scale study

White matter hyperintensities (WMH) are imaging manifestations frequently observed in various neurological disorders, yet the clinical application of WMH quantification is limited. In this study, we designed a series of dedicated WMH labeling protocols and proposed a convolutional neural network named 2D VB-Net for the segmentation of WMH and other coexisting intracranial lesions based on a large dataset of 1,045 subjects across various demographics and multiple scanners using 2D thick-slice protocols that are more commonly applied in clinical practice. Using our labeling pipeline, the Dice consistency of the WMH regions manually depicted by two observers was 0.878, which formed a solid basis for the development and evaluation of the automatic segmentation system. The proposed algorithm outperformed other state-of-the-art methods (uResNet, 3D V-Net and Visual Geometry Group network) in the segmentation of WMH and other coexisting intracranial lesions and was well validated on datasets with thick-slice magnetic resonance (MR) images and the 2017 medical image computing and computer assisted intervention WMH Segmentation Challenge dataset (with thin-slice MR images), all showing excellent effectiveness. Furthermore, our method can subclassify WMH to display the WMH distributions and is very lightweight. Additionally, in terms of correlation to visual rating scores, our algorithm showed excellent consistency with the manual delineations and was overall better than those from other competing methods. In conclusion, we developed an automatic WMH quantification framework for multiple application scenarios, exhibiting a promising future in clinical practice.

Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images

Robust automated segmentation of white matter hyperintensities (WMHs) in different datasets (domains) is highly challenging due to differences in acquisition (scanner, sequence), population (WMH amount and location) and limited availability of manual segmentations to train supervised algorithms. In this work we explore various domain adaptation techniques such as transfer learning and domain adversarial learning methods, including domain adversarial neural networks and domain unlearning, to improve the generalisability of our recently proposed triplanar ensemble network, which is our baseline model. We used datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For the source domain, we considered a dataset consisting of data acquired from 3 different scanners, while the target domain consisted of 2 datasets. We evaluated the domain adaptation techniques on the target domain datasets, and additionally evaluated the performance on the source domain test dataset for the adversarial techniques. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for fine-tuning in the target domain. On comparing the performance of different techniques on the target dataset, domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Predicting the progression of Parkinson's disease using conventional MRI and machine learning: An application of radiomic biomarkers in whole-brain white matter

PURPOSE

This study aimed to develop and validate a radiomics model based on whole-brain white matter and clinical features to predict the progression of Parkinson disease (PD).

METHODS

PD patient data from the Parkinson's Progress Markers Initiative (PPMI) database was evaluated. Seventy-two PD patients with disease progression, as measured by the Hoehn-Yahr Scale (HYS) (stage 1-5), and 72 PD patients with stable PD were matched by sex, age, and category of HYS and included in the current study. Each individual's T₁ -weighted MRI scans at the baseline timepoint were segmented to isolate whole-brain white matter for radiomics feature extraction. The total dataset was divided into a training and test set according to subject serial number. The size of the training dataset was reduced using the maximum relevance minimum redundancy (mRMR) algorithm to construct a radiomics signature using machine learning. Finally, a joint model was constructed by incorporating the radiomics signature and clinical progression scores. The test data were then used to validate the prediction models, which were evaluated based on discrimination, calibration, and clinical utility.

RESULTS

Based on the overall data, the areas under curve (AUCs) of the joint model, signature and Unified Parkinson Disease Rating Scale III PD rating score were 0.836, 0.795, and 0.550, respectively. Furthermore, the sensitivities were 0.805, 0.875, and 0.292, respectively, and the specificities were 0.722, 0.697, and 0.861, respectively. In addition, the predictive accuracy of the model was 0.827, the sensitivity was 0.829 and the specificity was 0.702 for stage-1 PD. For stage-2 PD, the predictive accuracy of the model was 0.854, the sensitivity was 0.960, and the specificity was 0.600.

CONCLUSION

Our results provide evidence that conventional structural MRI can predict the progression of PD. This work also supports the use of a simple radiomics signature built from whole-brain white matter features as a useful tool for the assessment and monitoring of PD progression.

Radiomics from magnetic resonance imaging may be used to predict the progression of white matter hyperintensities and identify associated risk factors

OBJECTIVE

The progression of white matter hyperintensities (WMH) varies considerably in adults. In this study, we aimed to predict the progression and related risk factors of WMH based on the radiomics of whole-brain white matter (WBWM).

METHODS

A retrospective analysis was conducted on 141 patients with WMH who underwent two consecutive brain magnetic resonance (MR) imaging sessions from March 2014 to May 2018. The WBWM was segmented to extract and score the radiomics features at baseline. Follow-up images were evaluated using the modified Fazekas scale, with progression indicated by scores ≥ 1. Patients were divided into progressive (n = 65) and non-progressive (n = 76) groups. The progressive group was subdivided into any WMH (AWMH), periventricular WMH (PWMH), and deep WMH (DWMH). Independent risk factors were identified using logistic regression.

RESULTS

The area under the curve (AUC) values for the radiomics signatures of the training sets were 0.758, 0.749, and 0.775 for AWMH, PWMH, and DWMH, respectively. The AUC values of the validation set were 0.714, 0.697, and 0.717, respectively. Age and hyperlipidemia were independent predictors of progression for AWMH. Age and body mass index (BMI) were independent predictors of progression for DWMH, while hyperlipidemia was an independent predictor of progression for PWMH. After combining clinical factors and radiomics signatures, the AUC values were 0.848, 0.863, and 0.861, respectively, for the training set, and 0.824, 0.818, and 0.833, respectively, for the validation set.

CONCLUSIONS

MRI-based radiomics of WBWM, along with specific risk factors, may allow physicians to predict the progression of WMH.

KEY POINTS

• Radiomics features detected by magnetic resonance imaging may be used to predict the progression of white matter hyperintensities. • Radiomics may be used to identify risk factors associated with the progression of white matter hyperintensities. • Radiomics may serve as non-invasive biomarkers to monitor white matter status.

The orbitofrontal cortex functionally links obesity and white matter hyperintensities

Many studies have linked dysfunction in cognitive control-related brain regions with obesity and the burden of white matter hyperintensities (WMHs). This study aimed to explore how functional connectivity differences in the brain are associated with WMH burden and degree of obesity using resting-state functional magnetic resonance imaging (fMRI) in 182 participants. Functional connectivity measures were compared among four different groups: (1) low WMH burden, non-obese; (2) low WMH burden, obese; (3) high WMH burden, non-obese; and (4) high WMH burden, obese. At a large-scale network-level, no networks showed significant interaction effects, but the frontoparietal network showed a main effect of degree of obesity. At a finer node level, the orbitofrontal cortex showed interaction effects between periventricular WMH burden and degree of obesity. Higher functional connectivity was observed when the periventricular WMH burden and degree of obesity were both high. These results indicate that the functional connectivity of the orbitofrontal cortex is affected by the mutual interaction between the periventricular WMHs and degree of obesity. Our results suggest that this region links obesity with WMHs in terms of functional connectivity.

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

BACKGROUND AND OBJECTIVE

Patients with migraine show an increased presence of white matter hyperintensities (WMHs), especially deep WMHs. Segmentation of small, deep WMHs is a critical issue in managing migraine care. Here, we aim to develop a novel approach to segmenting deep WMHs using deep neural networks based on the U-Net.

METHODS

148 non-elderly subjects with migraine were recruited for this study. Our model consists of two networks: the first identifies potential deep WMH candidates, and the second reduces the false positives within the candidates. The first network for initial segmentation includes four down-sampling layers and four up-sampling layers to sort the candidates. The second network for false positive reduction uses a smaller field-of-view and depth than the first network to increase utilization of local information.

RESULTS

Our proposed model segments deep WMHs with a high true positive rate of 0.88, a low false discovery rate of 0.13, and F₁ score of 0.88 tested with ten-fold cross-validation. Our model was automatic and performed better than existing models based on conventional machine learning.

CONCLUSION

We developed a novel segmentation framework tailored for deep WMHs using U-Net. Our algorithm is open-access to promote future research in quantifying deep WMHs and might contribute to the effective management of WMHs in migraineurs.

Cerebrovascular reactivity as a determinant of deep white matter hyperintensities in migraine

OBJECTIVE

To evaluate the association between the cerebrovascular reactivity to carbon dioxide (CO₂-CVR) and the deep white matter hyperintensity (WMH) burden in patients with migraine.

METHODS

A total of 86 nonelderly patients with episodic migraine without vascular risk factors and 35 headache-free controls underwent 3T MRI. Deep WMHs were quantified with a segmentation method developed for nonelderly migraineurs. The interictal CO₂-CVR was measured with transcranial Doppler with the breath-holding method. The mean breath-holding index of the bilateral middle cerebral arteries (MCA-BHI) was square root transformed and analyzed with univariate and multivariate logistic regression models to determine its association with the highest tertiles of deep WMH burden (number and volume).

RESULTS

A low MCA-BHI was independently associated with the highest tertile of deep WMH number in patients with migraine (adjusted odds ratio [OR] 0.02, 95% confidence interval [CI] 0.0007-0.63, p = 0.026). In controls, the MCA-BHI was not associated with deep WMH number. Interaction analysis revealed that migraine modified the effect of MCA-BHI on deep WMH number (p for interaction = 0.029). The MCA-BHI was not associated with increased deep WMH volume in both patients and controls. Age was independently associated with deep WMH volume in patients (adjusted OR 1.07, 95% CI 1.004-1.15, p = 0.037).

CONCLUSIONS

In this study, we found a migraine-specific association between a reduced CVR to apnea and increased number of deep WMHs in healthy, nonelderly patients with migraine. A dysfunctional vascular response to apnea may predispose migraineurs to an increased risk of WMHs.