Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images.
Ontology highlight
ABSTRACT:
SUBMITTER: Sundaresan V
PROVIDER: S-EPMC8573594 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:White matter hyperintensities (WMHs) have been associated with various cerebrovascular and neurodegenerative diseases. Reliable quantification of WMHs is essential for understanding their clinical impact in normal and pathological populations. Automated segmentation of WMHs is highly challenging due to heterogeneity in WMH characteristics between deep and periventricular white matter, presence of artefacts and differences in the pathology and demographics of populations. In this work, we propose an ensemble triplanar network that combines the predictions from three different planes of brain MR images to provide an accurate WMH segmentation. In the loss functions the network uses anatomical information regarding WMH spatial distribution in loss functions, to improve the efficiency of segmentation and to overcome the contrast variations between deep and periventricular WMHs. We evaluated our method on 5 datasets, of which 3 are part of a publicly available dataset (training data for MICCAI WMH Segmentation Challenge 2017 - MWSC 2017) consisting of subjects from three different cohorts, and we also submitted our method to MWSC 2017 to be evaluated on the unseen test datasets. On evaluating our method separately in deep and periventricular regions, we observed robust and comparable performance in both regions. Our method performed better than most of the existing methods, including FSL BIANCA, and on par with the top ranking deep learning methods of MWSC 2017.
| S-EPMC8505759 | biostudies-literature
Project description:White matter hyperintensities (WMHs) are associated with progressive age-related cognitive decline and cardiovascular risk factors, but their biological relevance as indicators of generalized white matter injury is unclear. Diffusion tensor imaging provides more sensitive indications of subtle white matter disruption and can therefore clarify whether WMHs represent foci of generalized white matter damage that extends over a broader neighborhood.Two hundred eight participants from the University of California, Davis Alzheimer's Disease Center received a comprehensive clinical evaluation and brain MRI including fluid-attenuated inversion recovery and diffusion tensor imaging sequences. Voxelwise maps of WMHs were produced from fluid-attenuated inversion recovery using a standardized WMH detection protocol. Fractional anisotropy maps were calculated from diffusion tensor imaging. All WMH and fractional anisotropy maps were coregistered to a standardized space. For each normal-appearing white matter voxel in each subject fluid-attenuated inversion recovery scan, a neighborhood white matter injury score was calculated that increased with increasing number and proximity of WMH in the vicinity of the normal-appearing white matter voxel. Fractional anisotropy was related to neighborhood white matter injury using a nonlinear mixed effect model controlling for relevant confounding factors.Fractional anisotropy was found to decrease as neighborhood white matter injury increased (? = -0.0017/%, P < 0.0001) with an accelerated rate (P < 0.0001) for neighborhood white matter injury >0.4. An increase of 1% in neighborhood white matter injury score was associated with a decrease in mean fractional anisotropy of 0.012 (P < 0.001).WMH may represent foci of more widespread and subtle white matter changes rather than distinct, sharply delineated anatomic abnormalities. We use the term white matter hyperintensities penumbra to explain this phenomenon.
| S-EPMC3125449 | biostudies-literature
Project description:White matter hyperintensities (WMHs) are a common manifestation of cerebral small vessel disease, that is increasingly studied with large, pooled multicenter datasets. This data pooling increases statistical power, but poses challenges for automated WMH segmentation. Although there is extensive literature on the evaluation of automated WMH segmentation methods, such evaluations in a multicenter setting are lacking. We performed WMH segmentations in sixty patients scanned on six different magnetic resonance imaging (MRI) scanners (10 patients per scanner) using five freely available and fully-automated WMH segmentation methods (Cascade, kNN-TTP, Lesion-TOADS, LST-LGA and LST-LPA). Different MRI scanner vendors and field strengths were included. We compared these automated WMH segmentations with manual WMH segmentations as a reference. Performance of each method both within and across scanners was assessed using spatial and volumetric correspondence with the reference segmentations by Dice's similarity coefficient (DSC) and intra-class correlation coefficient (ICC) respectively. We found the best performance, both within and across scanners, for kNN-TTP, followed by LST-LPA and LST-LGA, with worse performance for Lesion-TOADS and Cascade. Our findings can serve as a guide for choosing a method and also highlight the importance to further improve and evaluate consistency of methods in a multicenter setting.
| S-EPMC6856351 | biostudies-literature
Project description:Migraineurs show an increased load of white matter hyperintensities (WMHs) and more rapid deep WMH progression. Previous methods for WMH segmentation have limited efficacy to detect small deep WMHs. We developed a new fully automated detection pipeline, DEWS (DEep White matter hyperintensity Segmentation framework), for small and superficially-located deep WMHs. A total of 148 non-elderly subjects with migraine were included in this study. The pipeline consists of three components: 1) white matter (WM) extraction, 2) WMH detection, and 3) false positive reduction. In WM extraction, we adjusted the WM mask to re-assign misclassified WMHs back to WM using many sequential low-level image processing steps. In WMH detection, the potential WMH clusters were detected using an intensity based threshold and region growing approach. For false positive reduction, the detected WMH clusters were classified into final WMHs and non-WMHs using the random forest (RF) classifier. Size, texture, and multi-scale deep features were used to train the RF classifier. DEWS successfully detected small deep WMHs with a high positive predictive value (PPV) of 0.98 and true positive rate (TPR) of 0.70 in the training and test sets. Similar performance of PPV (0.96) and TPR (0.68) was attained in the validation set. DEWS showed a superior performance in comparison with other methods. Our proposed pipeline is freely available online to help the research community in quantifying deep WMHs in non-elderly adults.
| S-EPMC5964963 | biostudies-literature
Project description:White matter hyperintensities (WMHs) are frequently observed on structural neuroimaging of elderly populations and are associated with cognitive decline and increased risk of dementia. Many existing WMH segmentation algorithms produce suboptimal results in populations with vascular lesions or brain atrophy, or require parameter tuning and are computationally expensive. Additionally, most algorithms do not generate a confidence estimate of segmentation quality, limiting their interpretation. MRI-based segmentation methods are often sensitive to acquisition protocols, scanners, noise-level, and image contrast, failing to generalize to other populations and out-of-distribution datasets. Given these concerns, we propose a novel Bayesian 3D convolutional neural network with a U-Net architecture that automatically segments WMH, provides uncertainty estimates of the segmentation output for quality control, and is robust to changes in acquisition protocols. We also provide a second model to differentiate deep and periventricular WMH. Four hundred thirty-two subjects were recruited to train the CNNs from four multisite imaging studies. A separate test set of 158 subjects was used for evaluation, including an unseen multisite study. We compared our model to two established state-of-the-art techniques (BIANCA and DeepMedic), highlighting its accuracy and efficiency. Our Bayesian 3D U-Net achieved the highest Dice similarity coefficient of 0.89 ± 0.08 and the lowest modified Hausdorff distance of 2.98 ± 4.40 mm. We further validated our models highlighting their robustness on "clinical adversarial cases" simulating data with low signal-to-noise ratio, low resolution, and different contrast (stemming from MRI sequences with different parameters). Our pipeline and models are available at: https://hypermapp3r.readthedocs.io.
| S-EPMC8996363 | biostudies-literature
Project description:Accurate, automated white matter hyperintensity (WMH) segmentations are needed for large-scale studies to understand contributions of WMH to neurological diseases. We evaluated Bayesian Model Selection (BaMoS), a hierarchical fully-unsupervised model selection framework for WMH segmentation. We compared BaMoS segmentations to semi-automated segmentations, and assessed whether they predicted longitudinal cognitive change in control, early Mild Cognitive Impairment (EMCI), late Mild Cognitive Impairment (LMCI), subjective/significant memory concern (SMC) and Alzheimer's (AD) participants. Data were downloaded from the Alzheimer's disease Neuroimaging Initiative (ADNI). Magnetic resonance images from 30 control and 30 AD participants were selected to incorporate multiple scanners, and were semi-automatically segmented by 4 raters and BaMoS. Segmentations were assessed using volume correlation, Dice score, and other spatial metrics. Linear mixed-effect models were fitted to 180 control, 107 SMC, 320 EMCI, 171 LMCI and 151 AD participants separately in each group, with the outcomes being cognitive change (e.g. mini-mental state examination; MMSE), and BaMoS WMH, age, sex, race and education used as predictors. There was a high level of agreement between BaMoS' WMH segmentation volumes and a consensus of rater segmentations, with a median Dice score of 0.74 and correlation coefficient of 0.96. BaMoS WMH predicted cognitive change in: control, EMCI, and SMC groups using MMSE; LMCI using clinical dementia rating scale; and EMCI using Alzheimer's disease assessment scale-cognitive subscale (p < 0.05, all tests). BaMoS compares well to semi-automated segmentation, is robust to different WMH loads and scanners, and can generate volumes which predict decline. BaMoS can be applicable to further large-scale studies.
| S-EPMC7338814 | biostudies-literature
Project description:Lacunes and white matter hyperintensities (WMHs) are features of cerebral small vessel disease (CSVD) that are associated with poor functional outcomes. However, how the two are related remains unclear. In this study, we examined the association between lacunes and several WMH features in patients with a history of vascular disease. A total of 999 patients (mean age 59 ± 10 years) with a 1.5 T brain magnetic resonance imaging (MRI) scan were included from the SMART-MR study. Lacunes were scored visually and WMH features (volume, subtype and shape) were automatically determined. Analyses consisted of linear and Poisson regression adjusted for age, sex, and total intracranial volume (ICV). Patients with lacunes (n = 188; 19%) had greater total (B = 1.03, 95% CI: 0.86 to 1.21), periventricular/confluent (B = 1.08, 95% CI: 0.89 to 1.27), and deep (B = 0.71, 95% CI: 0.44 to 0.97) natural log-transformed WMH volumes than patients without lacunes. Patients with lacunes had an increased risk of confluent type WMHs (RR = 2.41, 95% CI: 1.98 to 2.92) and deep WMHs (RR = 1.41, 95% CI: 1.22 to 1.62) and had a more irregular shape of confluent WMHs than patients without lacunes, independent of total WMH volume. In conclusion, we found that lacunes on MRI were associated with WMH features that correspond to more severe small vessel changes, mortality, and poor functional outcomes.
| S-EPMC6890997 | biostudies-literature
Project description:Accumulating evidence suggests associations between cerebrovascular disease (CVD) and Alzheimer's disease (AD). White matter hyperintensities of presumed vascular origin (WMHs) are increased in subjects with mild cognitive impairment (MCI) and AD, but the exact pathomechanistic link is unknown. The current study investigated effects of amyloid dysmetabolism on the microstructure of WMHs in subjects with MCI or subjective cognitive decline (N?=?51), dichotomized according to pathological or normal levels of amyloid-? peptide (A?42) in cerebrospinal fluid (CSF). Thirty-one subjects with low CSF A?42 (A?+) and 20 subjects with normal CSF A?42 (A?-) were assessed with magnetic resonance diffusion tensor imaging (DTI), and fractional anisotropy (FA), radial diffusivity (DR), axial diffusivity (DA), and mean diffusivity (MD) were determined. There were no significant differences in WMH volume or distribution between the groups, and neither age nor WMH volume had significant impact on the DTI indices. Nevertheless, there were significantly higher DA, DR, and MD in WMHs in A?+ relative to A?-; however, no differences in FA were found. The present results suggest that amyloid accumulation is associated with impaired structural integrity (e.g. relating to more extensive demyelination and loss of axons) in WMHs putatively adding to effects of ischemia.
| S-EPMC5363752 | biostudies-literature
Project description:ObjectiveBrain tissue segmentation by conventional threshold-based techniques may have limited accuracy and repeatability in older subjects. We present a new multispectral magnetic resonance (MR) image analysis approach for segmenting normal and abnormal brain tissue, including white matter lesions (WMLs).MethodsWe modulated two 1.5T MR sequences in the red/green colour space and calculated the tissue volumes using minimum variance quantisation. We tested it on 14 subjects, mean age 73.3 +/- 10 years, representing the full range of WMLs and atrophy. We compared the results of WML segmentation with those using FLAIR-derived thresholds, examined the effect of sampling location, WML amount and field inhomogeneities, and tested observer reliability and accuracy.ResultsFLAIR-derived thresholds were significantly affected by the location used to derive the threshold (P = 0.0004) and by WML volume (P = 0.0003), and had higher intra-rater variability than the multispectral technique (mean difference +/- SD: 759 +/- 733 versus 69 +/- 326 voxels respectively). The multispectral technique misclassified 16 times fewer WMLs.ConclusionInitial testing suggests that the multispectral technique is highly reproducible and accurate with the potential to be applied to routinely collected clinical MRI data.
| S-EPMC2882045 | biostudies-literature
Project description:IntroductionSubtle inhomogeneities in the scanner's magnetic fields (B0 and B1) alter the intensity levels of the structural magnetic resonance imaging (MRI) affecting the volumetric assessment of WMH changes. Here, we investigate the influence that (1) correcting the images for the B1 inhomogeneities (i.e. bias field correction (BFC)) and (2) selection of the WMH change assessment method can have on longitudinal analyses of WMH progression and discuss possible solutions.MethodsWe used brain structural MRI from 46 mild stroke patients scanned at stroke onset and 3 years later. We tested three BFC approaches: FSL-FAST, N4 and exponentially entropy-driven homomorphic unsharp masking (E(2)D-HUM) and analysed their effect on the measured WMH change. Separately, we tested two methods to assess WMH changes: measuring WMH volumes independently at both time points semi-automatically (MCMxxxVI) and subtracting intensity-normalised FLAIR images at both time points following image gamma correction. We then combined the BFC with the computational method that performed best across the whole sample to assess WMH changes.ResultsAnalysis of the difference in the variance-to-mean intensity ratio in normal tissue between BFC and uncorrected images and visual inspection showed that all BFC methods altered the WMH appearance and distribution, but FSL-FAST in general performed more consistently across the sample and MRI modalities. The WMH volume change over 3 years obtained with MCMxxxVI with vs. without FSL-FAST BFC did not significantly differ (medians(IQR)(with BFC) = 3.2(6.3) vs. 2.9(7.4)ml (without BFC), p = 0.5), but both differed significantly from the WMH volume change obtained from subtracting post-processed FLAIR images (without BFC)(7.6(8.2)ml, p < 0.001). This latter method considerably inflated the WMH volume change as subtle WMH at baseline that became more intense at follow-up were counted as increase in the volumetric change.ConclusionsMeasurement of WMH volume change remains challenging. Although the overall volumetric change was not significantly affected by the application of BFC, these methods distorted the image intensity distribution affecting subtle WMH. Subtracting the FLAIR images at both time points following gamma correction seems a promising technique but is adversely affected by subtle WMH. It is important to take into account not only the changes in volume but also in the signal intensity.
| S-EPMC4846712 | biostudies-literature