Detection of diffusely abnormal white matter in multiple sclerosis on multiparametric brain MRI using semi-supervised deep learning

In addition to focal lesions, diffusely abnormal white matter (DAWM) is seen on brain MRI of multiple sclerosis (MS) patients and may represent early or distinct disease processes. The role of MRI-observed DAWM is understudied due to a lack of automated assessment methods. Supervised deep learning (DL) methods are highly capable in this domain, but require large sets of labeled data. To overcome this challenge, a DL-based network (DAWM-Net) was trained using semi-supervised learning on a limited set of labeled data for segmentation of DAWM, focal lesions, and normal-appearing brain tissues on multiparametric MRI. DAWM-Net segmentation performance was compared to a previous intensity thresholding-based method on an independent test set from expert consensus (N = 25). Segmentation overlap by Dice Similarity Coefficient (DSC) and Spearman correlation of DAWM volumes were assessed. DAWM-Net showed DSC > 0.93 for normal-appearing brain tissues and DSC > 0.81 for focal lesions. For DAWM-Net, the DAWM DSC was 0.49 ± 0.12 with a moderate volume correlation (ρ = 0.52, p < 0.01). The previous method showed lower DAWM DSC of 0.26 ± 0.08 and lacked a significant volume correlation (ρ = 0.23, p = 0.27). These results demonstrate the feasibility of DL-based DAWM auto-segmentation with semi-supervised learning. This tool may facilitate future investigation of the role of DAWM in MS.

Micro-diffusely abnormal white matter: An early multiple sclerosis lesion phase with intensified myelin blistering

OBJECTIVE

Multiple sclerosis (MS) is a chronic central nervous system disease whose white matter lesion origin remains debated. Recently, we reported subtle changes in the MS normal appearing white matter (NAWM), presenting with an increase in myelin blisters and myelin protein citrullination, which may recapitulate some of the prodromal degenerative processes involved in MS pathogenesis. Here, to clarify the relevance of these changes for subsequent MS myelin degeneration we explored their prevalence in WM regions characterized by subtly reduced myelination (dubbed as micro-diffusely abnormal white matter, mDAWM).

METHODS

We used an in-depth (immuno)histochemistry approach in 27 MS donors with histological presence of mDAWM and 5 controls. An antibody panel against degenerative markers was combined and the presence of myelin/axonal aberrations was analyzed and compared with the NAWM from the same cases/slices/regions.

RESULTS

mDAWM-defined areas exhibit ill-defined borders, no signs of Wallerian degeneration, and they associate with visible veins. Remarkably, such areas present with augmented myelin blister frequency, enhanced prevalence of polar myelin phospholipids, citrullination, and degradation of myelin basic protein (MBP) when compared with the NAWM. Furthermore, enhanced reactivity of microglia/macrophages against citrullinated MBP was also observed in this tissue.

INTERPRETATION

We report a new histologically defined early phase in MS lesion formation, namely mDAWM, which lacks signs of Wallerian pathology. These results support the prelesional nature of the mDAWM. We conceptualize that evolution to pathologically evident lesions comprises the previously documented imbalance of axo-myelinic units (myelin blistering) leading to their degeneration and immune system activation by released myelin components.

Intensity scaling of conventional brain magnetic resonance images avoiding cerebral reference regions: A systematic review

BACKGROUND

Conventional brain magnetic resonance imaging (MRI) produces image intensities that have an arbitrary scale, hampering quantification. Intensity scaling aims to overcome this shortfall. As neurodegenerative and inflammatory disorders may affect all brain compartments, reference regions within the brain may be misleading. Here we summarize approaches for intensity scaling of conventional T1-weighted (w) and T2w brain MRI avoiding reference regions within the brain.

METHODS

Literature was searched in the databases of Scopus, PubMed, and Web of Science. We included only studies that avoided reference regions within the brain for intensity scaling and provided validating evidence, which we divided into four categories: 1) comparative variance reduction, 2) comparative correlation with clinical parameters, 3) relation to quantitative imaging, or 4) relation to histology.

RESULTS

Of the 3825 studies screened, 24 fulfilled the inclusion criteria. Three studies used scaled T1w images, 2 scaled T2w images, and 21 T1w/T2w-ratio calculation (with double counts). A robust reduction in variance was reported. Twenty studies investigated the relation of scaled intensities to different types of quantitative imaging. Statistically significant correlations with clinical or demographic data were reported in 8 studies. Four studies reporting the relation to histology gave no clear picture of the main signal driver of conventional T1w and T2w MRI sequences.

CONCLUSIONS

T1w/T2w-ratio calculation was applied most often. Variance reduction and correlations with other measures suggest a biologically meaningful signal harmonization. However, there are open methodological questions and uncertainty on its biological underpinning. Validation evidence on other scaling methods is even sparser.

Distinct hemodynamic and functional connectivity features of fatigue in clinically isolated syndrome and multiple sclerosis: accounting for the confounding effect of concurrent depression symptoms

PURPOSE

This study aims to identify common and distinct hemodynamic and functional connectivity (FC) features for self-rated fatigue and depression symptoms in patients with clinically isolated syndrome (CIS) and relapsing-remitting multiple sclerosis (RR-MS).

METHODS

Twenty-four CIS, 29 RR-MS patients, and 39 healthy volunteers were examined using resting-state fMRI (rs-fMRI) to obtain whole-brain maps of (i) hemodynamic response patterns (through time shift analysis), (ii) FC (via intrinsic connectivity contrast maps), and (iii) coupling between hemodynamic response patterns and FC. Each regional map was correlated with fatigue scores, controlling for depression, and with depression scores, controlling for fatigue.

RESULTS

In CIS patients, the severity of fatigue was associated with accelerated hemodynamic response in the insula, hyperconnectivity of the superior frontal gyrus, and evidence of reduced hemodynamics-FC coupling in the left amygdala. In contrast, depression severity was associated with accelerated hemodynamic response in the right limbic temporal pole, hypoconnectivity of the anterior cingulate gyrus, and increased hemodynamics-FC coupling in the left amygdala. In RR-MS patients, fatigue was associated with accelerated hemodynamic response in the insula and medial superior frontal cortex, increased functional role of the left amygdala, and hypoconnectivity of the dorsal orbitofrontal cortex, while depression symptom severity was linked to delayed hemodynamic response in the medial superior frontal gyrus; hypoconnectivity of the insula, ventromedial thalamus, dorsolateral prefrontal cortex, and posterior cingulate; and decreased hemodynamics-FC coupling of the medial orbitofrontal cortex.

CONCLUSION

There are distinct FC and hemodynamic responses, as well as different magnitude and topography of hemodynamic connectivity coupling, associated with fatigue and depression in early and later stages of MS.

DARQ: Deep learning of quality control for stereotaxic registration of human brain MRI to the T1w MNI-ICBM 152 template

Linear registration to stereotaxic space is a common first step in many automated image-processing tools for analysis of human brain MRI scans. This step is crucial for the success of the subsequent image-processing steps. Several well-established algorithms are commonly used in the field of neuroimaging for this task, but none have a 100% success rate. Manual assessment of the registration is commonly used as part of quality control. To reduce the burden of this time-consuming step, we propose Deep Automated Registration Qc (DARQ), a fully automatic quality control method based on deep learning that can replace the human rater and accurately perform quality control assessment for stereotaxic registration of T1w brain scans. In a recently published study from our group comparing linear registration methods, we used a database of 9325 MRI scans and 64476 registrations from several publicly available datasets and applied seven linear registration tools to them. In this study, the resulting images that were assessed and labeled by a human rater are used to train a deep neural network to detect cases when registration failed. We further validated the results on an independent dataset of patients with multiple sclerosis, with manual QC labels available (n=1200). In terms of agreement with a manual rater, our automated QC method was able to achieve 89% accuracy and 85% true negative rate (equivalently 15% false positive rate) in detecting scans that should pass quality control in a balanced cross-validation experiments, and 96.1% accuracy and 95.5% true negative rate (or 4.5% FPR) when evaluated in a balanced independent sample, similar to manual QC rater (test-retest accuracy of 93%). The results show that DARQ is robust, fast, accurate, and generalizable in detecting failure in linear stereotaxic registrations and can substantially reduce QC time (by a factor of 20 or more) when processing large datasets.

Automatic segmentation of white matter hyperintensities: validation and comparison with state-of-the-art methods on both Multiple Sclerosis and elderly subjects

•

Automatic segmentation of MS lesions and age-related WMH from 3D T1 and T2-FLAIR.

•

Comparison to consensus show improved performance of WHASA-3D compared to WHASA.

•

WHASA-3D outperforms available state-of-the-art methods with their default settings.

•

WHASA-3D could be a useful tool for clinical practice and clinical trials.

Different types of white matter hyperintensities (WMH) can be observed through MRI in the brain and spinal cord, especially Multiple Sclerosis (MS) lesions for patients suffering from MS and age-related WMH for subjects with cognitive disorders and/or elderly people. To better diagnose and monitor the disease progression, the quantitative evaluation of WMH load has proven to be useful for clinical routine and trials. Since manual delineation for WMH segmentation is highly time-consuming and suffers from intra and inter observer variability, several methods have been proposed to automatically segment either MS lesions or age-related WMH, but none is validated on both WMH types. Here, we aim at proposing the White matter Hyperintensities Automatic Segmentation Algorithm adapted to 3D T2-FLAIR datasets (WHASA-3D), a fast and robust automatic segmentation tool designed to be implemented in clinical practice for the detection of both MS lesions and age-related WMH in the brain, using both 3D T1-weighted and T2-FLAIR images. In order to increase its robustness for MS lesions, WHASA-3D expands the original WHASA method, which relies on the coupling of non-linear diffusion framework and watershed parcellation, where regions considered as WMH are selected based on intensity and location characteristics, and finally refined with geodesic dilation. The previous validation was performed on 2D T2-FLAIR and subjects with cognitive disorders and elderly subjects. 60 subjects from a heterogeneous database of dementia patients, multiple sclerosis patients and elderly subjects with multiple MRI scanners and a wide range of lesion loads were used to evaluate WHASA and WHASA-3D through volume and spatial agreement in comparison with consensus reference segmentations. In addition, a direct comparison on the MS database with six available supervised and unsupervised state-of-the-art WMH segmentation methods (LST-LGA and LPA, Lesion-TOADS, lesionBrain, BIANCA and nicMSlesions) with default and optimised settings (when feasible) was conducted. WHASA-3D confirmed an improved performance with respect to WHASA, achieving a better spatial overlap (Dice) (0.67 vs 0.63), a reduced absolute volume error (AVE) (3.11 vs 6.2 mL) and an increased volume agreement (intraclass correlation coefficient, ICC) (0.96 vs 0.78). Compared to available state-of-the-art algorithms on the MS database, WHASA-3D outperformed both unsupervised and supervised methods when used with their default settings, showing the highest volume agreement (ICC = 0.95) as well as the highest average Dice (0.58). Optimising and/or retraining LST-LGA, BIANCA and nicMSlesions, using a subset of the MS database as training set, resulted in improved performances on the remaining testing set (average Dice: LST-LGA default/optimized = 0.41/0.51, BIANCA default/optimized = 0.22/0.39, nicMSlesions default/optimized = 0.17/0.63, WHASA-3D = 0.58). Evaluation and comparison results suggest that WHASA-3D is a reliable and easy-to-use method for the automated segmentation of white matter hyperintensities, for both MS lesions and age-related WMH. Further validation on larger datasets would be useful to confirm these first findings.

Diffusely abnormal white matter converts to T2 lesion volume in the absence of MRI-detectable acute inflammation

Diffusely abnormal white matter (DAWM), characterised by biochemical changes of myelin in the absence of frank demyelination, has been associated with clinical progression in secondary progressive MS (SPMS). However, little is known about changes of DAWM over time and their relation to focal white matter lesions (FWML).

The objectives of this work were: 1) To characterize the longitudinal evolution of FWML, DAWM, and DAWM that transforms into FWML, and 2) To determine whether gadolinium enhancement, known to be associated with the development of new FWML, is also related to DAWM voxels that transform into FWML.

Our data included 4220 MRI scans of 689 SPMS participants, followed for 156 weeks and 2677 scans of 686 RRMS participants, followed for 96 weeks. FWML and DAWM were segmented using a previously validated, automatic thresholding technique based on normalized T2 intensity values. Using longitudinally registered images, DAWM voxels at each visit that transformed into FWML on the last MRI scan as well as their overlap with gadolinium enhancing lesion masks were identified.

Our results showed that the average yearly rate of conversion of DAWM-to-FWML was 1.27 cc for SPMS and 0.80 cc for RRMS. FWML in SPMS participants significantly increased (t = 3.9; p = 0.0001) while DAWM significantly decreased (t = −4.3 p &lt; 0.0001) and the ratio FWML:DAWM increased (t = 12.7; p &lt; 0.00001). RRMS participants also showed an increase in the FWML:DAWM Ratio (t = 6.9; p &lt; 0.00001) but without a significant change of the individual volumes. Gadolinium enhancement was associated with 7.3% and 18.7% of focal New T2 lesion formation in the infrequent scans of the RRMS and SPMS cohorts, respectively. In comparison, only 0.1% and 0.0% of DAWM-to-FWML voxels overlapped with gadolinium enhancement.

We conclude that DAWM transforms into FWML over time, in both RRMS and SPMS. DAWM appears to represent a form of pre-lesional pathology that contributes to T2 lesion volume increase over time, independent of new focal inflammation and gadolinium enhancement.

Diffusely abnormal white matter in clinically isolated syndrome is associated with parenchymal loss and elevated neurofilament levels

We characterized the frequency of diffusely abnormal white matter (DAWM) across a broad spectrum of multiple sclerosis (MS) participants. 35% of clinically isolated syndrome (CIS), 57% of relapsing remitting and 64% of secondary progressive MS participants demonstrated DAWM. CIS with DAWM had decreased cortical thickness, higher lesion load and a higher concentration of serum neurofilament light chain compared to CIS without DAWM. DAWM may be useful in identifying CIS patients with greater injury to their brains. Larger and longitudinal studies are warranted.

Diffusely abnormal white matter in multiple sclerosis

MRI enables detailed in vivo depiction of multiple sclerosis (MS) pathology. Localized areas of MS damage, commonly referred to as lesions, or plaques, have been a focus of clinical and research MRI studies for over four decades. A nonplaque MRI abnormality which is present in at least 25% of MS patients but has received far less attention is diffusely abnormal white matter (DAWM). DAWM has poorly defined boundaries and a signal intensity that is between normal-appearing white matter and classic lesions on proton density and T₂ -weighted images. All clinical phenotypes of MS demonstrate DAWM, including clinically isolated syndrome, where DAWM is associated with higher lesion volume, reduced brain volume, and earlier conversion to MS. Advanced MRI metric abnormalities in DAWM tend to be greater than those in NAWM, but not as severe as focal lesions, with myelin, axons, and water-related changes commonly reported. Histological studies demonstrate a primary lipid abnormality in DAWM, with some axonal damage and lesser involvement of myelin proteins. This review provides an overview of DAWM identification, summarizes in vivo and postmortem observations, and comments on potential pathophysiological mechanisms, which may underlie DAWM in MS. Given the prevalence and potential clinical impact of DAWM, the number of imaging studies focusing on DAWM is insufficient. Characterization of DAWM significance and microstructure would benefit from larger longitudinal and additional quantitative imaging efforts. Revisiting data from previous studies that included proton density and T₂ imaging would enable retrospective DAWM identification and analysis.

Nonlesional diffusely abnormal appearing white matter in clinically isolated syndrome: Prevalence, association with clinical and MRI features, and risk for conversion to multiple sclerosis

BACKGROUND AND PURPOSE

While diffusely abnormal white matter (DAWM) is a nonlesional MRI abnormality identified in ∼25% of patients with multiple sclerosis (MS), it has yet to be investigated in patients at an earlier disease stage, namely clinically isolated syndrome (CIS). The goals of this study were to (1) determine the prevalence of DAWM in patients with a CIS suggestive of MS, (2) evaluate the association between DAWM and demographic, clinical, and MRI features, and (3) evaluate the prognostic significance of DAWM on conversion from CIS to MS.

METHODS

One hundred and forty-two CIS participants were categorized into DAWM and non-DAWM groups at baseline and followed for up to 24 months or until MS diagnosis. The primary outcome was conversion to MS (2005 McDonald criteria) within 6 months.

RESULTS

DAWM was present in 27.5% of participants, and was positively associated with brainstem symptom onset, receiving corticosteroids, dissemination in space, and T₂ lesion volume. DAWM was associated with an increased risk of conversion to MS over 6 months after adjustment for age and disability (hazard ratio [HR] = 2.24, p = 0.004). This association remained at a trend-level after adjustment for high-risk imaging features (HR = 1.68, p = 0.10).

CONCLUSIONS

DAWM is present in a similar proportion of patients with CIS and clinically definite MS, and it is associated with increased risk of conversion to MS over 6 months.

T2 Relaxometry Evidence of Microstructural Changes in Diffusely Abnormal White Matter in Relapsing-Remitting Multiple Sclerosis and Clinically Isolated Syndrome: Impact on Visuomotor Performance

BACKGROUND

Although diffusely abnormal white matter (DAWM) is commonly seen in multiple sclerosis (MS), it is rarely considered in clinical/imaging studies.

PURPOSE

To evaluate quantitative markers of microstructural changes in DAWM of patients with clinically isolated syndrome (CIS) and relapsing-remitting MS (RR-MS) in relation to MS lesions and degree of neurocognitive impairment, by using a multi-echo spin echo (MESE) Proton Density PD-to-T2 sequence.

STUDY TYPE

Prospective, cross-sectional.

POPULATION

Thirty-seven RR-MS patients, 33 CIS patients, and 52 healthy controls.

FIELD STRENGTH/SEQUENCE

1.5 T/T1-, T2-weighted, fluid-attenuated inversion recovery, and MESE sequences.

ASSESSMENT

Long T2, short T2, and myelin water fraction (MWF) values were estimated as indices of intra/extracellular water content and myelin content, respectively, in DAWM, posterior periventricular normal appearing white matter (NAWM), and focal MS lesions, classified according to their signal intensity on T1 sequences. Patients were, also, administered a battery of neuropsychological tests.

STATISTICAL TESTS

Comparisons of T2 and MWF values in DAWM, NAWM, and MS lesions were examined, using two-way mixed analyses of variance. Associations of Grooved Pegboard performance with T2 and MWF values in DAWM and NAWM were assessed using Pearson correlation coefficients.

RESULTS

T2 and MWF values of DAWM were intermediate between the respective values of NAWM and T1 hypointense focal lesions, while there was no difference between the respective values of DAWM and T1-isointense lesions. T2 values in DAWM were strongly associated with visuomotor performance in CIS patients.

DATA CONCLUSION

Intra/extracellular water and myelin water content of DAWM are similar to those of T1-isointense lesions and predict visuomotor performance in CIS patients.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 2.