Marcille, M. | Search bioRxiv

bioRxiv2023

The sequence of regional structural disconnectivity due to multiple sclerosis lesions

ObjectivePrediction of disease progression is challenging in multiple sclerosis (MS) as the sequence of lesion development and retention of inflammation within a subset of chronic lesions is heterogeneous among patients. We investigated the sequence of lesion-related regional structural disconnectivity across the spectrum of disability and cognitive impairment in MS. MethodsIn a full cohort of 482 patients, the Expanded Disability Status Scale was used to classify patients into (i) no or mild vs (ii) moderate or severe disability groups. In 363 out of 482 patients, Quantitative Susceptibility Mapping was used to identify paramagnetic rim lesions (PRL), which are maintained by a rim of iron-laden innate immune cells. In 171 out of 482 patients, Brief International Cognitive Assessment was used to identify subjects with cognitive impairment. Network Modification Tool was used to estimate the regional structural disconnectivity due to MS lesions. Discriminative event-based modeling was applied to investigate the sequence of regional structural disconnectivity due to all representative lesions across the spectrum of disability and cognitive impairment. ResultsStructural disconnection in the ventral attention and subcortical networks was an early biomarker of moderate or severe disability. The earliest biomarkers of disability progression were structural disconnections due to PRL in the motor-related regions. Subcortical structural disconnection was an early biomarker of cognitive impairment. InterpretationMS lesion-related structural disconnections in the subcortex is an early biomarker for both disability and cognitive impairment in MS. PRL-related structural disconnection in the motor cortex may identify the patients at risk for moderate or severe disability in MS.

neuroscience↗

bioRxiv2022

QSMRim-Net: Imbalance-Aware Learning for Identification of Chronic Active Multiple Sclerosis Lesions on Quantitative Susceptibility Maps

Background and PurposeChronic active multiple sclerosis (MS) lesions are characterized by a paramagnetic rim at the edge of the lesion and are associated with increased disability in patients. Quantitative susceptibility mapping (QSM) is an MRI technique that is sensitive to chronic active lesions, termed rim+ lesions on the QSM. We present QSMRim-Net, a data imbalance-aware deep neural network that fuses lesion-level radiomic and convolutional image features for automated identification of rim+ lesions on QSM. MethodsQSM and T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRI of the brain were collected at 3T for 172 MS patients. Rim+ lesions were manually annotated by two human experts, followed by consensus from a third expert, for a total of 177 rim+ and 3986 rim negative (rim-) lesions. Our automated rim+ detection algorithm, QSMRim-Net, consists of a two-branch feature extraction network and a synthetic minority oversampling network to classify rim+ lesions. The first network branch is for image feature extraction from the QSM and T2-FLAIR, and the second network branch is a fully connected network for QSM lesion-level radiomic feature extraction. The oversampling network is designed to increase classification performance with imbalanced data. ResultsOn a lesion-level, in a five-fold cross validation framework, the proposed QSMRim-Net detected rim+ lesions with a partial area under the receiver operating characteristic curve (pROC AUC) of 0.760, where clinically relevant false positive rates of less than 0.1 were considered. The method attained an area under the precision recall curve (PR AUC) of 0.704. QSMRim-Net out-performed other state-of-the-art methods applied to the QSM on both pROC AUC and PR AUC. On a subject-level, comparing the predicted rim+ lesion count and the human expert annotated count, QSMRim-Net achieved the lowest mean square error of 0.98 and the highest correlation of 0.89 (95% CI: 0.86, 0.92). ConclusionThis study develops a novel automated deep neural network for rim+ MS lesion identification using T2-FLAIR and QSM images.

bioinformatics↗