ObjectivesMagnetic resonance imaging (MRI) is an important tool for diagnosis and monitoring of disease course in multiple sclerosis (MS). However, its prognostic value for predicting disease worsening is still being debated. The aim of this study was to propose a deep learning algorithm to predict disease worsening at 2 years of follow-up on a multicenter cohort of MS patients collected from the Italian Neuroimaging Network Initiative using baseline MRI, and compare it with 2 expert physicians.Materials and MethodsFor 373 MS patients, baseline T2-weighted and T1-weighted brain MRI scans, as well as baseline and 2-year clinical and cognitive assessments, were collected from the Italian Neuroimaging Network Initiative repository. A deep learning architecture based on convolutional neural networks was implemented to predict: (1) clinical worsening (Expanded Disability Status Scale [EDSS]–based model), (2) cognitive deterioration (Symbol Digit Modalities Test [SDMT]–based model), or (3) both (EDSS + SDMT–based model). The method was tested on an independent data set and compared with the performance of 2 expert physicians.ResultsFor the test set, the convolutional neural network model showed high predictive accuracy for clinical (83.3%) and cognitive (67.7%) worsening, although the highest accuracy was reached when training the algorithm using both EDSS and SDMT information (85.7%). Artificial intelligence classification performance exceeded that of 2 expert physicians (70% of accuracy for the human raters).ConclusionsWe developed a robust and accurate model for predicting clinical and cognitive worsening of MS patients after 2 years, based on conventional T2-weighted and T1-weighted brain MRI scans obtained at baseline. This algorithm may be valuable for supporting physicians in their clinical practice for the earlier identification of MS patients at risk of disease worsening.
BackgroundChoroid plexus (CP) enlargement has been suggested as a reliable marker of neuroinflammation in adult multiple sclerosis (MS). We investigated CP volume in patients with paediatric MS compared with matched healthy controls (HC), possible sex-related effect, and the associations with clinical and structural MRI variables.MethodsBrain 3.0 T dual-echo and three-dimensional (3D) T1-weighted sequences were selected retrospectively from 69 patients with paediatric MS and 23 age-matched and sex-matched HC. CP volume was manually obtained from 3D T1-weighted scans by two expert raters.ResultsCP segmentation was highly reproducible (intraobserver agreement: rater I=0.963, rater II=0.958; interobserver agreement=0.968). Compared with HC, patients with paediatric MS showed higher normalised CP volume (p<0.001). Both female and male patients with paediatric MS showed higher normalised CP volume compared with sex-matched HC (women: p<0.001 and men: p=0.021), with a significant disease×sex interaction (p=0.040). In patients with MS, a higher normalised CP volume was significantly associated with higher brain lesional volume (β=0.252, p=0.017), larger lateral ventricle volume (β=0.470, false discovery rate (FDR)-p<0.001), lower normalised brain volume (β=−0.413, FDR-p=0.002) and lower normalised thalamic volume (β=0.291, FDR-p=0.046). No associations with disease duration, Expanded Disability Status Scale score, normalised cortical and white matter volumes were found (FDR-p≥0.172). A significant effect of the disease in the negative association between normalised volumes of CP and thalami was observed (FDR-p=0.046).ConclusionsCP enlargement occurs in paediatric MS, suggesting its early involvement in the pathophysiology of the disease. The higher CP volume, which is found especially in female patients, supports the hypothesis of sex-related differences occurring already in paediatric MS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.