Opportunities for Understanding MS Mechanisms and Progression With MRI Using Large-Scale Data Sharing and Artificial Intelligence

Abstract

Multiple sclerosis (MS) patients have heterogeneous clinical presentations, symptoms and progression over time, making MS difficult to assess and comprehend in vivo. The combination of large-scale data-sharing and artificial intelligence creates new opportunities for monitoring and understanding MS using magnetic resonance imaging (MRI).First, development of validated MS-specific image analysis methods can be boosted by verified reference, test and benchmark imaging data. Using detailed expert annotations, artificial intelligence algorithms can be trained on such MS-specific data. Second, understanding disease processes could be greatly advanced through shared data of large MS cohorts with clinical, demographic and treatment information. Relevant patterns in such data that may be imperceptible to a human observer could be detected through artificial intelligence techniques. This applies from image analysis (lesions, atrophy or functional network changes) to large multi-domain datasets (imaging, cognition, clinical disability, genetics, etc.).After reviewing data-sharing and artificial intelligence, this paper highlights three areas that offer strong opportunities for making advances in the next few years: crowdsourcing, personal data protection, and organized analysis challenges. Difficulties as well as specific recommendations to overcome them are discussed, in order to best leverage data sharing and artificial intelligence to improve image analysis, imaging and the understanding of MS.

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

“…However, these techniques may affect the succeeding image analysis. Consequently, protecting patients’ privacy while collecting their information continues to be a major challenge that needs to be addressed appropriately [ 110 ].…”

Task- and resting-state fMRI studies in multiple sclerosis: From regions to systems and time-varying analysis. Current status and future perspective

“…In particular, machine learning and deep learning techniques have been successfully employed for a variety of tasks, including lesion and brain tissue segmentation, analysis of different MRI data modalities, differential diagnosis with other white matter disorders and disease prognosis. ( Vrenken et al, 2021 ) To date, most of studies applying AI to MRI data in MS used T2- and T1-weighted imaging, or advanced structural MRI techniques, such as susceptibility-weighted and diffusion-weighted imaging. ( Vrenken et al, 2021 , Moazami et al, 2021 ) Nevertheless, recent investigations showed promising results also when applying AI to fMRI data.…”

“…( Vrenken et al, 2021 ) To date, most of studies applying AI to MRI data in MS used T2- and T1-weighted imaging, or advanced structural MRI techniques, such as susceptibility-weighted and diffusion-weighted imaging. ( Vrenken et al, 2021 , Moazami et al, 2021 ) Nevertheless, recent investigations showed promising results also when applying AI to fMRI data. For instance, Saccà et al ( Saccà et al, 2019 ) applied five different machine learning techniques to maps of the sensorimotor network (reconstructed by independent component analysis) in 18 people with early MS and 19 HC.…”

Artificial Intelligence and Multiple Sclerosis: Up-to-Date Review

“…AI and large-scale data sharing could easily predict the progression of MS, which is crucial for treatment planning and optimizing patient outcomes [ 61 , 62 ]. It covers a large field from MRI image analysis “T2-fluid-attenuated inversion recovery (FLAIR), 2D T1-weighted images (WI), 3D T1-WI, diffusion tensor imaging, and functional magnetic resonance imaging” to large multidomain datasets [ 61 , 63 ].…”