Discovering functional connectivity features characterizing multiple sclerosis phenotypes using explainable artificial intelligence

Yamin, Muhammad Abubakar; Valsasina, Paola; Tessadori, Jacopo; Filippi, Massimo; Murino, Vittorio; Rocca, Maria A.; Sona, Diego

doi:10.1002/hbm.26210

Cited by 4 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this regard, a recent paper exploited the patterns of brain functional connectivity derived from resting-state functional MRI to understand differences between relapsing and progressive forms of MS (Table 5). 46 To conclude, although the studies that have used AI to understand pathogenetic mechanisms in MS are still relatively few, they certainly contribute to a greater characterisation of MS by expanding the concept of classical phenotypes. Nonetheless, the integration with new quantitative MRI techniques that can show damage in apparently normal tissues, 47 even at very early disease stages, 48 would be necessary.…”

Section: Investigation Of Disease Mechanismsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Collorone,

Coll,

Lorenzi

et al. 2024

Mult Scler

View full text Add to dashboard Cite

Artificial intelligence (AI) is the branch of science aiming at creating algorithms able to carry out tasks that typically require human intelligence. In medicine, there has been a tremendous increase in AI applications thanks to increasingly powerful computers and the emergence of big data repositories. Multiple sclerosis (MS) is a chronic autoimmune condition affecting the central nervous system with a complex pathogenesis, a challenging diagnostic process strongly relying on magnetic resonance imaging (MRI) and a high and largely unexplained variability across patients. Therefore, AI applications in MS have the great potential of helping us better support the diagnosis, find markers for prognosis to eventually design more powerful randomised clinical trials and improve patient management in clinical practice and eventually understand the mechanisms of the disease. This topical review aims to summarise the recent advances in AI applied to MRI data in MS to illustrate its achievements, limitations and future directions.

show abstract

Section: Investigation Of Disease Mechanismsmentioning

confidence: 99%

Section: Investigation Of Disease Mechanismsmentioning

confidence: 99%

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Collorone,

Coll,

Lorenzi

et al. 2024

Mult Scler

View full text Add to dashboard Cite

show abstract

Discovering functional connectivity features characterizing multiple sclerosis phenotypes using explainable artificial intelligence

Yamin

Valsasina

Tessadori

et al. 2023

Human Brain Mapping

View full text Add to dashboard Cite

Multiple sclerosis (MS) is a neurological condition characterized by severe structural brain damage and by functional reorganization of the main brain networks that try to limit the clinical consequences of structural burden. Resting‐state (RS) functional connectivity (FC) abnormalities found in this condition were shown to be variable across different MS phases, according to the severity of clinical manifestations. The article describes a system exploiting machine learning on RS FC matrices to discriminate different MS phenotypes and to identify relevant functional connections for MS stage characterization. To this end, the system exploits some mathematical properties of covariance‐based RS FC representation, which can be described by a Riemannian manifold. The classification performance of the proposed framework was significantly above the chance level for all MS phenotypes. Moreover, the proposed system was successful in identifying relevant RS FC alterations contributing to an accurate phenotype classification.

show abstract

Cognitive rehabilitation effects on grey matter volume and Go-NoGo activity in progressive multiple sclerosis: results from the CogEx trial

Rocca,

Valsasina,

Romanò

et al. 2024

J Neurol Neurosurg Psychiatry

View full text Add to dashboard Cite

BackgroundResearch on cognitive rehabilitation (CR) and aerobic exercise (EX) to improve cognition in progressive multiple sclerosis (PMS) remains limited. CogEx trial investigated the effectiveness of CR and EX in PMS: here, we present MRI substudy volumetric and task-related functional MRI (fMRI) findings.MethodsParticipants were randomised to: ‘CR plus EX’, ‘CR plus sham EX (EX-S)’, ‘EX plus sham CR (CR-S)’ and ‘CR-S plus EX-S‘ and attended 12-week intervention. All subjects performed physical/cognitive assessments at baseline, week 12 and 6 months post intervention (month 9). All MRI substudy participants underwent volumetric MRI and fMRI (Go-NoGo task).Results104 PMS enrolled at four sites participated in the CogEx MRI substudy; 84 (81%) had valid volumetric MRI and valid fMRI. Week 12/month 9 cognitive performances did not differ among interventions; however, 25–62% of the patients showed Symbol Digit Modalities Test improvements. Normalised cortical grey matter volume (NcGMV) changes at week 12 versus baseline were heterogeneous among interventions (p=0.05); this was mainly driven by increased NcGMV in ‘CR plus EX-S’ (p=0.02). Groups performing CR (ie, ‘CR plus EX’ and ‘CR plus EX-S’) exhibited increased NcGMV over time, especially in the frontal (p=0.01), parietal (p=0.04) and temporal (p=0.04) lobes, while those performing CR-S exhibited NcGMV decrease (p=0.008). In CR groups, increased NcGMV (r=0.36, p=0.01) at week 12 versus baseline correlated with increased California Verbal Learning Test (CVLT)-II scores. ‘CR plus EX-S’ patients exhibited Go-NoGo activity increase (p<0.05, corrected) at week 12 versus baseline in bilateral insula.ConclusionsIn PMS, CR modulated grey matter (GM) volume and insular activity. The association of GM and CVLT-II changes suggests GM plasticity contributes to cognitive improvements.Trial registration numberNCT03679468.

show abstract

Discovering functional connectivity features characterizing multiple sclerosis phenotypes using explainable artificial intelligence

Cited by 4 publications

References 53 publications

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Discovering functional connectivity features characterizing multiple sclerosis phenotypes using explainable artificial intelligence

Cognitive rehabilitation effects on grey matter volume and Go-NoGo activity in progressive multiple sclerosis: results from the CogEx trial

Contact Info

Product

Resources

About