D. Peruzzo, Tommaso Ciceri, Sara Mascheretti, Valentina Lampis, Filippo Arrigoni, Nivedita Agarwal, Alice Giubergia, Filippo Maria Villa, Alessandro Crippa, Maria Nobile, Elisa Mani, Annamaria Russo, Maria Grazia D'Angelo
{"title":"Brain Alteration Patterns in Children with Duchenne Muscular Dystrophy: A Machine Learning Approach to Magnetic Resonance Imaging.","authors":"D. Peruzzo, Tommaso Ciceri, Sara Mascheretti, Valentina Lampis, Filippo Arrigoni, Nivedita Agarwal, Alice Giubergia, Filippo Maria Villa, Alessandro Crippa, Maria Nobile, Elisa Mani, Annamaria Russo, Maria Grazia D'Angelo","doi":"10.3233/JND-230075","DOIUrl":null,"url":null,"abstract":"Background\nDuchenne Muscular Dystrophy (DMD) is a genetic disease in which lack of the dystrophin protein causes progressive muscular weakness, cardiomyopathy and respiratory insufficiency. DMD is often associated with other cognitive and behavioral impairments, however the correlation of abnormal dystrophin expression in the central nervous system with brain structure and functioning remains still unclear.\n\n\nObjective\nTo investigate brain involvement in patients with DMD through a multimodal and multivariate approach accounting for potential comorbidities.\n\n\nMethods\nWe acquired T1-weighted and Diffusion Tensor Imaging data from 18 patients with DMD and 18 age- and sex-matched controls with similar cognitive and behavioral profiles. Cortical thickness, structure volume, fractional anisotropy and mean diffusivity measures were used in a multivariate analysis performed using a Support Vector Machine classifier accounting for potential comorbidities in patients and controls.\n\n\nResults\nthe classification experiment significantly discriminates between the two populations (97.2% accuracy) and the forward model weights showed that DMD mostly affects the microstructural integrity of long fiber bundles, in particular in the cerebellar peduncles (bilaterally), in the posterior thalamic radiation (bilaterally), in the fornix and in the medial lemniscus (bilaterally). We also reported a reduced cortical thickness, mainly in the motor cortex, cingulate cortex, hippocampal area and insula.\n\n\nConclusions\nOur study identified a small pattern of alterations in the CNS likely associated with the DMD diagnosis.","PeriodicalId":3,"journal":{"name":"ACS Applied Electronic Materials","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Electronic Materials","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3233/JND-230075","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Duchenne Muscular Dystrophy (DMD) is a genetic disease in which lack of the dystrophin protein causes progressive muscular weakness, cardiomyopathy and respiratory insufficiency. DMD is often associated with other cognitive and behavioral impairments, however the correlation of abnormal dystrophin expression in the central nervous system with brain structure and functioning remains still unclear.
Objective
To investigate brain involvement in patients with DMD through a multimodal and multivariate approach accounting for potential comorbidities.
Methods
We acquired T1-weighted and Diffusion Tensor Imaging data from 18 patients with DMD and 18 age- and sex-matched controls with similar cognitive and behavioral profiles. Cortical thickness, structure volume, fractional anisotropy and mean diffusivity measures were used in a multivariate analysis performed using a Support Vector Machine classifier accounting for potential comorbidities in patients and controls.
Results
the classification experiment significantly discriminates between the two populations (97.2% accuracy) and the forward model weights showed that DMD mostly affects the microstructural integrity of long fiber bundles, in particular in the cerebellar peduncles (bilaterally), in the posterior thalamic radiation (bilaterally), in the fornix and in the medial lemniscus (bilaterally). We also reported a reduced cortical thickness, mainly in the motor cortex, cingulate cortex, hippocampal area and insula.
Conclusions
Our study identified a small pattern of alterations in the CNS likely associated with the DMD diagnosis.