Meeting Banner
Abstract #3583

Integrating BMAT and FA Imaging for Improved Classification of Multiple Sclerosis: A Machine Learning Perspective

Cristian Montalba1,2,3, Pamela Franco4, Raúl Caulier-Cisterna5, Macarena Vasquez6, Claudia Cárcamo7,8, Ethel Ciampi7,9, and Marcelo Andia1,3,10
1Biomedical Imaging Center, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile., Santiago, Chile, 2Instituto Milenio Intelligent Healthcare Engineering, Santiago, Chile, 3Radiology Department, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile., Santiago, Chile, 4Universidad Andrés Bello, Energy Transformation Center, Faculty of Engineering, Santiago, Chile, 5Department of Informatics and Computing, Faculty of Engineering, Universidad Tecnológica Metropolitana, Santiago, Chile., Santiago, Chile, 6Multiple Sclerosis Program, Faculty of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile., Santiago, Chile, 7Neurology Department, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile., Santiago, Chile, 8Interdisciplinary Center of Neurosciences, Pontificia Universidad Católica de Chile, Santiago, Chile., Santiago, Chile, 9Neurology Service, Hospital Dr. Sótero del Río, Santiago, Chile, Santiago, Chile, 10Instituto Milenio Intelligent Healthcare Engineering, Santiago, Chile., Santiago, Chile

Synopsis

Keywords: Multiple Sclerosis, Multiple Sclerosis, AI

Motivation: This research aims to improve early diagnosis and treatment of MS by integrating cognitive assessment and advanced neuroimaging techniques with machine learning.

Goal(s): The goal is to enhance MS classification accuracy by integrating cognitive metrics and neuroimaging data using machine learning algorithms.

Approach: This study employs a collaborative approach, combining cognitive assessments, neuroimaging data, and machine learning to classify cognitive changes in MS.

Results: The machine learning model achieved an accuracy of 80.89% in classifying MS patients, effectively distinguishing between cognitively preserved and impaired groups based on critical neuroanatomical features identified from imaging data.

Impact: This study enhances diagnostic precision for MS, facilitating early intervention and personalized treatment strategies. It encourages further exploration of cognitive decline mechanisms in MS and may inspire similar integrative approaches in other neurological disorders, ultimately improving patient outcomes.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords