Contrast/modality-invariant anatomical recognition in clinical scans for multiple sclerosis study

Multiple sclerosis (MS) is a chronic and progressive autoimmune disease that affects the central nervous system (CNS), including the brain and the spinal cord. In MS, the immune system attacks the myelin that covers the neuronal fibers, resulting in inflammation and damage of CNS that leads to a wide range of symptoms concerning movement, sensation, and cognition. Big data analysis with multi-contrast/modality medical imaging can help improve our understanding of the disease. However, when collecting multi-centre clinical brain and spinal cord scans of MS patients, the file names are usually uninformative for the anatomy within the scan, making manual data organization for downstream analysis time-consuming. To tackle these challenges, the project will develop a new algorithm using few-shot learning to allow contrast-invariant anatomical identification. The resulting algorithm can greatly improve the efficiency of data collection and organization for the study of MS and biomarker discovery.

Faculty Supervisor:

Yiming Xiao

Student:

Partner:

NeuroRx Solutions Inc

Discipline:

Computer science

Sector:

Health and Related Sciences & Technology; Professional, scientific and technical services

University:

Concordia University

Program: