Using multivariate deep-learning algorithms for automatic quality control of high-resolution MRI

NeuroRx is an imaging contract research organization (CRO) specialized in the central nervous system (CNS) that utilizes state-of-the-art digital image processing techniques to produce accurate and precise outcome measures for clinical trials of drugs in development. Prior to analysis, all scans must pass Quality Control (QC). The goal of this project will be to incorporate advanced computer algorithms to automatically classify the quality of high-resolution structural brain Magnetic Resonance Images. The advanced computer algorithms will include deep learning algorithms. Developing an automated algorithm to realize this time-consuming procedure can help companies save time and increase efficiency. NeuroRx will provide thousands of QC’d scans for algorithm training, and benefit from the most technologically advanced concepts and resources developed at a world-renowned institution, the Neuro at McGill.

Faculty Supervisor:

Amir Shmuel

Student:

Ricardo Pizarro

Partner:

NeuroRx Research Inc.

Discipline:

Engineering - biomedical

Sector:

Medical devices

University:

Program: