Program Description
MUlti-Scale multi-modal Image and omics Computing for health (MUSIC)” is a new interdisciplinary NSERC CREATE program that intends to respond to an acute need for a multi-faceted, data-driven approach to understanding the biological processes that lead to disease. Our goal with the program is to teach a multidisciplinary cohort of trainees from engineering, computer science, and medicine. MUSIC is a unique program in Canada that provides comprehensive training that integrates AI/machine learning skills with imaging and omics biological data across multiple scales and modalities.
Joining the Program
To make this program successful, we are prioritizing trainees (MASc and PhD students) who are undertaking interdisciplinary projects with multidisciplinary co-supervisors or collaborators. Please note that any interested Graduate students must be nominated for the program by their supervisors. Please reach out to your supervisor about nomination for the program.
Trainees will have a broad training experience including (a) getting familiar with various biomedical data types (at various scales) and how AI/machine learning could be utilized to analyze biomedical data, (b) industry or academic internships, and (c) professional development opportunities (including mentorship programs). Through the MUSIC program, we intend to create two graduate-level courses, outlined below. Note, the first cohort of the program (Jan 2024) will not be required (but encouraged) to take these courses. However, professional development and cohort activities as well as internships will be required to be fulfilled.
Program Details
MUSIC Program Graduate Student Awards
If a graduate student is selected as an awardee, they will receive $18,000 (MASc) or $27,000 (PhD) spread across two (MSc) or three (PhD) years. If the graduate student holds a major award/fellowship (e.g., NSERC CGS), MUSIC will top up to $30,000 (MASc) or $40,000 (PhD) for 1 year.
Graduate Student Program Requirements
1) Course 1: Biomedical Data Fundamentals (3 credits, course description below, hosted by SBME)*
2) Course 2: Machine Learning (ML) in Medicine (3 credits, course description below, hosted by SBME)*
*Note, the first cohort of the program (Jan 2024 intake) will not be required (but encouraged) to take these courses that will be offered in Sep 2024. Other course requirements are dictated by the home department where the trainee is doing their graduate studies.
In addition to the above, the trainees are required to participate in the following activities spread across their graduate program (total of 36 hours over the first two or three years of MSc or PhD programs):
3) Mentors program (minimum of 2 hours total of training)
4) Professional Craftsmanship (minimum of 12 hours total of training)
5) Training in EDI (minimum of 2 hours total of training)
6) Annual Showcase (1 per year; full day)
7) Ethics & Regulatory Workshops of AI in Medicine (minimum of 5 hours total of training)
8) Monthly Emerging Topics Lectures (minimum of 12 hours total of training)
9) Industry or academic internship (min. one per degree; 3-4 months)
Course 1) Biomedical Data Fundamentals: In this course, an overview of molecular, cellular and clinical imaging, and omics technologies and their relationship with each other will be covered. This new course will cover various biological or medical imaging and omics modalities, including the advantages and limitations of each technology, and provide awareness and understanding of how they are brought together in modern biomedical studies to capture data from micro to macro scales. The course will have three modules: Module 1: Modern Biomedical Multi-Modal Multi-Scale Studies, Module 2: Molecular & Cellular Imaging and Omics, Module 3: Clinical Imaging. As part of this course, we will introduce weekly student-driven “Discovery” sessions, where students come together for a deep dive into all facets of multi-modal multi-scale data in relation to a specific pathology, facilitated by one or more post-graduates and faculty. These sessions will provide opportunities for trainees to acquire collaboration, communication, and interdisciplinary problem-solving skills on top of technical competencies.
Course 2) Machine Learning (ML) in Medicine: A lecture and project-based course focused on applying ML techniques to solve real biomedical problems. Weekly “Discovery” sessions will continue in this course by bringing ML to multi-modal multi-scale data. In this course, the students will acquire hands-on experience with various data modalities and how ML can be applied to these data types.
Contact Us
If you have questions about this program or would like to learn more, please contact Dr. Ali Bashashati.