McMedHacks – medical image analysis and deep learning in Python
Yujing and Luca both work on multi-modal image analysis using deep learning for various purposes from tumor auto-segmentation to outcome prediction using multiple diagnostic imaging modalities. They noticed that a few of their colleagues that were new to the field experienced some common challenges that they had experienced themselves: like how to work with DICOM files, getting started with practical deep learning programming in Python with little to no theory knowledge background and so on. This prompted them to establish a workshop series to help kickstart peoples’ research projects involving medical imaging analysis and deep learning. We quickly discovered that there was interest that far exceeded our lab group within the McGill community.
Our mission is to teach students and researchers new to the field the fundamentals of medical image analysis and deep learning in Python. McMedHacks is a program organized by students of Dr. Enger’s lab at McGill Medical Physics Unit and the Lady Davis Institute and consists of a workshop series and a hackathon.
Participants will learn how to
- process data in formats ranging from JPG images to DICOM files used in clinical settings
- analyze images from several imaging modalities such as pathology, endoscopy, and CT
- use both algorithmic and deep learning-based approaches to medical image analysis
- recognize and overcome common challenges associated with different imaging modalities and analysis methods
From June 12th – July 31st, we will be hosting a series of weekly keynotes and interactive workshops. Leading researchers in medical image analysis and deep learning will present their cutting-edge research to inspire and motivate students for the complimentary workshops.
Our interactive workshops will be instructed by current and former students with research experience in deep learning and medical image analysis. Each workshop will consist of:
- a classroom-style introduction to a new image analysis method and imaging modality
- an interactive demonstration of the newly learned skills
The workshops will be free. Due to COVID restrictions and for accessibility purposes, the workshops will be held entirely online, recorded, and made publicly available. Anyone from anywhere can join All demonstrations will be performed in Google Colab, which will allow anyone with internet access to perform complex computations on their machines regardless of hardware specifications.
To put the skills that participants learned during the workshops to the test, we will be hosting a hackathon in the first week of August. Participants will be asked to solve problems in medical image analysis using deep learning. The event will be held online and in-person optionally, if COVID restrictions allow. During the event, participants will receive mentorship from researchers and experienced students.