Supervisor: Michelle Noga
Project: Computer aided pattern recognition in medical imaging: Application in the cardiac catheterization laboratory
Doctor of Medicine
Why did you choose this program?
In retrospect, studying medicine is what I always imagined I would do, I just took an indirect path to getting here today. I really appreciate the opportunity to be a lifelong learner and to dedicate to a profession that strongly encourages constant development with the opportunity for practical application to the real world.
What was it like to continue your research project when much of the country was in a lockdown or faced major restrictions?
To be honest, I was very fortunate to have the opportunity to continue working on my project this summer, almost entirely uninterrupted. Working in a fully digital environment, you definitely miss out on the social experience of working in a lab and getting to know the other students. However, with a little creativity, the experience has still been great!
What's been the best part of your experience so far?
I have been able to apply skills and knowledge that come from my background as an engineer to medical research in the field that I hope to work in for my future career. It has been an incredible opportunity to find a project that motivated me to learn new things that I had been interested in for a long time. It's been great to see that some of the things I learned in my previous career are very relevant to my current studies and future!
How has your studentship helped you towards your career aspirations?
This studentship allowed me to engage in a research project in the specific field that I am currently interested in for my future career as a physician. One of the most important steps of medical school is career exploration and trying to determine the specific field of practice that you would like to go into. I honestly feel that involvement in a research project is the best way to do this by allowing you to obtain more meaningful and longitudinal experience.
What has the support from WCHRI and the Stollery Children's Hospital Foundation meant to you?
I feel extremely grateful to have had the opportunity to participate in this research project and will continue to do so through the MD Special Training in Research program (made possible by this support). I understand what a privilege it is to be able to spend time dedicated to learning new things and hope that I will do justice to the project and the support of the WCHRI Summer Studentship program.
The objective of this research project is to develop an improved system for automatic analysis of 3D imaging data used to inform the treatment of young patients who require medical procedures to repair their hearts and the surrounding blood vessels. In the current state, doctors who are performing these procedures rely on manual visual inspection of X-ray images, but are typically unable to acquire quantitative measurements to inform their treatment. Especially in the context of time-sensitive procedures, there is the potential to have a positive impact on patient outcomes by providing additional information about the size, location and structure of the heart and vessels of interest.
This project will focus on the analysis of relevant X-ray imaging datasets that have been previously collected and anonymized from procedures at the Mazankowski Alberta Heart Institute’s Cardiac Catheterization Lab. The first stage of this project will focus on developing a reference dataset of X-ray images in which the specific structures of interest—the pulmonary artery and subsequent vessels—have been identified and digitally labelled. This will involve development of a robust labelling strategy that will require visual inspection by expert users to confirm accuracy.
Once this labelled group of data has been generated from a subset of the total scan data acquired, it will be used to train a machine-learning algorithm which is capable of automatically labelling the pulmonary artery and subsequent vessels of interest. The performance of the generated algorithm will then be evaluated in terms of processing time and accuracy by performing automated segmentation on the remaining data sets.