Author: Ravinya Athukoralage

My name is Qifan Yang, and I am an incoming third-year student with Statistics Major and Mathematical Applications in Finance and Economics Specialist at the University of Toronto. This past summer, I had the opportunity to work on an ROP299 research project with Professor Tyrrell, and I would like to share my four-month journey in research, a completely new experience for me.

When I started, I was a complete novice in medical imaging and unfamiliar with the full process of scientific research. Before our first meeting, I felt quite nervous. I still remember Professor Tyrrell, during the interview, warning me about the potential challenges ahead. Coming from a statistics and mathematics background, I initially found both machine learning concepts and medical terminology quite intimidating. Although I had completed a few Kaggle courses, I lacked hands-on experience with building models from raw datasets and running end-to-end training and testing.

My research journey began along two paths: first, learning the fundamentals of machine learning and medical imaging, where review papers became my best starting point, and second, exploring rheumatic heart disease (RHD) and its potential for automated diagnosis using transthoracic echocardiography (TTE). The first obstacle I encountered was the lack of publicly available, large-scale datasets for RHD with detailed labels. This led me to pivot toward studying image quality in TTE, since I found a large echocardiography database with quality labels. However, a second challenge soon emerged: I struggled to identify a research question that was both technically meaningful and scientifically impactful.

This is where Professor Tyrrell’s mentorship made all the difference. In one group meeting, he mentioned severe motion blur he had observed in knee ultrasound images. That sparked the idea for my project: detecting and correcting non-uniform motion blur in echocardiography using deep learning. This was the turning point when the project truly began to take shape.

The real research work involved splitting and labeling datasets, designing a neural network model, training and testing on GPUs, and visualizing and evaluating results. Each of these steps was entirely new to me, requiring both technical learning and persistent problem-solving. I am deeply grateful for the guidance of Professor Tyrrell, as well as the support from Giuseppe, Noushin, and other members of the lab, including previous students whose work provided valuable reference points.

By the end of the summer, I had taken full charge of the project, running it from start to end. This responsibility taught me far more than technical skills. I developed a stronger sense of self-motivation, learned to manage my time effectively, and built the resilience needed to handle research setbacks. I realized that research is not just about repetitive lab work; it is about thinking critically, asking meaningful questions, and telling a compelling story through data and results.

The experience was more than an introduction to the research world; it taught me to think boldly and work carefully. I learned not to let ideas live only in conversation or in my head, but to translate them into small, testable experiments that turn speculation into evidence. Each modest prototype, whether a quick data split, a minimal model, or a rough visualization, sharpened my questions, exposed constraints, and informed the next step. Gradually, those incremental wins compounded into a coherent pipeline and credible results. The discipline I gained is simple but powerful: think wild, start small, measure honestly, and move steadily. This balance of wild curiosity with careful craftsmanship now guides how I approach complex, unfamiliar problems, and it’s the mindset I’ll carry into future research and professional work.

This was my first course related to research, and also my first time working with medical imaging. When I heard that we would be doing independent research, I immediately realized that this course would undoubtedly be a great challenge for me. Independent research meant there was no clear “standard answer”; instead, I had to explore and persist on my own.

At the beginning of my ROP project, I was actually the first student in the class to finalize a research direction. I quickly chose skin tone bias in melanoma detection as my topic and decided to work with the ISIC dataset. At that time, I felt well prepared: even though I noticed that dark-skin samples were rare, I believed the number would be “enough.” I even imagined finishing the project in less than two months.

But soon, reality hit me. Out of more than 30,000 ISIC images, there were almost no dark-skin cases. After that, I kept switching datasets: PAD, Fitzpatrick17k, MSKCC. However, each of them had serious problems: some had almost no melanoma cases, some had almost no dark-skin samples, some images contained a lot of background noise rather than just lesions, and some lacked skin tone labels altogether. Even when I combined them, the total number of dark-skin melanoma images was barely more than one hundred. During that period, I felt like I was constantly “starting over,” and every time I thought I had found a breakthrough, it quickly fell apart.

In this struggle, I tried almost everything I could think of. I trained my own U-Net, experimented with CLIP, SVM, EfficientNet, and ResNet; I tested light-skin-trained models directly on dark-skin data; I even used YOLO to crop lesions in order to reduce background noise. My research focus also shifted again and again: from melanoma, to pigmented lesions, and finally to red scaly diseases; and my tasks shifted from classification to segmentation and back again. Altogether, I must have attempted more than a dozen different approaches, yet none of them produced satisfactory results.

As the deadline drew closer, my anxiety grew stronger. By the last month, despite all the models, tasks, and research objects I had tried, I still had no meaningful results to show. At times I felt completely lost, unsure of what else I could even do. In desperation, I wrote Dr. Tyrrell a very long email, confessing that I might not be able to continue and even considered abandoning the project altogether. I told him that if I could start over, I would never choose to study bias so hastily, but would first spend more time carefully understanding the limitations of the datasets.

That month was probably the hardest part of the entire ROP. I stayed up late almost every day, exhausted and anxious, sometimes even afraid to run my code because I expected yet another failure. Dr. Tyrrell was sometimes worried and even a bit frustrated, which made me feel sad, but I was also deeply grateful that he cared so much. In the final weeks, Giuseppe also began to support me more closely, and I truly appreciated his help. During that time, even the smallest result—no matter how unrepresentative—felt important enough for me to immediately share with Dr. Tyrrell and Giuseppe for feedback.

Finally, near the very end, something changed. About ten days before the deadline, I obtained a result that was still imperfect, but at least demonstrated a sign of bias. It was not a breakthrough, but it was enough to build a conclusion. In the last week, I focused on writing the report, experimenting with bias-mitigation methods, and managed to finish everything just in time.

Looking back on these four months, I went through so many emotions: the early excitement of being “ahead,” the anxiety of being overtaken, the regret and despair of repeated failures, and the relief of a small last-minute success. If you ask me what kept me going, I honestly don’t know, perhaps the support from Dr. Tyrrell and Giuseppe, perhaps the stubborn voice in my head saying “try one more time,” or perhaps just a little bit of luck.

Through this course, I developed a new understanding of medical imaging and machine learning: they are not only technical problems but also involve fairness, data limitations, and persistence throughout the research process. I realized that the true value of research is not in quickly achieving a perfect result, but in continuously experimenting, reflecting, and learning from failures. In the future, I hope to further explore fairness in medical imaging, especially to investigate why my findings differed from previous studies and how I can avoid or better explain such discrepancies. I believe this will not only help me improve my research methods but also allow me to move forward more confidently on my academic path.