Trainee Rounds: Reza Basiri and Xuanzi (Elly) Zhou
DATE: July 23 (Tue.)
TIME: 12pm to 1pm ET
METHOD: Zoom
PRESENTERS: Reza Basiri and Xuanzi (Elly) Zhou
Reza Basiri
PhD candidate, Institute of Biomedical Engineering, Faculty of Engineering, University of Toronto
TITLE: Advancing DFU Management: Introducing WoundVista-2.0 for Enhanced AI-Powered Diagnosis and Education
ABSTRACT: Diabetic Foot Ulcers (DFUs) are a significant concern, affecting 6.3% to 13% of diabetics worldwide. Effective management requires precise assessment and monitoring, challenged by limited resources and the growing diabetic patient population. Our proposed WoundVista-2.0, the DFU management platform powered by generative AI, enhances the quality of care by offering tools for both electronic health record transcriptions and synthetic image generation. Building on the success of WoundVista-1.0 and making use of the comprehensive Zivot dataset, it introduces innovative solutions for easier and more comprehensive patient reporting and synthetic and diverse DFU images to use in clinical education and R&D.
ABOUT: Reza Basiri, a PhD student at the University of Toronto, specializes in biomedical engineering with a focus on diabetic foot ulcer research. His expertise spans advanced imaging techniques, algorithm development, and deep learning, aiming to enhance healthcare through technology. Reza has held roles such as senior research analyst and research coordinator, contributing significantly to clinical efficiency and medical device innovation related to diabetic foot ulcers. His work includes creating the Zivot DFU Dataset, one of the kind and largest diabetic foot ulcer multimodal dataset, and the development of wound detection and classification models using the latest AI techniques.
Xuanzi (Elly) Zhou
PhD candidate, Institute of Medical Science, Temerty Faculty of Medicine, University of Toronto
TITLE: Developing a Digital Lung: A Deep Learning Approach to Simulating Physiological Lung Function during Ex Vivo Lung Perfusion
ABSTRACT: My project is focused on building a digital twin of ex vivo lungs based on high-resolution time-series ventilator data. Using artificial intelligence, we aim to create a digital version of a human lung that accurately simulates the lung function in the virtual space. With this model we will then be able to test and evaluate new treatments on the digital twin instead of having to test on additional organs. The success of this work will result in smarter and faster clinical trials which in turn will lead to important innovations making their way to patients sooner.
ABOUT: Elly Zhou is a second-year PhD student under the department of IMS at the University of Toronto. She is currently working with the Toronto lung transplant program to develop AI-based diagnostic tools for lung transplantation.
