AI-Powered Medical Imaging

In the first podcast sponsored by the IEEE Signal Processing Society, Ervin Sejdić, Professor at University of Toronto’s Edward S. Rogers Sr. Department of Electrical & Computer Engineering interviews April Khademi, Associate Professor of Biomedical Computer and Electrical Engineering at Toronto Metropolitan University and Canada Research Chair in AI for Medical Imaging. April Khademi April, an expert in AI-driven medical image analysis, focuses on AI-driven signal processing methods that have revolutionized medical imaging, improving diagnostic and therapeutic accuracy. In this podcast, she discusses how AI advancements continuously push the boundaries of medical imaging, providing clinicians with robust, quantitative disease metrics and enhancing overall healthcare quality. AI-driven foundation models in medical imaging, like MRI and CT, enhance object detection and segmentation. They mitigate data constraints and enable fine-tuning for smaller datasets. FDA-approved algorithms in image acquisition improve efficiency, allowing faster, lower-dose scans and super-resolution for better image quality, yielding substantial business benefits. AI also enhances interrater agreement in medical image interpretation, reducing subjectivity and varying expertise among clinicians. It ensures consistent, accurate diagnoses, especially in community hospitals without specialized pathologists, ultimately leading to more reliable patient treatment outcomes.