AI, Research, and the New Identity of Scientists
In my acceptance remarks at the Duke Med Phys program graduation ceremony, I thanked ChatGPT for arriving at the right time and making our lives as PhD students easier. I genuinely meant it. Then I started thinking about how AI tools have changed scientific research and efficiency, especially for PhD students. Doing research in a…
How synthetic CT datasets are generated using Monte Carlo physics
Generating realistic synthetic CT data requires modeling two key steps: how x-rays travel through the body and how the detector converts those x-rays into an image. In theory, the most accurate way to do this would be to use a full Monte Carlo simulation that tracks every x-ray photon from the source, through the body,…
Multi-scanner Domain Shift in CT Imaging
Multi-scanner domain shift has been a persistent barrier to quantitative and qualitative CT imaging and robust medical AI. I worked on this problem during my PhD because I found images varied across scanners and models shouldn’t fail simply because a patient was scanned on a different detector, scanner, or even image acquisition protocol. By combining…
