Abstract:  Computational approaches have the potential to transform the way we diagnose and treat diseases. Deep learning-based image analysis finds direct applications across various clinical fields including radiology, histopathology, and surgery, and has demonstrated to outperform medical experts in specific tasks such as diagnosing lung cancer on chest x-rays. However, conceptual and regulatory barriers hinder clinical translation, resulting in a limited number of models progressing to clinical stages. In this presentation, I will highlight some of the most promising applications of computational data analysis in diverse clinical domains. Additionally, I will explore strategies to overcome translational barriers for innovations in Artificial Intelligence-based medicine. Finally, I will discuss the broader scope of AI in medicine, extending beyond patient care to potential enhancements in education and research within biomedical fields.

Biography: Fiona Kolbinger is a Research Assistant Professor at Purdue University's Weldon School of Biomedical Engineering. A physician by training, she completed her doctorate at the German Cancer Research Center in Heidelberg, Germany in 2019. Since then, she has conducted translational research at the intersection of data science and clinical medicine. Her research aims to develop computational tools for personalized treatment in surgery and interventional medicine and to evaluate the clinical value of these tools in early-phase clinical trials.

~ BME Host: Young Kim ~

Zoom link: https://purdue-edu.zoom.us/j/5593290378?pwd=eFBOZFlNTU50ZDA2S2gwcnpyOWIwUT09

Note: Students registered for the seminar are expected to attend in-person.