Medical imaging is currently one of the areas where much machine learning is done both on the academic side and from startup or larger established companies. With standardized acquisition setups, image views and also clear applications (diagnosis, treatment planning) this seems suitable but also has several difficulties, such as varying acquisition parameters, changing imaging equipment, but also limited data and particularly missing annotations with clinicians being chronically overloaded. Prof. Henning Müller (professor in computer science at HES-SO & at the deparment of radiology and medical informatics at the University of Geneva) highlights in his presentation some of the challenges and partial solutions that he and his team are currently working on to address these challenges.
Tuesday, 10-04-2022, 05:00 p.m. – 06:00 p.m., virtual event
Further details: https://www.i-aida.org/events/challenges-for-machine-learning-using-medical-data/.
This is an event of I-AIDA – International Artificial Intelligence Doctoral Academy.