On May 24, 2023, Prof. Julia Schnabel (Computational Imaging and AI in Medicine, TUM) will talk about “Quality matters - how artifical intelligence can enable better medical imaging.”

Abstract: Artificial intelligence, in particular from the class of deep learning, has shown great promise for application in medical imaging. However, its success is often limited by the image quality. A common approach is to train models on well curated databases of high-quality image acquisitions, which however then may fail on real patient cases in a hospital setting where image acquisitions can be of more variable quality. By using physically realistic artefact simulations for data augmentation, we can train AI models that are able deal with such artefacts during image formation, which in turn can improve and even be combined with further clinical downstream tasks. As an outlook, we can apply these principles towards online image quality control as well as active scanning preparations.

Date: May 24, 2023 Time: 13:00 CEST (until approx. 14:00) Location: online

Registration: The TUM-IAS Wednesday Coffee talks are currently held online via Zoom. To register and to receive the Zoom link, please send an email to events@ias.tum.de.

THE TUM-IAS WEDNESDAY COFFEE TALKS

To enable our ever-growing international community to participate, the TUM-IAS Wednesday Coffee Talks are currently held online via zoom.

Would you like to receive regular updates on the TUM-IAS Wednesday Coffee Talk and the online link? Just send a short note to events@ias.tum.de.

An overview on upcoming and past TUM-IAS Wednesday Coffee Talks can be found at the TUM-IAS Wednesday Coffee Talk Overview.