Disputation von Fabian Westhäußer am 08.10.2024, 09:00 Uhr
8. Oktober 2024, von Reinhard Zierke
Einladung zur hochschulöffentlichen Disputation im Rahmen des Promotionsverfahrens von Fabian Westhäußer
Titel der Dissertation: Robust and Trustworthy Deep Learning-based Disease Detection and Risk Assessment on MRI and Histopathological Images That Exceeds Predictive Performance of Human Experts
Medical deep learning models often struggle to meet requirements for clinical applicability such as human-level performance, robustness to data variability, and interpretability. This research proposes solutions to these challenges in the context of prostate cancer aggressiveness grading through the development of the Prostate Cancer Aggressiveness Index (PCAI). Trained on a diverse dataset, PCAI demonstrates superior predictive capabilities over several medical experts by predicting cancer risk based on objective patient outcomes. Besides generalizing across several clinical environments, the model quantifies its predictive confidence, enhancing trustworthiness by detecting problematic input and making it a potential blueprint for future clinical decision support systems.
The presentation will be given in English.
Datum und Uhrzeit: Dienstag, 8. Oktober 2024 um 09:00 Uhr
Ort: Albert-Einstein-Ring 8-10, Raum 0005/0010 oder per Videokonferenz
Betreuerin: Prof. Dr. Simone Frintrop, Co-Betreuer: Prof. Dr. Stefan Bonn
Prof. Dr. Matthias Rarey
Vorsitzender des Fachpromotionsausschusses Informatik