Multicenter Privacy-Preserving Model Training for Deep Learning Brain Metastases Autosegmentation

no code implementations • 17 May 2024 • Yixing Huang, Zahra Khodabakhshi, Ahmed Gomaa, Manuel Schmidt, Rainer Fietkau, Matthias Guckenberger, Nicolaus Andratschke, Christoph Bert, Stephanie Tanadini-Lang, Florian Putz

When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0. 839) than naive TL (0. 570) and single-center training (0. 688) on combined UKER and USZ test data.

Automatized Self-Supervised Learning for Skin Lesion Screening

no code implementations • 11 Nov 2023 • Vullnet Useini, Stephanie Tanadini-Lang, Quentin Lohmeyer, Mirko Meboldt, Nicolaus Andratschke, Ralph P. Braun, Javier Barranco García

A clinical validation study was conducted to evaluate the tool's performance, which demonstrated an average sensitivity of 93% for the top-10 AI-identified UDs on skin lesions selected by the majority of experts in pigmented skin lesions.

object-detection Object Detection +1