More than meets the eye: Validation in automated image analysis
Tuesday, 11.09.2023, 9:30 – 10:30
Andreas-Pfitzmann-Bau APB/E023
by Annika Reinke
Annika Reinke did her Ph.D. at the division of Intelligent Medical Systems at the German Cancer Research Center (DKFZ) with the goal of adapting mathematical concepts to societally relevant topics, like scientific benchmarking and validation. Having published disruptive findings on biomedical image analysis challenges in Nature Communications, she is a founding member of the initiative of Biomedical Image Analysis ChallengeS (BIAS) aiming for bringing biomedical image analysis challenges to the next level of quality. She serves as the secretary of the MICCAI special interest group on biomedical challenges and as an active member and taskforce lead of the MONAI working group on evaluation, reproducibility and benchmarking.
Abstract
The importance of automatic artificial intelligence (AI)-based biomedical image analysis is growing rapidly. However, only a small number of algorithms have been successfully applied in clinical real-world settings. The fact that validation is frequently undervalued could be one of the causes. To enable the accurate tracking of scientific progress, however, and to close the current gap between method research and method translation into practice, reliable algorithm validation is essential. Several difficulties with validating AI algorithms will be discussed in this talk, along with suggestions for how to avoid them. In particular, we will address how to choose performance metrics in a problem-aware manner.