Approaching Peak Ground Truth
Florian Kofler, Johannes Wahle, Ivan Ezhov, Sophia J. Wagner, Rami Al-Maskari, Emilia Agnieszka Gryska, Mihail Ivilinov Todorov, Christina Bukas, Felix Meissen, Tingying Peng, Ali Ertürk, Daniel Rueckert, Rolf A. Heckemann, Jan Stefan Kirschke, Claus Zimmer, Benedikt Wiestler, Bjoern H. Menze, Marie Piraud · 2023
Machine learning models are typically evaluated by computing similarity with reference annotations and trained by maximizing similarity with such. Especially in the biomedical domain, annotations are subjective and suffer from low inter-and intra-rater reliability. Since annotations only reflect one interpretation of the real world, this can lead to sub-optimal predictions even though the model achieves high similarity scores. Here, the theoretical concept of Peak Ground Truth (PGT) is introduced. PGT marks the point beyond which an increase in similarity with the reference annotation stops translating to better Real World Model Performance (RWMP). Additionally, a quantitative technique to approximate PGT by computing inter- and intra-rater reliability is proposed. Finally, four categories of PGT-aware strategies to evaluate and improve model performance are reviewed.