Contribution to a conference proceedings/Contribution to a book

DZNE-2023-00988

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Approaching Peak Ground Truth

Kofler, F. ; Wahle, J.DZNE* ; Ezhov, I. ; Wagner, S. J. ; Al-Maskari, R. ; Gryska, E. ; Todorov, M. ; Bukas, C. ; Meissen, F. ; Peng, T. ; Ertürk, A. ; Rueckert, D. ; Heckemann, R. ; Kirschke, J. ; Zimmer, C. ; Wiestler, B. ; Menze, B. ; Piraud, M.

2023
IEEE

This record in other databases:  

Please use a persistent id in citations: doi:10.1109/ISBI53787.2023.10230497

Abstract: 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. © 2023 IEEE.

---

Contributing Institute(s):

1. Statistics and Machine Learning (AG Mukherjee)

Research Program(s):

1. 354 - Disease Prevention and Healthy Aging (POF4-354) (POF4-354)

Appears in the scientific report 2023

---