000265364 001__ 265364 000265364 005__ 20231014131029.0 000265364 0247_ $$2doi$$a10.1109/ISBI53787.2023.10230497 000265364 037__ $$aDZNE-2023-00988 000265364 1001_ $$aKofler, Florian$$b0 000265364 1112_ $$a2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)$$cCartagena$$d2023-04-18 - 2023-04-21$$wColombia 000265364 245__ $$aApproaching Peak Ground Truth 000265364 260__ $$bIEEE$$c2023 000265364 29510 $$a2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) : [Proceedings] - IEEE, 2023. - ISBN 978-1-6654-7358-3 - doi:10.1109/ISBI53787.2023.10230497 000265364 300__ $$a1-6 000265364 3367_ $$2ORCID$$aCONFERENCE_PAPER 000265364 3367_ $$033$$2EndNote$$aConference Paper 000265364 3367_ $$2BibTeX$$aINPROCEEDINGS 000265364 3367_ $$2DRIVER$$aconferenceObject 000265364 3367_ $$2DataCite$$aOutput Types/Conference Paper 000265364 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1697198914_22039 000265364 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb 000265364 520__ $$aMachine 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. 000265364 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0 000265364 588__ $$aDataset connected to CrossRef Conference 000265364 7001_ $$0P:(DE-2719)9002062$$aWahle, Johannes$$b1$$udzne 000265364 7001_ $$aEzhov, Ivan$$b2 000265364 7001_ $$aWagner, Sophia J.$$b3 000265364 7001_ $$aAl-Maskari, Rami$$b4 000265364 7001_ $$aGryska, Emilia$$b5 000265364 7001_ $$aTodorov, Mihail$$b6 000265364 7001_ $$aBukas, Christina$$b7 000265364 7001_ $$aMeissen, Felix$$b8 000265364 7001_ $$aPeng, Tingying$$b9 000265364 7001_ $$aErtürk, Ali$$b10 000265364 7001_ $$aRueckert, Daniel$$b11 000265364 7001_ $$aHeckemann, Rolf$$b12 000265364 7001_ $$aKirschke, Jan$$b13 000265364 7001_ $$aZimmer, Claus$$b14 000265364 7001_ $$aWiestler, Benedikt$$b15 000265364 7001_ $$aMenze, Bjoern$$b16 000265364 7001_ $$aPiraud, Marie$$b17 000265364 773__ $$a10.1109/ISBI53787.2023.10230497 000265364 8564_ $$uhttps://pub.dzne.de/record/265364/files/DZNE-2023-00988_Restricted.pdf 000265364 8564_ $$uhttps://pub.dzne.de/record/265364/files/DZNE-2023-00988_Restricted.pdf?subformat=pdfa$$xpdfa 000265364 909CO $$ooai:pub.dzne.de:265364$$pVDB 000265364 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9002062$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b1$$kDZNE 000265364 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0 000265364 9141_ $$y2023 000265364 9201_ $$0I:(DE-2719)1013030$$kAG Mukherjee$$lStatistics and Machine Learning$$x0 000265364 980__ $$acontrib 000265364 980__ $$aVDB 000265364 980__ $$acontb 000265364 980__ $$aI:(DE-2719)1013030 000265364 980__ $$aUNRESTRICTED