Hidden Variables in Deep Learning Digital Pathology and Their Potential to Cause Batch Effects: Prediction Model Study

Autor:	Max Schmitt, Axel Hauschild, Dieter Krahl, Jakob Nikolas Kather, Markus Tiemann, Roman C. Maron, Achim Hekler, Frederick Klauschen, Titus J. Brinker, Albrecht Stenzinger, Sebastian Haferkamp, Michael Weichenthal, Christof von Kalle, Stefan Fröhling, Heinz Kutzner, Eva Krieghoff-Henning, Jochen Utikal
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	Computer science pitfalls Health Informatics artifacts Machine learning computer.software_genre lcsh:Computer applications to medicine. Medical informatics Convolutional neural network 03 medical and health sciences 0302 clinical medicine Robustness (computer science) convolutional neural networks Pathology Humans 030304 developmental biology 0303 health sciences Original Paper Artificial neural network Learnability business.industry Deep learning lcsh:Public aspects of medicine Digital pathology deep learning lcsh:RA1-1270 artificial intelligence neural networks Data set Variable (computer science) machine learning 030220 oncology & carcinogenesis clinical pathology lcsh:R858-859.7 Artificial intelligence Neural Networks Computer business digital pathology computer
Zdroj:	Journal of Medical Internet Research, Vol 23, Iss 2, p e23436 (2021) Journal of Medical Internet Research Journal of medical internet research 23(2), e23436 (2021). doi:10.2196/23436
ISSN:	1438-8871
DOI:	10.2196/23436
Popis:	Journal of medical internet research 23(2), e23436 (2021). doi:10.2196/23436 Published by Healthcare World, Richmond, Va.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c24d65ae837cda6d28d324c82f1f9c01 https://www.jmir.org/2021/2/e23436 Zobrazit plný text záznamu Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.