Zurück zur Übersicht
| Medical image analysis. 2022 Nov 23. doi: 10.1016/j.media.2022.102699. pii: S1361-8415(22)00327-9 |
| Mitosis domain generalization in histopathology images - The MIDOG challenge. |
| Aubreville M1, Stathonikos N2, Bertram CA3, Klopfleisch R4, Ter Hoeve N5, Ciompi F6, Wilm F7, Marzahl C8, Donovan TA9, Maier A10, Breen J11, Ravikumar N12, Chung Y13, Park J14, Nateghi R15, Pourakpour F16, Fick RHJ17, Ben Hadj S18, Jahanifar M19, Shephard A20, Dexl J21, Wittenberg T22, Kondo S23, Lafarge MW24, Koelzer VH25, Liang J26, Wang Y27, Long X28, Liu J29, Razavi S30, Khademi A31, Yang S32, Wang X33, Erber R34, Klang A35, Lipnik K36, Bolfa P37, Dark MJ38, Wasinger G39, Veta M40, Breininger K41 |
 Author information
|
|
Abstract The density of mitotic figures (MF) within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of MF by pathologists is subject to a strong inter-rater bias, limiting its prognostic value. State-of-the-art deep learning methods can support experts but have been observed to strongly deteriorate when applied in a different clinical environment. The variability caused by using different whole slide scanners has been identified as one decisive component in the underlying domain shift. The goal of the MICCAI MIDOG 2021 challenge was the creation of scanner-agnostic MF detection algorithms. The challenge used a training set of 200 cases, split across four scanning systems. As test set, an additional 100 cases split across four scanning systems, including two previously unseen scanners, were provided. In this paper, we evaluate and compare the approaches that were submitted to the challenge and identify methodological factors contributing to better performance. The winning algorithm yielded an F score of 0.748 (CI95: 0.704-0.781), exceeding the performance of six experts on the same task. |
|
Copyright © 2022 Elsevier B.V. All rights reserved. |
|
KEYWORDS: Challenge, Deep Learning, Domain generalization, Histopathology, Mitosis |
|
Publikations ID: 36463832 Quelle: öffnen |
Author information
Schnellinfo
-- Cancer Care
-- Kliniken und Partner
-- CCC Cancer School
-- Young CCC
-- CCC Tumorboards
-- CCC Forschungscluster
-- CCC Units
-- CCC Platforms
-- SOPs / Leitlinien
-- Kontakt
Featured
