Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Aubreville, Marc, Stathonikos, Nikolas, Donovan, Taryn A., Klopfleisch, Robert, Ganz, Jonathan, Ammeling, Jonas, Wilm, Frauke, Veta, Mitko, Jabari, Samir, Eckstein, Markus, Annuscheit, Jonas, Krumnow, Christian, Bozaba, Engin, Cayir, Sercan, Gu, Hongyan, Chen, Xiang 'Anthony', Jahanifar, Mostafa, Shephard, Adam, Kondo, Satoshi, Kasai, Satoshi, Kotte, Sujatha, Saipradeep, VG, Lafarge, Maxime W., Koelzer, Viktor H., Wang, Ziyue, Zhang, Yongbing, Yang, Sen, Wang, Xiyue, Breininger, Katharina, Bertram, Christof A.
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914735100788736
author Aubreville, Marc
Stathonikos, Nikolas
Donovan, Taryn A.
Klopfleisch, Robert
Ganz, Jonathan
Ammeling, Jonas
Wilm, Frauke
Veta, Mitko
Jabari, Samir
Eckstein, Markus
Annuscheit, Jonas
Krumnow, Christian
Bozaba, Engin
Cayir, Sercan
Gu, Hongyan
Chen, Xiang 'Anthony'
Jahanifar, Mostafa
Shephard, Adam
Kondo, Satoshi
Kasai, Satoshi
Kotte, Sujatha
Saipradeep, VG
Lafarge, Maxime W.
Koelzer, Viktor H.
Wang, Ziyue
Zhang, Yongbing
Yang, Sen
Wang, Xiyue
Breininger, Katharina
Bertram, Christof A.
author_facet Aubreville, Marc
Stathonikos, Nikolas
Donovan, Taryn A.
Klopfleisch, Robert
Ganz, Jonathan
Ammeling, Jonas
Wilm, Frauke
Veta, Mitko
Jabari, Samir
Eckstein, Markus
Annuscheit, Jonas
Krumnow, Christian
Bozaba, Engin
Cayir, Sercan
Gu, Hongyan
Chen, Xiang 'Anthony'
Jahanifar, Mostafa
Shephard, Adam
Kondo, Satoshi
Kasai, Satoshi
Kotte, Sujatha
Saipradeep, VG
Lafarge, Maxime W.
Koelzer, Viktor H.
Wang, Ziyue
Zhang, Yongbing
Yang, Sen
Wang, Xiyue
Breininger, Katharina
Bertram, Christof A.
contents Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert consensus and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an $F_1$ score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, but with only minor changes in the order of participants in the ranking.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15589
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge
Aubreville, Marc
Stathonikos, Nikolas
Donovan, Taryn A.
Klopfleisch, Robert
Ganz, Jonathan
Ammeling, Jonas
Wilm, Frauke
Veta, Mitko
Jabari, Samir
Eckstein, Markus
Annuscheit, Jonas
Krumnow, Christian
Bozaba, Engin
Cayir, Sercan
Gu, Hongyan
Chen, Xiang 'Anthony'
Jahanifar, Mostafa
Shephard, Adam
Kondo, Satoshi
Kasai, Satoshi
Kotte, Sujatha
Saipradeep, VG
Lafarge, Maxime W.
Koelzer, Viktor H.
Wang, Ziyue
Zhang, Yongbing
Yang, Sen
Wang, Xiyue
Breininger, Katharina
Bertram, Christof A.
Computer Vision and Pattern Recognition
Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert consensus and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an $F_1$ score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, but with only minor changes in the order of participants in the ranking.
title Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.15589