A comprehensive multi-domain dataset for mitotic figure detection.
Journal
Scientific data
ISSN: 2052-4463
Titre abrégé: Sci Data
Pays: England
ID NLM: 101640192
Informations de publication
Date de publication:
25 07 2023
25 07 2023
Historique:
received:
25
04
2023
accepted:
22
06
2023
medline:
27
7
2023
pubmed:
26
7
2023
entrez:
25
7
2023
Statut:
epublish
Résumé
The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species.
Identifiants
pubmed: 37491536
doi: 10.1038/s41597-023-02327-4
pii: 10.1038/s41597-023-02327-4
pmc: PMC10368709
doi:
Types de publication
Dataset
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
484Subventions
Organisme : Deutsche Forschungsgemeinschaft (German Research Foundation)
ID : 460333672
Informations de copyright
© 2023. The Author(s).
Références
Vet Pathol. 2022 Mar;59(2):211-226
pubmed: 34965805
J Pathol Inform. 2013 Sep 27;4:27
pubmed: 24244884
Vet Pathol. 2013 Sep;50(5):738-48
pubmed: 23444036
Mod Pathol. 2005 Aug;18(8):1067-78
pubmed: 15920556
Vet Pathol. 2011 Jan;48(1):147-55
pubmed: 21062911
J Clin Pathol. 2022 Jun;75(6):365-372
pubmed: 34556501
Med Image Anal. 2023 Feb;84:102699
pubmed: 36463832
J Am Vet Med Assoc. 1997 Dec 1;211(11):1422-7
pubmed: 9394893
Sci Data. 2020 Nov 27;7(1):417
pubmed: 33247116
Ann Diagn Pathol. 2017 Aug;29:11-16
pubmed: 28807335
Med Image Anal. 2015 Feb;20(1):237-48
pubmed: 25547073
Cytometry. 1997 Jun 1;28(2):135-40
pubmed: 9181303
Sci Rep. 2020 Aug 3;10(1):9795
pubmed: 32747665
Mod Pathol. 2012 Aug;25(8):1117-27
pubmed: 22499226
PLoS One. 2016 Aug 16;11(8):e0161286
pubmed: 27529701
Sci Data. 2019 Nov 21;6(1):274
pubmed: 31754105
J Pathol Inform. 2013 May 30;4:8
pubmed: 23858383
Med Image Anal. 2019 May;54:111-121
pubmed: 30861443
Vet Pathol. 2021 Mar;58(2):243-257
pubmed: 33371818
Int J Cancer. 1984 Jan 15;33(1):37-42
pubmed: 6693192
IEEE J Biomed Health Inform. 2021 Feb;25(2):325-336
pubmed: 33085623
Br J Cancer. 1957 Sep;11(3):359-77
pubmed: 13499785
Sci Data. 2023 Jul 25;10(1):484
pubmed: 37491536
Vet Pathol. 2021 Sep;58(5):809-828
pubmed: 33769136
Vet Pathol. 2016 Jan;53(1):7-9
pubmed: 26712813