BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images.
Journal
Database : the journal of biological databases and curation
ISSN: 1758-0463
Titre abrégé: Database (Oxford)
Pays: England
ID NLM: 101517697
Informations de publication
Date de publication:
17 10 2022
17 10 2022
Historique:
accepted:
01
10
2022
revised:
16
09
2022
received:
18
03
2022
entrez:
17
10
2022
pubmed:
18
10
2022
medline:
20
10
2022
Statut:
ppublish
Résumé
Breast cancer is the most commonly diagnosed cancer and registers the highest number of deaths for women. Advances in diagnostic activities combined with large-scale screening policies have significantly lowered the mortality rates for breast cancer patients. However, the manual inspection of tissue slides by pathologists is cumbersome, time-consuming and is subject to significant inter- and intra-observer variability. Recently, the advent of whole-slide scanning systems has empowered the rapid digitization of pathology slides and enabled the development of Artificial Intelligence (AI)-assisted digital workflows. However, AI techniques, especially Deep Learning, require a large amount of high-quality annotated data to learn from. Constructing such task-specific datasets poses several challenges, such as data-acquisition level constraints, time-consuming and expensive annotations and anonymization of patient information. In this paper, we introduce the BReAst Carcinoma Subtyping (BRACS) dataset, a large cohort of annotated Hematoxylin and Eosin (H&E)-stained images to advance AI development in the automatic characterization of breast lesions. BRACS contains 547 Whole-Slide Images (WSIs) and 4539 Regions Of Interest (ROIs) extracted from the WSIs. Each WSI and respective ROIs are annotated by the consensus of three board-certified pathologists into different lesion categories. Specifically, BRACS includes three lesion types, i.e., benign, malignant and atypical, which are further subtyped into seven categories. It is, to the best of our knowledge, the largest annotated dataset for breast cancer subtyping both at WSI and ROI levels. Furthermore, by including the understudied atypical lesions, BRACS offers a unique opportunity for leveraging AI to better understand their characteristics. We encourage AI practitioners to develop and evaluate novel algorithms on the BRACS dataset to further breast cancer diagnosis and patient care. Database URL: https://www.bracs.icar.cnr.it/.
Identifiants
pubmed: 36251776
pii: 6762252
doi: 10.1093/database/baac093
pmc: PMC9575967
pii:
doi:
Substances chimiques
Eosine Yellowish-(YS)
TDQ283MPCW
Hematoxylin
YKM8PY2Z55
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© The Author(s) 2022. Published by Oxford University Press.
Références
J Pathol Inform. 2013 May 30;4:8
pubmed: 23858383
Med Image Anal. 2016 Oct;33:170-175
pubmed: 27423409
Med Image Anal. 2019 Aug;56:122-139
pubmed: 31226662
JAMA. 2017 Dec 12;318(22):2199-2210
pubmed: 29234806
J Digit Imaging. 2020 Jun;33(3):632-654
pubmed: 31900812
J Pathol Inform. 2021 Nov 15;12:45
pubmed: 34881099
Med Image Anal. 2022 Jan;75:102264
pubmed: 34781160
IEEE Trans Biomed Eng. 2016 Jul;63(7):1455-62
pubmed: 26540668
PLoS One. 2017 Jun 1;12(6):e0177544
pubmed: 28570557
Cell. 2020 Nov 25;183(5):1436-1456.e31
pubmed: 33212010
Breast J. 2010 Jan-Feb;16(1):55-9
pubmed: 19825003
J Pathol Inform. 2018 Nov 14;9:38
pubmed: 30607305
Sci Rep. 2017 Dec 4;7(1):16878
pubmed: 29203879
J Pathol Clin Res. 2022 Mar;8(2):116-128
pubmed: 35014198
Med Image Anal. 2021 Jan;67:101813
pubmed: 33049577
Med Image Anal. 2019 May;54:111-121
pubmed: 30861443
Lab Invest. 2021 Apr;101(4):412-422
pubmed: 33454724
Semin Cancer Biol. 2021 Jul;72:226-237
pubmed: 32818626