Structured crowdsourcing enables convolutional segmentation of histology images
2019; Oxford University Press; Volume: 35; Issue: 18 Linguagem: Inglês
10.1093/bioinformatics/btz083
ISSN1367-4811
AutoresMohamed Amgad, Habiba Elfandy, Hagar Hussein, Lamees A Atteya, Mai Alaaeldin Temraz Elsebaie, Lamia S Abo Elnasr, Rokia Sakr, Hazem S E Salem, Ahmed F Ismail, Anas M. Saad, Joumana Ahmed, Maha AT Elsebaie, Mustafijur Rahman, Inas A. Ruhban, Nada M. Elgazar, Yahya Alagha, Mohamed Osman, Ahmed M. Alhusseiny, Mariam M Khalaf, Abo-Alela F Younes, Ali Abdulkarim, Duaa M Younes, Ahmed Gadallah, Ahmad M Elkashash, Yahya Salma, Basma M Zaki, Jonathan Beezley, Deepak R. Chittajallu, David Manthey, David A. Gutman, Lee Cooper,
Tópico(s)Colorectal Cancer Screening and Detection
ResumoWhile deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images.We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy.Dataset is freely available at: https://goo.gl/cNM4EL.Supplementary data are available at Bioinformatics online.
Referência(s)