Multiclass Classification of Breast Cancer in Whole-Slide Images
- 3.2k Downloads
Breast cancer is one of the leading cause of cancer-related death worldwide. During the diagnosis of breast cancer, the histopathological assessment of Haemotoxylin and Eosin(H&E) stained slides provides important clinical values. By applying computer-aid diagnosis on whole-slide image(WSI), the efficiency and consistency of such assessment could be improved. In this paper, we propose a deep learning-based framework that classifies H&E stained WSIs into regions of normal tissue, benign lesion, in-situ carcinoma and invasive carcinoma. The framework utilizes both microscopy images and WSIs to train a patch classifier in two stages. The underlying classifier is based on Inception-Resnet-v2. This framework won both parts of the ICIAR2018 Grand Challenge on Breast Cancer Histology Images  competition, achieved a part A multiclass accuracy of 87% and part B score of 0.6929.
KeywordsBreast cancer Deep learning Whole-Slide Images Multiclass classification
We would like to thank the organizers of ICIAR2018 and BACH2018 who supported and organized this challenge.
- 1.Camelyon16 (2016). https://camelyon16.grand-challenge.org/results/
- 2.Camelyon17 (2017). https://camelyon17.grand-challenge.org/results/
- 3.Breast Cancer Facts and Figures 2017–2018 (2018). https://www.cancer.org/research/cancer-facts-statistics/breast-cancer-facts-figures.html
- 4.ICIAR 2018 Grand Challenge on Breast Cancer Histology Images (2018). https://iciar2018-challenge.grand-challenge.org/
- 7.Habibzadeh, M.N., Jannesary, M., Aboulkheyr, H., Khosravi, P., Elemento, O., Totonchi, M., Hajirasouliha, I.: Breast cancer histopathological image classification: a deep learning approach. bioRxiv (2018). https://www.biorxiv.org/content/early/2018/01/04/242818
- 9.Janowczyk, A., Madabhushi, A.: Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases. J. Pathol. Inform. 7(1), 29 (2016). http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2016;volume=7;issue=1;spage=29;epage=29;aulast=Janowczyk;t=6CrossRefGoogle Scholar
- 12.Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. ArXiv e-prints, September 2014Google Scholar
- 14.Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, ArXiv e-prints, February 2016Google Scholar
- 15.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going Deeper with Convolutions. ArXiv e-prints, September 2014Google Scholar
- 16.Zhong, A., Li, Q.: HMS-MGH-CCDS Camelyon17 presentation (2017). https://camelyon17.grand-challenge.org/serve/public_html/presentations/HMS-MGH-CCDS_Camelyon17_presentation.pptx