Classification of Mitotic Cells
Tumor diagnostics are based on histopathological assessments of tissue biopsies of the suspected carcinogen region. One standard task in histopathology is counting of mitotic cells, a task that provides great potential to be improved in speed, accuracy and reproducability. The advent of deep learning methods brought a significant increase in precision of algorithmic detection methods, yet it is dependent on the availability of large amounts of data, completely capturing the natural variability in the material. Fully segmented images are provided by the MITOS dataset with 300 mitotic events. The ICPR2012 dataset provides 326 mitotic cells and in AMIDA2014 dataset, 550 mitotic cells for training and 533 for testing. In contrast to these datasets, a dataset with high number of mitotic events is missing. For this, either one of two pathologist annotated at least 10 thousand cell images for cells of the type mitosis, eosinophilic granulocyte and normal tumor cell from canine mast cell tumor whole-slide images, exceeding all publicly available data sets by approximately one order of magnitude. We tested performance using a standard CNN approach and found accuracies of up to 0.93.
Unable to display preview. Download preview PDF.
- 1.Kiupel M, Webster J, Bailey K, et al. Proposal of a 2-Tier histologic grading system for canine cutaneous mast cell tumors to more accurately predict biological behavior. Veterin Pathology. 2011;48(1):147–155.Google Scholar
- 2.Meuten D, Moore F, George J. Mitotic count and the field of view area: Time to standardize. SAGE Publications Sage CA: Los Angeles, CA; 2016.Google Scholar
- 3.Northrup N, Howerth E, Harmon B, et al. Variation among Pathologists in the histologic grading of canine cutaneous mast cell tumors with uniform use of a single grading reference. J Veterin Diagn Invest. 2005;17(6):561–564.Google Scholar
- 4.Romo-Bucheli D, Janowczyk A, Gilmore H, et al. A deep learning based strategy for identifying and associating mitotic activity with gene expression derived risk categories in estrogen receptor positive breast cancers. Cytometry A. 2017.Google Scholar
- 5.Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems; 2012. p. 1097–1105.Google Scholar
- 6.Malon CD, Cosatto E, et al. Classification of mitotic figures with convolutional neural networks and seeded blob features. J Pathol Inform. 2013;4(1):9.Google Scholar
- 7.Cireşan DC, Giusti A, Gambardella LM, et al.; Springer. Mitosis detection in breast cancer histology images with deep neural networks. Proc MICCAI. 2013; p. 411–418.Google Scholar
- 8.Albarqouni S, Baur C, Achilles F, et al. AggNet: deep learning from crowds for mitosis detection in breast cancer histology images. IEEE Trans Med Imaging. 2016;35(5):1313–1321.Google Scholar
- 9.Chen H, Dou Q, Wang X, et al. Mitosis detection in breast cancer histology images via deep cascaded networks. In: 13th AAAI Conf Artific Intell; 2016.Google Scholar
- 10.Goode A, Satyanarayanan M. A Vendor-Neutral library and viewer for whole-slide images. Computer Science Department, Carnegie Mellon University. 2008.Google Scholar