Back to Other Samples
Decision Support & AI

Mitosis Analysis

In reporting of breast cancer pathology, mitosis detection and counting of mitotic cells are important factors that affect the tumor grade and the treatment of the patient. Mitotic cell counting requires standardization to a fixed field area. The total number of mitoses per 10 HPF is recorded. Normally, the count is performed manually by pathologists, but automating the process could reduce its time, minimize errors, and improve the comparability of results obtained in different pathology laboratories . Mitosis detection is a complex process because only definite mitotic figures have to be counted; hyperchromatic and pyknotic nuclei are ignored since they are more likely to represent apoptosis rather than cells in mitosis [1]. Therefore, an artificial intelligence method, convolutional neural networks (CNN), is used for mitosis detection in this analysis module.

Back to Other Samples
Keywords

Breast Cancer, Artificial Intelligence, Deep Learning, Mitosis Detection.

Methods

The several deep learning models were used to detect and classify mitotic cells. Firstly, all the nuclei of cells in the histopathological images of the breast tissue were segmented using U-Net architecture. The outputs of the nuclei detection model were regarded as ROI for mitosis detection. After detecting nuclei, VGG-11 architecture was used to make predictions for each nucleus region to determine whether the nucleus is mitotic or non-mitotic. By now, a unique dataset was created using 4794 mitotic and 4794 non-mitotic cell nuclei.

Quantitative output variables
  • Nuclei Count
  • Mitosis Count
  • Mitosis Grade
  • Mitosis Count in Regions
  • List of Mitosis with Probability 
  • List of Mitosis Count in Regions
Workflow
  1. View the H&E stained whole slide digital image of breast cancer on ViraPath.
  2. Select the tumor regions on digital image.
  3. Run the mitosis analysis.
References

[1] Sunil R. Lakhani, Ian O. Ellis, Stuart J. Schnitt, Puay Hoon Tan, Marc J. van de Vijver (Ed.). (2012). WHO Classification of Tumours of the Breast (4th ed.) International Agency for Research on Cancer (IARC), Lyon, France: pp 19-20

Contact us
for more information

For more information about our solutions, you can contact us and request a demo.

Other Solutions

Workflow Solution & BI

Discover

Collaboration

Discover

Academic

Discover