Open Access

ARTICLE

Tumor Cell Identification in Ki-67 Images on Deep Learning

Ruihan Zhang^1,2, Junhao Yang¹, Chunxiao Chen^1,*
1 Department of Biomedical Engineering, Nanjing University of Aeronautics & Astronautics, Nanjing, 211106, China.
2 The University of Melbourne, Parkville Campus, Melbourne, Victoria, 3010, Australia.
* Corresponding Author: Chunxiao Chen. E-mail: . Email:

Molecular & Cellular Biomechanics 2018, 15(3), 177-187. https://doi.org/ 10.3970/mcb.2018.04292

Abstract

The proportion of cells staining for the nuclear antigen Ki-67 is an important predictive indicator for assessment of tumor cell proliferation and growth in routine pathological investigation. Instead of traditional scoring methods based on the experience of a trained laboratory scientist, deep learning approach can be automatically used to analyze the expression of Ki-67 as well. Deep learning based on convolutional neural networks (CNN) for image classification and single shot multibox detector (SSD) for object detection are used to investigate the expression of Ki-67 for assessment of biopsies from patients with breast cancer in this study. The results focus on estimating the probability heatmap of tumor cells using CNN with accuracy of 98% and detecting the tumor cells using SSD with accuracy of 90%. This deep learning framework will provide an objective basis for the malignant degree of breast tumors and be beneficial to the pathologists for fast and efficiently Ki-67 scoring.

---

Keywords

Ki-67, breast cancer, convolution neural networks, single shot multibox detector.

---