An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index

Ki-67 labeling index is a widely used biomarker for the diagnosis and monitoring of cancer. Many automated techniques have been proposed for evaluating Ki-67 index. In this paper, we introduce an integrated deep learning based approach. We use MobileUnet model for segmentation and classification and connected component based algorithm for the estimation of Ki-67 index in bladder cancer cases. The average F1 score is 0.92 and dice score is 0.96. The mean absolute error in the evaluated Ki-67 index is 2.1. We also explore possible pre-processing steps to generalize the segmentation model to at least one another type of cancer. Histogram matching and re-sizing improve the performance in breast cancer data by 12% in F1 score and 8% in dice score.

[1]  Hai Su,et al.  An Integrated Framework for Automatic Ki-67 Scoring in Pancreatic Neuroendocrine Tumor , 2013, MICCAI.

[2]  Vilppu J Tuominen,et al.  ImmunoRatio: a publicly available web application for quantitative image analysis of estrogen receptor (ER), progesterone receptor (PR), and Ki-67 , 2010, Breast Cancer Research.

[3]  S. Osowski,et al.  New automated image analysis method for the assessment of Ki-67 labeling index in meningiomas. , 2010, Folia histochemica et cytobiologica.

[4]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[5]  Hai Su,et al.  Automatic Ki-67 Counting Using Robust Cell Detection and Online Dictionary Learning , 2014, IEEE Transactions on Biomedical Engineering.

[6]  G. Petris,et al.  Objective Quantification of the Ki67 Proliferative Index in Neuroendocrine Tumors of the Gastroenteropancreatic System: A Comparison of Digital Image Analysis With Manual Methods , 2013 .

[7]  Sung Hun Kim,et al.  Clinical usefulness of the free web-based image analysis application ImmunoRatio for assessment of Ki-67 labelling index in breast cancer , 2017, Journal of Clinical Pathology.

[8]  Toby C. Cornish,et al.  Software-automated counting of Ki-67 proliferation index correlates with pathologic grade and disease progression of follicular lymphomas. , 2013, American journal of clinical pathology.

[9]  W. Jonat,et al.  Is the Ki-67 labelling index ready for clinical use? , 2011, Annals of oncology : official journal of the European Society for Medical Oncology.

[10]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[11]  C. Chakraborty,et al.  An Advanced Deep Learning Approach for Ki-67 Stained Hotspot Detection and Proliferation Rate Scoring for Prognostic Evaluation of Breast Cancer , 2017, Scientific Reports.

[12]  Yun-bin Chen,et al.  Automated Ki-67 Quantification of Immunohistochemical Staining Image of Human Nasopharyngeal Carcinoma Xenografts , 2016, Scientific Reports.

[13]  Deniz Erdogmus,et al.  Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks , 2017, MLMI@MICCAI.

[14]  Rafael C. González,et al.  Digital image processing, 3rd Edition , 2008 .