Relationship between the Ki67 index and its area based approximation in breast cancer

• Published in: BMC cancer 2018-09, Vol.18 (1), p.867-867, Article 867
• Main Authors: Niazi, Muhammad Khalid Khan, Senaras, Caglar, Pennell, Michael, Arole, Vidya, Tozbikian, Gary, Gurcan, Metin N
• Format: Article
• Language: English
• Subjects: Analysis; Automation; Biological markers; Biomarkers, Tumor - genetics; Biopsy; Breast cancer; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - genetics; Breast Neoplasms - pathology; Cancer therapies; Cell cycle; Cell division; Cell growth; Cell proliferation; Cell Proliferation - genetics; Computational efficiency; Female; Humans; Image processing; Image Processing, Computer-Assisted; Image retrieval; International conferences; Ki-67 antigen; Ki-67 Antigen - genetics; Ki67 index; Laboratories; Medical imaging; Microscopy; Neuroblastoma; Nuclei; Nuclei detection; Pathology; Photonics; Prognosis; Segmentation; Standardization; Trends; Tumors; Working groups
• ISSN: 1471-2407; 1471-2407
• DOI: 10.1186/s12885-018-4735-5

The Ki67 Index has been extensively studied as a prognostic biomarker in breast cancer. However, its clinical adoption is largely hampered by the lack of a standardized method to assess Ki67 that limits inter-laboratory reproducibility. It is important to standardize the computation of the Ki67 Index before it can be effectively used in clincial practice. In this study, we develop a systematic approach towards standardization of the Ki67 Index. We first create the ground truth consisting of tumor positive and tumor negative nuclei by registering adjacent breast tissue sections stained with Ki67 and H&E. The registration is followed by segmentation of positive and negative nuclei within tumor regions from Ki67 images. The true Ki67 Index is then approximated with a linear model of the area of positive to the total area of tumor nuclei. When tested on 75 images of Ki67 stained breast cancer biopsies, the proposed method resulted in an average root mean square error of 3.34. In comparison, an expert pathologist resulted in an average root mean square error of 9.98 and an existing automated approach produced an average root mean square error of 5.64. We show that it is possible to approximate the true Ki67 Index accurately without detecting individual nuclei and also statically demonstrate the weaknesses of commonly adopted approaches that use both tumor and non-tumor regions together while compensating for the latter with higher order approximations.