Dual Stage Normalization Approach Towards Classification of Breast Cancer

ABSTRACT

Breast cancer is a major concern among women that causes high risk of death. Early diagnosis of such cancer becomes challenging due to alterations in the color of the histopathological breast images. This study uses a publicly available dataset of breast cancer histopathology images. This paper introduces a dual stage normalization approach, to address the color variation problem of biopsy specimen collectively caused by incompatible staining in biopsy process and bizarre imaging quality. The dual stage normalization proposed here consists of a stain normalization unit and a light normalization unit. This system addresses the variations of both imaging and staining of specimen that are caused by a microscopic imaging setup. Later on, eight features have been extracted from the normalized images and used for the classification of breast cancer (benign and malignant). The overall accuracy of the back propagation algorithm (BPA) classifier is obtained as 81.8%. After comparison with other classifier accuracies, BPA classifier is found to be acceptable. Recall and precision values are approximately 89% and 90%, respectively, which is acceptable. The saturation-weighted hue statistics produces balanced and uniform color hues for stain normalization. This statistic is powerful against variations in model parameters and unsusceptible to image subjects and achromatic colors. This normalization technique retains all histological data with an enhanced performance.

Keywords:

• Back propagation algorithm
• Biopsy
• Breast cancer
• Histopathology
• Light normalization
• Stain normalization

Additional information

Notes on contributors

M. A. Aswathy

M A Aswathy received her BTech degree in electronics and communication engineering from Vidya Academy of Science and Technology, Kerala and ME degree in applied electronics from KSR College of Technology, Tamil Nadu, India, in 2011 and 2013, respectively. She has been with the Department of Electronics Engineering as a lecturer at SETCEM, Kerala, India. Currently, she is working as PhD scholar at Vellore Institute of Technology (VIT), Tamil Nadu, India. Her fields of interest are biomedical engineering, digital image processing, and signal processing. Email: [email protected]

M. Jagannath

M Jagannath is an associate professor in the School of Electronics Engineering at Vellore Institute of Technology (VIT), Chennai, India. Prior to joining VIT, he was serving the position of senior project officer at the Industrial Consultancy and Sponsored Research at IIT Madras. He obtained his PhD from IIT Madras in 2012. He received the Best Academic Researcher of the Year 2017 from the Office of the Prime Minister of the Republic of India. He received Technical Icon of the Year 2012 from the Institution of Engineering and Technology, Young Professional Society (Chennai Network), UK. His research interests include sleep research, music research, biomedical instrumentation systems, and signal and image processing.