Improved breast cancer detection using fusion of bimodal sonographic features through binary firefly algorithm

ABSTRACT

Breast cancer is a major health issue and causes a larger number of deaths in women. As per GLOBOCAN statistics, breast cancer has surpassed lung cancer in 2020 with 2.3 million anticipated new cases which is 11.7% of total cancer cases. Sonography is used in addition to mammography to detect, describe and locate breast lesions effectively. Elastography and Echography are widely used sonographic techniques as they provide different and distinctive information for identifying breast diseases. To obtain improved detection performance, this work focuses on the fusion of Local Binary Pattern (LBP) texture features from ultrasound elastogram and echogram images followed by feature selection using Binary Firefly Algorithm (BFA) with Optimum Path Forest (OPF) classifier accuracy as a fitness function for feature selection. This method produces 97.3% accuracy, 96.2% sensitivity, 98.2% specificity, 97.3% precision, 96.2% F1 score, 94.71% Balanced Classification Rate, and Mathews Correlation Coefficient of 0.884 outperforming existing works.

KEYWORDS:

• Breast cancer
• echography
• elastography
• binary firefly algorithm
• feature fusion
• support vector machine

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

S. Sasikala

Dr. S. Sasikala received her B.E. (ECE) degree from Bharadhidasan University in 1998. She obtained her M.Tech (Biomedical Engineering) degree from the Indian Institute of Technology Madras in 2005. She has twenty-two years of teaching experience at the college level. She completed her Doctoral Programme in Information and Communication Engineering in 2018 at Anna University, Chennai. Currently, she is working as an Associate Professor in the Department of ECE at Kumaraguru College of Technology, Coimbatore. She is an active member in IEEE, ISTE, IE(I). Her areas of interest include Signal Processing, Image Processing, Biomedical Systems, and Machine learning. To her credit, she has around 60 technical papers published in international peer-reviewed Scopus/SCI-indexed journals and conferences.

S. Arun Kumar

Mr. S. Arun Kumar is working as an Assistant professor at Kumaraguru College of Technology, Coimbatore. Currently, he is pursuing Ph.D. at Anna University in Computational Intelligence in Signal/Image Processing. He completed his bachelor's degree in Electronics and Communication Engineering from KCT. Further, he completed his M.Tech degree in Communication Engineering and Signal Processing from Amrita University Coimbatore. He is an active member of IEEE and IE(I) Professional Society. He is an avid researcher in Signal Processing, Image Processing, Biomedical Systems, and Machine learning. To his credit, he has around 30 technical papers published in international peer-reviewed and Scopus-indexed journals and conferences.

M. Ezhilarasi

Dr. M. Ezhilarasi, is an alumnus of GCT and MIT with a doctorate in Medical Imaging. She has 30 years of academic experience spread over the roles of Teaching, Research and Administration. She served as Principal for over 5 years at KGiSL Institute of Technology. She has published and reviewed many research papers, produced 7 PhDs, and a granted Patent. She has been in the Boards of Studies of reputed Institutions. She is a member of ISTE, ISoI, CSI, and also a Fellow of the Institution of Engineers. She has been deeply interested in internalization and is an ardent practitioner and trainer of meditation under heartfulness way.