A Fuzzy Min-Max Neural Network based Classification of Histopathology Images

• Published in: 2019 International Conference on Signal Processing and Communication (ICSC) pp. 143 - 146
• Main Authors: Kumar, Santhos A, Kumar, A., Bajaj, V., Singh, G. K., Kuldeep, B.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-03-2019
• Subjects: Biopsy; Breast cancer; Breast tumor; Feature extraction; Fuzzy Min-Max (FMM) neural network; Gray level co-occurrence matrix (GLCM); Histopathology images; Magnifying factor; Needles; Training
• ISBN: 9781538694350; 1538694352
• ISSN: 2643-444X
• DOI: 10.1109/ICSC45622.2019.8938321

Classification of histopathology images can provide support towards diagnosis of breast cancer. In this study, a Fuzzy Min-Max (FMM) network based approach is studied and used to classify the magnification independent breast cancer histopathology images. Gray level co-occurrence matrix (GLCM) is used to extract the features from images, and are then feed into FMM network to classify the dataset. BreaKHis database is used in this work, which contains microscopic benign and malignant breast tumor images at four different magnifying factors. Experimental results show that the magnifying factor of 200× gives better recognition rate than other magnification rates.