Histopathology Image Classification using Enhanced Fuzzy Min-Max network

Histopathology Image Classification using Enhanced Fuzzy Min-Max network

Histopathology image classification can offer great support towards breast cancer identification. In this paper, an Enhanced fuzzy min max (EFMM) neural network is considered and applied to histopathological images. Gray level co-occurrence matrix (GLCM) based feature extractor is employed to extrac...

Full description

Saved in:
Bibliographic Details
Published in:2020 International Conference on Communication and Signal Processing (ICCSP) pp. 0488 - 0492
Main Authors: Santhos Kumar, A, Kumar, Anil, Bajaj, Varun, Singh, G. K.
Format: Conference Proceeding
Language:English
Published: IEEE 01-07-2020
Subjects:
Biopsy
BreaKHis Database
Breast cancer
Breast tumor
Enhanced Fizzy Min-Max model
Feature extraction
GLCM
Magnification factor
Neural networks
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Histopathology image classification can offer great support towards breast cancer identification. In this paper, an Enhanced fuzzy min max (EFMM) neural network is considered and applied to histopathological images. Gray level co-occurrence matrix (GLCM) based feature extractor is employed to extract the textural information from each histopathology image and then these information are applied on EFMM model to accurately classify the histopathology images. In this work, Breast cancer histopathology (BreaKHis) database is considered, which comprises malignant and benign histopathology images at four different magnifications. Simulation outcomes depict that the magnification factor of 100 \times provides greater recognition rate than other magnifying factors.
DOI:10.1109/ICCSP48568.2020.9182361