Automatic Classification of Breast masses for Diagnosis of Breast Cancer in Digital Mammograms using Neural Network

Hitiksha Shah

CALL FOR PAPERS : Mar-2023

Submission Last Date

25-Mar-23

Submit Manuscript Online

FOR AUTHORS

FOR REVIEWERS

ARCHIEVES

DOWNLOADS

Open Access

Automatic Classification of Breast masses for Diagnosis of Breast Cancer in Digital Mammograms using Neural Network

Author(s):

Hitiksha Shah , Government Engineering College, Gandhinagar, India

Keywords:

Digital mammogram, Median filter, neural network, Texture feature, Wavelet transform

Abstract:

This paper presents a computer aided diagnosis (CAD) system for automatic classification of breast masses in digital mammograms. Initially, Digital mammogram is pre-processed by 2D-median filter, connected component labelling method, and morphological functions for breast extraction. Wavelet transform is used for enhancement of mammogram and triangular mask is used for pectoral muscle suppression. Morphological functions like opening, closing, erosion, dilation and reconstruction are used for the segmentation of mammogram to extract region of interest (ROI). From ROI, intensity histogram based texture features are extracted. Extracted features are fed into classifier algorithm. In this proposed work, concept of neural network is used for classification, which is applied for two levels. In the first level, neural network classify the segmented ROI into normal (without tumor) and abnormal (with tumor) ROI. Second level neural network classify abnormal ROI into malignant and benign masses. The proposed CAD system achieves 96.07% specificity and 94.73% sensitivity at first level classification, 91.66% specificity and 80% sensitivity at second level.