False Positive Reduction in Mammographic Mass Detection Using Image Representations for Textural Analysis

Abstract

Breast cancer is a prominent disease affecting women and is associated with low survival rate. Mammogram is a widely accepted and adopted modality for diagnosing breast cancer. The challenges faced in the early detection of breast cancer include poor contrast of mammograms, complex nature of abnormalities and difficulty in interpreting dense tissues. Computer-Aided Diagnosis (CAD) schemes help radiologists improve the sensitivity by rendering an objective diagnosis, in addition to reducing the time and cost involved. Conventional methods for automated diagnosis involve extracting handcrafted features from Region of Interest (ROI) followed by classification using Machine Learning (ML) techniques. The main challenge faced in CAD is higher false positive rate which adds to patient anxiety. This paper proposes a new CAD scheme for reducing the number of false positives in mammographic mass detection using a Deep Learning (DL) method. Convolutional Neural Network (CNN) can be considered as a prospective candidate for efficiently eliminating false positives in mammographic mass detection. More specifically, image representations that include Hilbert's image representation and forest fire model which contain rich textural information are given as input to CNN for mammogram classification. The proposed system outperforms ML approach based on handcrafted features extracted from the image representations considered. In particular, forest fire- CNN combination achieves accuracy as high as 96%.