Detection of Breast Cancer Based on Feature Extraction Using WPSO in Conjunction with CNN

Abstract

According to cancer reports from the past few years in India, thirty percent of instances are breast cancer, and furthermore, it is possible that this percentage would increase in the near future. In addition, one woman is given a diagnosis every two minutes, and another woman passes away every nine minutes as a result of her condition. People who are diagnosed with cancer at an earlier stage have a better chance of survival. Micro calcifications are one of the most important symptoms to look out for when trying to diagnose breast cancer in its earlier stages. Several scientific investigations have been carried out in an effort to combat this illness, for which techniques related to machine learning can be utilized to a significant extent. Particle swarm optimization, often known as PSO, is acknowledged as one of several effective and promising methods for identifying breast cancer. This method helps medical professionals administer treatment that is both timely and appropriate. The weighted particle swarm optimization (WPSO) approach is utilized in this work for the purpose of extracting textural information from the segmented mammography picture for the purpose of classifying micro calcifications as normal, benign, or malignant, hence increasing the accuracy. A portion of the cancerous growth is removed from the breast region using optimizing techniques. In this article, Convolutional Neural Networks (CNNs) are presented for the purpose of identifying breast cancer in order to cut down on the amount of manual overhead. The CNN framework is built in order to extract features as effectively as possible. This algorithm was developed to identify areas in mammograms (MG) that are suspicious for cancer and to classify those areas as normal or abnormal as quickly as possible. This model makes use of MG pictures that were gathered from a variety of hospitals in the surrounding area.