Mass Classification of Breast Cancer Using CNN and Faster R-CNN Model Comparison

Abstract

Threat of breast cancer is a frightening type and threatens the female population worldwide. Early detection is preventive solution to determine cancer diagnosis or tumors in the female breast area. Today, machine learning technology in managing medical images has become an innovative trend in the health sector. This technology can accelerate diagnosing disease based on the acquisition of accuracy values. The primary purpose of this research is to innovate by comparing two deep learning models to build a prediction system for early-stage breast cancer. This research utilizes Convolutional Neural Network (CNN) sequential models and Faster Region-based Convolutional Neural Network (R-CNN) models that can determine the classification of normal or abnormal breast image data, which can determine the normal or abnormal classification of breast image. The dataset's source in this study came from the Mammographic Image Analysis Society (MIAS). This dataset consists of 322 mammogram data with 123 abnormal and 199 normal classes. The experimental results of this study show that the accuracy of the CNN and R-CNN models in image classification are 91.26% and 63.89%, respectively. Based on these results, the CNN sequential model has better accuracy than the Faster R-CNN model, because it does not require unique characteristics to detect breast cancer.