Breast Cancer Diagnosis Model Based on Convolutional Neural Networks’ Multiple Architectures.

Abstract

In year 2020, the World Health Organization (WHO) estimates that 2.3 million women worldwide were diagnosed of breast cancer, which resulted in 685,000 deaths. According to projections, the number of women who have been diagnosed with breast cancer over the last five years before and by the end of 2020 was expected to reach 7.8 million, making it the most common type of cancers worldwide. Early diagnosis could prevent the ailment however, lack of availability of health facilities, cost of accessing treatment especially in developing nations are among the challenges confronting the solution. With the advent of artificial intelligence, and machine learning models, specifically, Convolutional Neural Networks (CNNs) considering its multiple architectures is highly promising to address the challenge of early diagnosis. Therefore, this research aims to proposed an architecture of CNNs that gives the best accuracy, F1 score, and Cohen Kappa score among Custom Optimized CNN, ResNet, EfficientNet architectures being considered in this work. From the results, ResNet’s performance across the five metrics outweigh the other two architectures. While ResNet reported an accuracy, precision, and F1 score of 0.9987, 0.9934, and 0.9950 respectively, EfficientNet, which has the second performance reported 0.9977, 0.9914, and 0.9939 as accuracy, precision, and F1 score respectively. Therefore, the best performing architecture can be deployed for other available breast cancer datasets in order to ensure its total efficiency.