Klasifikasi Kanker Payudara Berbasis Citra MRI Menggunakan Ektraksi Fitur Convolutional Neural Network (CNN) Berbasis ResNet50

Abstract

Breast cancer is one of the most prevalent types of cancer and a leading cause of death among women worldwide. Delayed diagnosis remains a major issue due to the limitations of conventional detection methods. One potential approach to overcome this problem is through the analysis of breast MRI images using deep learning techniques. This study aims to develop a breast cancer classification system based on MRI images by utilizing the Convolutional Neural Network (CNN) architecture, specifically ResNet50. The MRI dataset was obtained from the Kaggle platform and categorized into two classes: cancerous and non-cancerous. Transfer learning was employed to optimize the model training process, and evaluation was carried out using Stratified K-Fold Cross-Validation with five folds to ensure more objective and balanced assessment. The results show that the CNN model based on ResNet50 is capable of classifying breast cancer MRI images with an average accuracy of 97.27%, along with high precision, recall, and F1-Score values. These findings indicate that the deep learning approach is effective in improving the accuracy of breast cancer diagnosis and can serve as a foundation for the development of clinical decision support systems.