ResNet Based Deep Feature Extraction for Classifier Performance Enhancement in Histopathological Breast Cancer Detection

Breast cancer detection in histopathological images is a crucial aspect of medical diagnostics, where accurate identification of cancerous tissues can impact patient outcomes. This study focuses on enhancing classifier performance by employing a ResNet based Deep representation-based method, specifically tailored for breast tumor detection. ResNet is utilized to automatically obtain high-level characteristics derived from histopathological images, which are then applied to train and evaluate various classifiers, including SVM, KNN, Decision Tree, Random Forest, and Extreme Gradient Boosting. The performance of the ResNet based approach is compared with GLCM, which captures textural information. The comparative analysis is conducted on a standardized dataset, and the results reveal that deep features extracted using ResNet significantly improve classifier efficiency in terms of precision and reliability. This research highlights the superiority of deep learning-based feature extraction over traditional methods, offering promising implications for the future of automated breast cancer detection in clinical settings.