Trustworthy Deep Feature Extraction and Ensemble-Based Machine Learning Approach for Breast Cancer Detections

Breast cancer (BC) has become a major public health concern and is critically associated with the highest global death rate for cancer detection. The diagnosis process and the techniques remain complex and often influenced by the diagnostician's background, which makes it challenging. Despite advancements in BC detection, existing methods cannot often effectively combine interpretability and high accuracy in complex imaging data, limiting their clinical applicability. This study proposes a reliable strategy for detecting BC by combining deep learning (DL) strengths with ensemble-based machine learning (ML) techniques. ML models offer interpretability and generalisation, while DL enhances the ability to learn and uncover hidden patterns in complicated BC images. The pre-trained model is used in the proposed technique for effective feature extraction, followed by applying eight different ML models to identify BC. The performance of the study is evaluated in terms of precision, recall, F1-score, and confusion matrices for all classifiers. In addition, ROC curves are drawn for each classifier. Our rigorous experimentation yields compelling results that demonstrate exceptional performance compared with those of existing state-of-the-art models. We achieve a higher accuracy rate of 97.50%, a precision of 97.15%, a recall of 97.00%, and an F1-score of 96.98%. Furthermore, we determine that the support vector classifier is the most effective ML model when integrated with the pre-trained VGG-16 architecture. The strategies, exhaustive performance analysis, and reliable assessment presented in this research provide valuable advances in BC detection, helping doctors make better decisions, offering better patient care, and improving BC outcomes.