Artificial Intelligence for Early Detection and Diagnosis of Breast Cancer: A Systematic Review of Machine Learning and Deep Learning Approaches

Breast cancer remains one of the leading causes of cancer-related mortality among women globally, highlighting the critical need for early detection and accurate diagnosis. Recent advances in artificial intelligence (AI), encompassing both machine learning (ML) and deep learning (DL) approaches, have demonstrated significant potential in enhancing diagnostic accuracy, reducing human error, and supporting clinical decision-making. This systematic review critically analyzes existing studies that employ AI for breast cancer detection, focusing on methodological approaches, dataset characteristics, model performance, and interpretability. ML-based techniques, including support vector machines, random forests, and gradient boosting, show promising results in structured datasets, particularly where dataset sizes are limited, and interpretability is essential. In contrast, DL approaches, primarily convolutional neural networks and their variants, outperform ML in raw image analysis, multi-modal imaging, and complex feature extraction, achieving higher accuracy and sensitivity. Hybrid models integrating ML and DL, often augmented with radiomics features, offer a balanced framework, combining high predictive performance with improved interpretability. Additionally, explainable AI (XAI) techniques are increasingly applied to DL models, mitigating the “black-box” problem and fostering clinical trust. Despite these advancements, challenges remain, including the need for large, high-quality, multi-institutional datasets, computational resource demands, and generalizability across diverse populations. Low-resource and portable AI solutions offer potential for broader accessibility, though with modest reductions in predictive performance. Overall, AI demonstrates transformative potential in early breast cancer detection, particularly when combined with hybrid and explainable frameworks. Future research should prioritize multi-modal integration, rigorous cross-center validation, and deployment strategies that balance accuracy, interpretability, and accessibility, ultimately facilitating clinical adoption and improving patient outcomes.