Recent Advancements in Machine Learning and Deep Learning for Early Detection of Breast Cancer: A Comprehensive Review

• Comprehensive review of Machine Learning (ML) and Deep Learning (DL) approaches for breast cancer detection and classification (2020–2025). • The study categorizes approaches into two major groups: ML-based and DL-based methodologies. • ML-based approaches include traditional algorithms such as SVM, Random Forest, k-NN, and ensemble techniques with feature engineering. • DL-based approaches are further classified by imaging modality: ultrasound, histopathological images, thermal imaging , and mammograms . • Identification of current trends, key challenges (e.g., data imbalance, model interpretability), and limitations in existing research. • Discussion on potential future directions including explainable AI, data fusion, and real-time clinical integration. Breast cancer remains one of the most prevalent and life-threatening diseases affecting women globally. Early and accurate detection is crucial for effective treatment and improved survival rates. In recent years, Machine Learning (ML) and Deep Learning (DL) techniques have shown significant promise in enhancing the accuracy, speed, and reliability of breast cancer diagnosis and classification. This review presents a comprehensive analysis and quality assessment of research studies published between 2020 and 2025, evaluating dataset representativeness, reference standards, validation methodology, and risk of bias using adapted QUADAS-AI Framework, focusing on ML and DL-based approaches applied to breast cancer detection and classi-fication. We categorize the reviewed literature based on the type of input data (e.g., mammograms, histopathological images, ultrasound, and clinical data), learning models (such as Support Vector Machines, Random Forests, Convolutional Neural Networks, and Transformers), and performance metrics used. Additionally, we highlight key trends, challenges, and innovations, including the rise of hybrid models, transfer learning, and explainable AI in medical diagnostics. This review aims to provide researchers and clinicians with a structured understanding of the recent advancements and future directions in AI-driven breast cancer diagnostics.