Leveraging AI for the Next Era of Precision Oncology in Breast Cancer Detection

Abstract: Cutting-edge progress in ML and DL techniques has led to substantial gains in the accuracy and reliability of breast cancer diagnostic systems. Conventional diagnostic means could have limited sensitivity and can be subjective; therefore, AI supported Computer-Aided Diagnosis (CAD) systems are introduced to overcome these issues. This review summarizes developments from 2022–2025 in ML and DL techniques applied to mammography, ultrasound, MRI, histopathology, and thermography. Deep learning methods, with convolutional neural networks at the forefront, have achieved notable accuracy across multiple imaging types, while emerging trends such as radiomics, deep reinforcement learning, hybrid ML–DL frameworks, and explainable AI (XAI) further enhance diagnostic performance and clinical trust. Challenges including data scarcity, model interpretability, and generalization remain, with promising solutions found in self-supervised learning, federated learning, and foundation models. These advancements collectively support earlier detection, improved treatment planning, and the advancement of precision oncology.

Keywords: Breast cancer detection, machine learning, deep learning, CNN, CAD systems, radiomics, explainable AI, federated learning