Breast Cancer Diagnosis with AI Technologies

The integration of advanced technologies in healthcare has opened new pathways for improving disease detection and diagnosis. Among the others, Breast Cancer (BC) indeed is one of the biggest concerns worldwide, and its early and precise diagnosis is indispensable. The present paper gives an overview of the introduction of modern machinery, such as ML, DL, IoT, blockchain, cloud computing, and data mining, to aid the detection of BC. By systematically reviewing the contemporary literature, we point out the advances accomplished in the application of AI-assisted techniques in the monitoring and diagnosing of BC, whilst at the same time discussing the ongoing issues. Several ML algorithms are examined in detail, whereas the spotlight is on deep learning approaches such as CNNs and RNNs, which are known to be very effective in interpreting medical images. We examine the performance of models such as CNNs (both self-trained and those employing transfer learning), SPWO-based Deep Maxout networks, ShCNN (utilizing FACS features), and GRU-based RNNs across different publicly available datasets. Our findings aim to provide valuable insights for researchers and healthcare professionals by outlining current trends and evaluating the effectiveness of AI-based approaches. The review emphasizes the growing role of intelligent systems in supporting early diagnosis and improving treatment planning for breast cancer patients.