Use of digital pathology and artificial intelligence (AI) in breast cancer diagnosis and management: opportunities and challenges

Abstract

The application of digital pathology (DP) and artificial intelligence (AI) in pathology, including breast pathology, has advanced significantly in recent years, improving diagnosis, classification, grading, biomarker analysis, and lymph node assessment. AI techniques, such as convolutional neural networks (CNNs), have shown promise in automating these tasks, enhancing accuracy, and reducing interobserver variability. AI is used for classifying breast lesions, nodal assessment, predicting prognosis, and analysing biomarkers like oestrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2), which are essential in determining treatment options. This review explores the role of AI in breast cancer pathology and its potential to revolutionize diagnostic workflows and improve patient outcomes. It also highlights challenges, quality issues and considerations for pathologists introducing DP technology and AI algorithms.