Explainable Artificial Intelligence Methods for Breast Cancer Recognition

Abstract

Breast cancer remains a leading cause of cancer-related mortality among women worldwide, necessitating early and accurate detection for effective treatment and improved survival rates. Artificial intelligence (AI) has shown significant potential in enhancing the diagnostic and prognostic capabilities in breast cancer recognition. However, the black-box nature of many AI models poses challenges for their clinical adoption due to the lack of transparency and interpretability. Explainable AI (XAI) methods address these issues by providing human-understandable explanations of AI models’ decision-making processes, thereby increasing trust, accountability, and ethical compliance. This review explores the current state of XAI methods (Local Interpretable Model-agnostic Explanations, Shapley Additive explanations, Gradient-weighted Class Activation Mapping) in breast cancer recognition, detailing their applications in various tasks such as classification, detection, segmentation, prognosis, and biomarker discovery. By integrating domain-specific knowledge and developing visualization techniques, XAI methods enhance the usability and interpretability of AI systems in clinical settings. The study also identifies the key challenges and future directions in the evaluation of XAI methods, the development of standardized metrics, and the seamless integration of XAI into clinical workflows.