With the advancement of modern medicine and engineering, breast deformation analysis has become increasingly important in the fields such as cosmetic surgery, reconstructive surgery, sports biomechanics, and health-related research. The morphological changes in breast tissue not only affect an individual's aesthetic appearance and mental well-being but are also closely linked to breast health. Finite Element Method (FEM) and Machine Learning (ML) are two advanced technologies that exhibit significant potential in breast deformation analysis. FEM plays a crucial role in modeling the mechanical behavior of breast soft tissues and analyzing deformations due to its precise numerical solutions and realistic simulation capabilities. On the other hand, machine learning techniques provide new perspectives for personalized health management and disease risk assessment by processing large-scale breast morphology data to uncover patterns and correlations. This paper reviews the latest advancements in the application of FEM and ML in breast tissue morphology analysis, explores their potential and challenges in simulating both static and dynamic breast deformations in clinical practice, and summarizes the characteristics and application scenarios of both technologies. This paper discusses the novel opportunities brought by the integration of these two approaches for the clinical diagnosis and analysis of breast-related diseases. It synthesizes these developments and explores the potential benefits of methodological integration for future breast morphology-related research and clinical applications.
Yu et al. (2026) studied this question.