With advancements in the field of breast cancer treatment, the assessment of postsurgical cosmetic outcomes has gained increasing significance owing to its substantial impact on patients' quality of life. However, evaluating breast cosmesis is challenging because of the inherently subjective nature of expert labeling. In this study, we present a novel automated approach, attention-guided denoising diffusion anomaly detection (AG-DDAD), designed to assess breast cosmesis following surgery. The model addresses the limitations of conventional supervised learning and existing anomaly detection models. Our approach leverages the attention mechanism of distillation with no labels and a self-supervised vision transformer, combined with a diffusion model, to achieve high-quality image reconstruction and precise transformation of discriminative regions. By training the diffusion model on unlabeled data, predominantly with normal cosmesis, we adopted an unsupervised anomaly detection perspective to automatically score the cosmesis. Real-world data experiments demonstrated the effectiveness of our method, providing visually appealing representations and quantifiable scores for cosmesis evaluation. Compared with commonly used rule-based programs, our fully automated approach eliminates the need for manual annotations and offers an objective evaluation. Moreover, our anomaly detection model exhibits state-of-the-art performance, surpassing existing models in terms of accuracy. Beyond the scope of breast cosmesis, our research represents a significant advancement in unsupervised anomaly detection within the medical domain, thereby paving the way for future investigations.
Keywords: Anomaly detection; Breast cosmesis; Diffusion model; Vision transformer.
Copyright © 2025. Published by Elsevier B.V.