Label-independent framework for objective evaluation of cosmetic outcome in breast cancer

Sangjoon Park; Yong Bae Kim; Jee Suk Chang; Seo Hee Choi; Hyungjin Chung; Ik Jae Lee; Hwa Kyung Byun

doi: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.

YUHSpace

BROWSE

0 0

Cited 0 times in

Label-independent framework for objective evaluation of cosmetic outcome in breast cancer

Authors: Sangjoon Park ; Yong Bae Kim ; Jee Suk Chang ; Seo Hee Choi ; Hyungjin Chung ; Ik Jae Lee ; Hwa Kyung Byun

Citation: ARTIFICIAL INTELLIGENCE IN MEDICINE, Vol.167 : 103179, 2025-09

Journal Title: ARTIFICIAL INTELLIGENCE IN MEDICINE

ISSN: 0933-3657

Issue Date: 2025-09

MeSH: 1

Keywords: Breast Neoplasms* / diagnostic imaging ; Breast Neoplasms* / surgery ; Female ; Humans ; Image Processing, Computer-Assisted* / methods ; Quality of Life

Abstract: Anomaly detection; Breast cosmesis; Diffusion model; Vision transformer

Article Number: 10.1016/j.artmed.2025.103179

DOI: 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.

Appears in Collections:: 1. College of Medicine (의과대학) > Dept. of Radiation Oncology (방사선종양학교실) > 1. Journal Papers

Yonsei Authors: Kim, Yong Bae(김용배) https://orcid.org/0000-0001-7573-6862
Park, Sang Joon(박상준)
Byun, Hwa Kyung(변화경) https://orcid.org/0000-0002-8964-6275
Lee, Ik Jae(이익재) https://orcid.org/0000-0001-7165-3373
Chang, Jee Suk(장지석) https://orcid.org/0000-0001-7685-3382
Choi, Seo Hee(최서희) https://orcid.org/0000-0002-4083-6414

URI: https://ir.ymlib.yonsei.ac.kr/handle/22282913/207410

사서에게 알리기

Show full item record Find it @ YMLIB

License

YUHSpace: Label-independent framework for objective evaluation of cosmetic outcome in breast cancer

YUHSpace

BROWSE

Browse

Links