Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery
BackgroundEarly detection of periocular aging is a common concern in cosmetic surgery. Traditional diagnostic and treatment methods often require hospital visits and consultations with plastic surgeons, which are costly and time-consuming. This study aims to develop and evaluate an AI-based decision...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-03-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2025.1532195/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849706054091276288 |
|---|---|
| author | Xiang Lian Xiang Lian Xiang Lian Xin Hu Guannan Li Siqi Wu Yihao Liu Ke Qin Kai Liu Kai Liu Kai Liu |
| author_facet | Xiang Lian Xiang Lian Xiang Lian Xin Hu Guannan Li Siqi Wu Yihao Liu Ke Qin Kai Liu Kai Liu Kai Liu |
| author_sort | Xiang Lian |
| collection | DOAJ |
| description | BackgroundEarly detection of periocular aging is a common concern in cosmetic surgery. Traditional diagnostic and treatment methods often require hospital visits and consultations with plastic surgeons, which are costly and time-consuming. This study aims to develop and evaluate an AI-based decision-making system for periocular cosmetic surgery, utilizing a Hierarchical Attention Transformer (HATrans) model designed for multi-label classification in periocular conditions, allowing for home-based early aging identification.MethodsThis cross-sectional study was conducted at the Department of Plastic and Reconstructive Surgery at Shanghai Jiao Tong University School of Medicine’s Ninth People’s Hospital from September 1, 2010, to April 30, 2024. The study enhanced the Vision Transformer (ViT) by adding two specialized branches: the Region Recognition Branch for foreground area identification, and the Patch Recognition Branch for refined feature representation via contrastive learning. These enhancements allowed for better handling of complex periocular images.ResultsThe HATrans model significantly outperformed baseline architectures such as ResNet and Swin Transformer, achieving superior accuracy, sensitivity, and specificity in identifying periocular aging. Ablation studies demonstrated the critical role of the hierarchical attention mechanism in distinguishing subtle foreground-background differences, improving the model’s performance in smartphone-based image analysis.ConclusionThe HATrans model represents a significant advancement in multi-label classification for facial aesthetics, offering a practical solution for early periocular aging detection at home. The model’s robust performance supports its potential for assisting clinical decision-making in cosmetic surgery, facilitating accessible and timely treatment recommendations. |
| format | Article |
| id | doaj-art-bf26f35488b643d9a7f6c75cf891b04e |
| institution | DOAJ |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-bf26f35488b643d9a7f6c75cf891b04e2025-08-20T03:16:18ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-03-011210.3389/fmed.2025.15321951532195Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgeryXiang Lian0Xiang Lian1Xiang Lian2Xin Hu3Guannan Li4Siqi Wu5Yihao Liu6Ke Qin7Kai Liu8Kai Liu9Kai Liu10Department of Plastic and Reconstructive Surgery, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaShanghai Key Laboratory of Tissue Engineering, Shanghai Ninth People’s Hospital, National Tissue Engineering Center of China, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaShanghai Institute for Plastic and Reconstructive Surgery, Shanghai, ChinaUniversity of Electronic Science and Technology of China, Chengdu, Sichuan, ChinaUniversity of Electronic Science and Technology of China, Chengdu, Sichuan, ChinaDepartment of Plastic and Reconstructive Surgery, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaEcole Polytechnique, Institut Polytechnique de Paris, Palaiseau, FranceUniversity of Electronic Science and Technology of China, Chengdu, Sichuan, ChinaDepartment of Plastic and Reconstructive Surgery, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaShanghai Key Laboratory of Tissue Engineering, Shanghai Ninth People’s Hospital, National Tissue Engineering Center of China, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaShanghai Institute for Plastic and Reconstructive Surgery, Shanghai, ChinaBackgroundEarly detection of periocular aging is a common concern in cosmetic surgery. Traditional diagnostic and treatment methods often require hospital visits and consultations with plastic surgeons, which are costly and time-consuming. This study aims to develop and evaluate an AI-based decision-making system for periocular cosmetic surgery, utilizing a Hierarchical Attention Transformer (HATrans) model designed for multi-label classification in periocular conditions, allowing for home-based early aging identification.MethodsThis cross-sectional study was conducted at the Department of Plastic and Reconstructive Surgery at Shanghai Jiao Tong University School of Medicine’s Ninth People’s Hospital from September 1, 2010, to April 30, 2024. The study enhanced the Vision Transformer (ViT) by adding two specialized branches: the Region Recognition Branch for foreground area identification, and the Patch Recognition Branch for refined feature representation via contrastive learning. These enhancements allowed for better handling of complex periocular images.ResultsThe HATrans model significantly outperformed baseline architectures such as ResNet and Swin Transformer, achieving superior accuracy, sensitivity, and specificity in identifying periocular aging. Ablation studies demonstrated the critical role of the hierarchical attention mechanism in distinguishing subtle foreground-background differences, improving the model’s performance in smartphone-based image analysis.ConclusionThe HATrans model represents a significant advancement in multi-label classification for facial aesthetics, offering a practical solution for early periocular aging detection at home. The model’s robust performance supports its potential for assisting clinical decision-making in cosmetic surgery, facilitating accessible and timely treatment recommendations.https://www.frontiersin.org/articles/10.3389/fmed.2025.1532195/fullperiocular agingHierarchical Attention Transformer (HATrans)AI-based decision-makingmulti-label classificationlower blepharoplastydouble eyelid surgery |
| spellingShingle | Xiang Lian Xiang Lian Xiang Lian Xin Hu Guannan Li Siqi Wu Yihao Liu Ke Qin Kai Liu Kai Liu Kai Liu Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery Frontiers in Medicine periocular aging Hierarchical Attention Transformer (HATrans) AI-based decision-making multi-label classification lower blepharoplasty double eyelid surgery |
| title | Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery |
| title_full | Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery |
| title_fullStr | Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery |
| title_full_unstemmed | Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery |
| title_short | Hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery |
| title_sort | hierarchical attention transformer provides assistant suggestions for orbital rejuvenation surgery |
| topic | periocular aging Hierarchical Attention Transformer (HATrans) AI-based decision-making multi-label classification lower blepharoplasty double eyelid surgery |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2025.1532195/full |
| work_keys_str_mv | AT xianglian hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT xianglian hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT xianglian hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT xinhu hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT guannanli hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT siqiwu hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT yihaoliu hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT keqin hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT kailiu hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT kailiu hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery AT kailiu hierarchicalattentiontransformerprovidesassistantsuggestionsfororbitalrejuvenationsurgery |