Explainable deep learning reveals a stagewise temporal deterioration from skin tone to contour to texture in Chinese women’s skin aging

深度学习 人工智能 模式识别(心理学) 皮肤老化 混淆矩阵 计算机科学 面子(社会学概念) 纹理(宇宙学) 混乱 主动外观模型 过程(计算) 计算机视觉 健康衰老 机器学习 主成分分析 面部识别系统
作者
Guo-long Dong,Fan Hu,Ya-wen Liu,Xiao Wei-zhen,Fan Yi,Chen-juan Zhang,Rui-min Liu,Yue Wu
出处
期刊:Frontiers in Medicine [Frontiers Media]
卷期号:13: 1945376-1945376
标识
DOI:10.3389/fmed.2026.1945376
摘要

Skin aging is a continuous and progressive physiological process characterized by gradual structural and functional changes. Early identification and accurate assessment of aging-related facial features are essential for developing targeted skincare strategies. This study aimed to establish a deep learning-based framework combined with Shapley Additive Explanations (SHAP) analysis to classify facial aging stages in Chinese women and provide interpretable evidence for personalized skincare. A total of 300 Chinese women aged 18-60 years were included. Standardized facial images were acquired using the VISIA imaging system. Four dimensions, including tone, contour, texture, and porphyrin, were evaluated, and 23 facial indicators were extracted. A hybrid multimodal deep learning classification model was developed by integrating facial image data with quantitative facial aging indicators. Five-fold stratified cross-validation was performed to evaluate model performance, with Top-2 accuracy used as the primary evaluation metric. SHAP analysis was further applied to assess the contribution weights of different facial aging indicators to model predictions. Based on the fitted quantitative facial aging indicators, a six-class facial aging classification model was established. The model demonstrated stable convergence and achieved a highest validation Top-2 accuracy of 85.0%. The confusion matrix showed that classification errors occurred primarily between adjacent aging stages. SHAP analysis revealed a progressive aging pattern characterized by early changes in skin color, middle-stage changes in facial contour, and later deterioration in skin texture. This study demonstrates that integrating deep learning with SHAP analysis can effectively classify facial aging stages in Chinese women while providing interpretable insights into the key features driving aging-related predictions.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
caoshanyu完成签到,获得积分20
刚刚
刚刚
海绵发布了新的文献求助10
刚刚
刚刚
jjjj完成签到,获得积分10
刚刚
刚刚
隐形曼青的应助被瘦瘦青文采纳,获得10
刚刚
null的应助被TMEDA采纳,获得10
刚刚
刚刚
Jasper的应助被timi2026采纳,获得10
刚刚
zy完成签到,获得积分10
刚刚
粟禾发布了新的文献求助10
1秒前
玥洋完成签到 ,获得积分10
1秒前
ZYC007发布了新的文献求助10
1秒前
hua发布了新的文献求助10
1秒前
平淡语薇发布了新的文献求助10
1秒前
1秒前
Austin发布了新的文献求助10
1秒前
1秒前
kaka完成签到,获得积分10
2秒前
2秒前
2秒前
备注发布了新的文献求助10
2秒前
2秒前
2秒前
情怀的应助被六金采纳,获得10
2秒前
芋泥泥泥完成签到,获得积分10
2秒前
酷波er的应助被楠木木采纳,获得10
3秒前
心灵美的清完成签到,获得积分10
3秒前
YHY完成签到,获得积分10
3秒前
高芷完成签到 ,获得积分10
3秒前
yuan完成签到,获得积分10
4秒前
WbinWu完成签到,获得积分10
4秒前
4秒前
sufu_jony的应助被nyiboyj采纳,获得30
4秒前
xucc发布了新的文献求助10
4秒前
浮云发布了新的文献求助10
5秒前
5秒前
一条蚂蚁完成签到,获得积分10
6秒前
CodeCraft的应助被任某人采纳,获得10
6秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
Resource Recovery Handbook 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8175943
求助须知:如何正确求助?哪些是违规求助? 9567501
关于积分的说明 21793186
捐赠科研通 7770490
什么是DOI,文献DOI怎么找? 3431935
关于科研通互助平台的介绍 2556294
邀请新用户注册赠送积分活动 2477485