Deep learning-driven high-frequency ultrasound method for skin aging assessment_Journal of Biomedical Engineering

Authors：

ZHANG Xiaofang ¹ ,  HE Bingbing ¹ , SUN Dongjie ² , LI Haiyan ¹ , ZHANG Ningtao ³ , ZHANG Yufeng ¹

1. School of Information, Yunnan University, Kunming 650504, P. R. China;
2. Department of Dermatology, The First Affiliated Hospital of Kunming Medical University, Kunming 650032, P. R. China;
3. Yunnan Botanee Biotechnology Group Co., Kunming 650106, P. R. China;

Corresponding?author：

HE Bingbing, Email: hebingbing@ynu.edu.cn

Keywords：

Skin aging; High-frequency ultrasound; Global-aware temporal hierarchical network; Dual-enhanced attention mechanism; Multi-scale path dropout

DOI：

10.7507/1001-5515.202510021

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Ultraviolet radiation is a primary external factor contributing to skin photoaging, as it induces cellular deoxyribonucleic acid damage and collagen degeneration, thereby accelerating skin aging and increasing the risk of skin cancer. Currently, skin aging assessment mainly relies on dermatologists’ empirical judgment, which is inherently subjective and inefficient. To address these limitations, this study proposes a deep learning–driven intelligent skin aging classification method based on high-frequency ultrasound images. The proposed model employs efficient network version 2 (EfficientNetV2) as the backbone network and introduces the Gaussian error linear unit (GELU) activation function and layer normalization to enhance nonlinear feature representation and training stability. In addition, a global-aware temporal hierarchical network is integrated to enable efficient multi-scale feature extraction of skin tissue. A dual enhancement attention mechanism, combining parallel channel–spatial attention and squeeze-and-excitation modules, is further designed to improve the model’s sensitivity to key aging-related regions. Moreover, a multi-scale path dropout regularization strategy is adopted to effectively alleviate overfitting. Experiments conducted on a facial high-frequency ultrasound dataset collected from subjects aged 25~55 years demonstrate that the proposed method achieves an accuracy of 87.66%, a precision of 88.27%, a recall of 87.66%, an F1 score of 87.80%, and a specificity of 97.94%, consistently outperforming existing mainstream models. These results indicate that the proposed approach enables high-precision identification of skin aging levels and provides an efficient and objective auxiliary diagnostic tool for skincare, anti-aging treatment, and the prevention of photoaging-related skin diseases.

Citation： ZHANG Xiaofang, HE Bingbing, SUN Dongjie, LI Haiyan, ZHANG Ningtao, ZHANG Yufeng. Deep learning-driven high-frequency ultrasound method for skin aging assessment. Journal of Biomedical Engineering, 2026, 43(3): 487-495. doi: 10.7507/1001-5515.202510021 Copy

1.	Farage M A, Miller K W, Elsner P, et al. Characteristics of the aging skin. Adv Wound Care, 2013, 2(1): 5-10.
2.	Orentreich N, Selmanowitz V J. Section of biological and medical sciences: levels of biological functions with aging. Trans N Y Acad Sci, 1969, 31(8 Series II): 992-1012.
3.	Hussain F, Kayani H U R. Aging-oxidative stress, antioxidants and computational modeling. Heliyon, 2020, 6(5): e04107.
4.	Sarandy M M, Gon?alves R V, Valacchi G. Cutaneous redox senescence. Biomedicines, 2024, 12(2): 348.
5.	Uitto J. Understanding premature skin aging. N Engl J Med, 1997, 337(20): 1463-1465.
6.	堯阿敏, 歐陽夢婷, 溫磊, 等. 皮膚光老化發生機制研究進展. 皮膚科學通報, 2024, 41(5): 562-568.
7.	趙宇馨. 皮膚光老化機制及治療方法研究進展. 智慧健康, 2024, 10(22): 27-29.
8.	陳珩, 王玨, 周栩, 等. 紫外線輻射致皮膚老化機制的研究進展. 組織工程與重建外科, 2024, 20(3): 382-387.
9.	Robinson J K. Sun exposure, sun protection, and vitamin D. JAMA, 2005, 294(12): 1541-1543.
10.	Parkin D M, Mesher D, Sasieni P. Cancers attributable to solar (ultraviolet) radiation exposure in the UK in 2010. Br J Cancer, 2011, 105(2): S66-S69.
11.	Csekes E, Ra?ková L. Skin aging, cellular senescence and natural polyphenols. Int J Mol Sci, 2021, 22(23): 12641.
12.	La Padula S, Hersant B, Bompy L, et al. In search of a universal and objective method to assess facial aging: the new face objective photo-numerical assessment scale. J Craniomaxillofac Surg, 2019, 47(8): 1209-1215.
13.	李玲玉, 薛錦霞, 賀向前, 等. 基于機器視覺下的皮膚老化分級研究. 生物醫學工程學雜志, 2017, 34(3): 449-455.
14.	劉一洲, 王久存, 馬彥云. 利用無創測量表征人體面部皮膚老化表型. 上海醫藥, 2024, 45(11): 42-45.
15.	Moon C I, Lee O. Skin microstructure segmentation and aging classification using CNN-based models. IEEE Access, 2021, 9: 4948-4956.
16.	Dremin V, Marcinkevics Z, Zherebtsov E, et al. Skin complications of diabetes mellitus revealed by polarized hyperspectral imaging and machine learning. IEEE Trans Med Imaging, 2021, 40(4): 1207-1216.
17.	Lupu M, Malciu A M, Cozma E C, et al. The CSIESA: a novel score for the assessment of intrinsic and extrinsic skin aging based on reflectance confocal microscopy imaging. Diagnostics, 2022, 12(12): 3161.
18.	Tsai T H, Jee S H, Dong C Y, et al. Multiphoton microscopy in dermatological imaging. J Dermatol Sci, 2009, 56(1): 1-8.
19.	Vingan N R, Parsa S, Barillas J, et al. Evaluation and characterization of facial skin aging using optical coherence tomography. Lasers Surg Med, 2023, 55(1): 22-34.
20.	Assi A, Fischman S, Lopez C, et al. Evaluating facial dermis aging in healthy Caucasian females with LC-OCT and deep learning. Sci Rep, 2024, 14(1): 24113.
21.	Almuhanna N, Wortsman X, Wohlmuth-Wieser I, et al. Overview of ultrasound imaging applications in dermatology. J Cutan Med Surg, 2021, 25(5): 521-529.
22.	Negru?iu M, Danescu S, Popa T, et al. Ultrasound in non-tumoral pathology of the skin. Med Ultrason, 2023, 25(3): 330-339.
23.	Vargas E A T, Finato V M L, Azulay-Abulafia L, et al. Ultrasound of nails: why, how, when. Semin Ultrasound CT MRI, 2024, 45(3): 233-250.
24.	Mendes-Bastos P, Martorell A, Bettoli V, et al. The use of ultrasound and magnetic resonance imaging in the management of hidradenitis suppurativa: a narrative review. Br J Dermatol, 2023, 188(5): 591-600.
25.	Cavallieri F A, de Almeida Balassiano L K, Munhoz G, et al. Ultrasound in aesthetics: filler and non-filler applications. Semin Ultrasound CT MRI, 2024, 45(3): 251-263.
26.	Vergilio M M, Kiihl S F, Florindo J B, et al. Enhancing skin aging parameter assessment in clinical trials: AI-driven analysis of ultrasound images. Biomed Signal Process Control, 2025, 100: 106962.
27.	Pequeno A L V, Bagatin E. Dermatological ultrasound in assessing skin aging. Front Med, 2024, 11: 353605.
28.	De Rigal J, Escoffier C, Querleux B, et al. Assessment of aging of the human skin by in vivo ultrasonic imaging. J Invest Dermatol, 1989, 93(5): 621-625.
29.	Levy J, Barrett D L, Harris N, et al. High-frequency ultrasound in clinical dermatology: a review. Ultrasound J, 2021, 13(1): 24.
30.	Sciolla B, Delachartre P, Cowell L, et al. Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound. Comput Biol Med, 2017, 87: 302-310.
31.	Kia S, Setayeshi S, Shamsaei M, et al. Computer-aided diagnosis of the skin disease based on an intelligent classification of sonogram using neural network. Neural Comput Appl, 2013, 22(6): 1049-1062.
32.	Marosán-Vilimszky P, Szalai K, Horváth A, et al. Automated skin lesion classification on ultrasound images. Diagnostics, 2021, 11(7): 1207.
33.	Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation//IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe: IEEE, 2018: 1451-1460.
34.	Hu J, Shen L, Sun G. Squeeze-and-excitation networks//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City: IEEE, 2018: 7132-7141.
35.	Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module//European Conference on Computer Vision (ECCV), Munich: Springer, 2018: 3-19.
36.	Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2020: 11534-11542.

1. Farage M A, Miller K W, Elsner P, et al. Characteristics of the aging skin. Adv Wound Care, 2013, 2(1): 5-10.
2. Orentreich N, Selmanowitz V J. Section of biological and medical sciences: levels of biological functions with aging. Trans N Y Acad Sci, 1969, 31(8 Series II): 992-1012.
3. Hussain F, Kayani H U R. Aging-oxidative stress, antioxidants and computational modeling. Heliyon, 2020, 6(5): e04107.
4. Sarandy M M, Gon?alves R V, Valacchi G. Cutaneous redox senescence. Biomedicines, 2024, 12(2): 348.
5. Uitto J. Understanding premature skin aging. N Engl J Med, 1997, 337(20): 1463-1465.
6. 堯阿敏, 歐陽夢婷, 溫磊, 等. 皮膚光老化發生機制研究進展. 皮膚科學通報, 2024, 41(5): 562-568.
7. 趙宇馨. 皮膚光老化機制及治療方法研究進展. 智慧健康, 2024, 10(22): 27-29.
8. 陳珩, 王玨, 周栩, 等. 紫外線輻射致皮膚老化機制的研究進展. 組織工程與重建外科, 2024, 20(3): 382-387.
9. Robinson J K. Sun exposure, sun protection, and vitamin D. JAMA, 2005, 294(12): 1541-1543.
10. Parkin D M, Mesher D, Sasieni P. Cancers attributable to solar (ultraviolet) radiation exposure in the UK in 2010. Br J Cancer, 2011, 105(2): S66-S69.
11. Csekes E, Ra?ková L. Skin aging, cellular senescence and natural polyphenols. Int J Mol Sci, 2021, 22(23): 12641.
12. La Padula S, Hersant B, Bompy L, et al. In search of a universal and objective method to assess facial aging: the new face objective photo-numerical assessment scale. J Craniomaxillofac Surg, 2019, 47(8): 1209-1215.
13. 李玲玉, 薛錦霞, 賀向前, 等. 基于機器視覺下的皮膚老化分級研究. 生物醫學工程學雜志, 2017, 34(3): 449-455.
14. 劉一洲, 王久存, 馬彥云. 利用無創測量表征人體面部皮膚老化表型. 上海醫藥, 2024, 45(11): 42-45.
15. Moon C I, Lee O. Skin microstructure segmentation and aging classification using CNN-based models. IEEE Access, 2021, 9: 4948-4956.
16. Dremin V, Marcinkevics Z, Zherebtsov E, et al. Skin complications of diabetes mellitus revealed by polarized hyperspectral imaging and machine learning. IEEE Trans Med Imaging, 2021, 40(4): 1207-1216.
17. Lupu M, Malciu A M, Cozma E C, et al. The CSIESA: a novel score for the assessment of intrinsic and extrinsic skin aging based on reflectance confocal microscopy imaging. Diagnostics, 2022, 12(12): 3161.
18. Tsai T H, Jee S H, Dong C Y, et al. Multiphoton microscopy in dermatological imaging. J Dermatol Sci, 2009, 56(1): 1-8.
19. Vingan N R, Parsa S, Barillas J, et al. Evaluation and characterization of facial skin aging using optical coherence tomography. Lasers Surg Med, 2023, 55(1): 22-34.
20. Assi A, Fischman S, Lopez C, et al. Evaluating facial dermis aging in healthy Caucasian females with LC-OCT and deep learning. Sci Rep, 2024, 14(1): 24113.
21. Almuhanna N, Wortsman X, Wohlmuth-Wieser I, et al. Overview of ultrasound imaging applications in dermatology. J Cutan Med Surg, 2021, 25(5): 521-529.
22. Negru?iu M, Danescu S, Popa T, et al. Ultrasound in non-tumoral pathology of the skin. Med Ultrason, 2023, 25(3): 330-339.
23. Vargas E A T, Finato V M L, Azulay-Abulafia L, et al. Ultrasound of nails: why, how, when. Semin Ultrasound CT MRI, 2024, 45(3): 233-250.
24. Mendes-Bastos P, Martorell A, Bettoli V, et al. The use of ultrasound and magnetic resonance imaging in the management of hidradenitis suppurativa: a narrative review. Br J Dermatol, 2023, 188(5): 591-600.
25. Cavallieri F A, de Almeida Balassiano L K, Munhoz G, et al. Ultrasound in aesthetics: filler and non-filler applications. Semin Ultrasound CT MRI, 2024, 45(3): 251-263.
26. Vergilio M M, Kiihl S F, Florindo J B, et al. Enhancing skin aging parameter assessment in clinical trials: AI-driven analysis of ultrasound images. Biomed Signal Process Control, 2025, 100: 106962.
27. Pequeno A L V, Bagatin E. Dermatological ultrasound in assessing skin aging. Front Med, 2024, 11: 353605.
28. De Rigal J, Escoffier C, Querleux B, et al. Assessment of aging of the human skin by in vivo ultrasonic imaging. J Invest Dermatol, 1989, 93(5): 621-625.
29. Levy J, Barrett D L, Harris N, et al. High-frequency ultrasound in clinical dermatology: a review. Ultrasound J, 2021, 13(1): 24.
30. Sciolla B, Delachartre P, Cowell L, et al. Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound. Comput Biol Med, 2017, 87: 302-310.
31. Kia S, Setayeshi S, Shamsaei M, et al. Computer-aided diagnosis of the skin disease based on an intelligent classification of sonogram using neural network. Neural Comput Appl, 2013, 22(6): 1049-1062.
32. Marosán-Vilimszky P, Szalai K, Horváth A, et al. Automated skin lesion classification on ultrasound images. Diagnostics, 2021, 11(7): 1207.
33. Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation//IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe: IEEE, 2018: 1451-1460.
34. Hu J, Shen L, Sun G. Squeeze-and-excitation networks//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City: IEEE, 2018: 7132-7141.
35. Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module//European Conference on Computer Vision (ECCV), Munich: Springer, 2018: 3-19.
36. Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2020: 11534-11542.

Journal of Biomedical Engineering

Deep learning-driven high-frequency ultrasound method for skin aging assessment

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content