Research progress on intelligent diagnosis of eye diseases based on facial photos

doi:10.3969/j.issn.1674-8115.2025.09.017

Abstract

Abstract:

The number of patients with eye diseases in China is enormous, and the negative effects of these conditions, such as impaired visual function, psychological burdens, and restricted social participation, are becoming increasingly severe. Due to the limited and unevenly distributed ophthalmic resources, and the significant limitations of traditional diagnostic and therapeutic approaches in terms of accuracy and efficiency, there is an urgent need for more sensitive and efficient modalities. With the rapid advancement of artificial intelligence technology, ophthalmic diagnosis has entered a new stage of intelligent transformation. Facial photos, as a noninvasive and convenient medium, show unique advantages in eye disease diagnosis. Artificial intelligence systems based on facial photo analysis have been applied to the screening and diagnosis of conditions such as myopia, strabismus, ptosis, and thyroid eye disease, showing promising results. This review introduces the workflow of intelligent diagnosis for ocular diseases based on facial photographs, with a focus on recapitulating relevant research findings both domestically and internationally in recent years. It summarizes the innovative features and application advantages of intelligent diagnosis systems for eye diseases based on facial photos, analyzes the current technical bottlenecks and challenges in application, proposes corresponding countermeasures, and discusses future development directions, aiming to provide references and new insights for the intelligent screening and diagnosis of eye diseases.

Key words: eye disease, artificial intelligence, diagnosis, face, photo

CLC Number:

XU Hanwen, CHEN Moxin, LIANG Xiaoyi, SHU Qin, NIE Wanqin, YANG Xuefeng, SHEN Minxuan, LI Xiaojing, CAO Yu, LI Lin. Research progress on intelligent diagnosis of eye diseases based on facial photos[J]. Journal of Shanghai Jiao Tong University (Medical Science), 2025, 45(9): 1249-1255.

TrendMD

References 39

[1]	陈彬彬, 楼丽霞, 叶娟. 中国眼病疾病负担现状及三十年变化趋势[J]. 浙江大学学报(医学版), 2021, 50(4): 420-428.
	CHEN B B, LOU L X, YE J. Eye diseases burden in China in the past 30 years[J]. Journal of Zhejiang University(Medical Sciences), 2021, 50(4): 420-428.
[2]	陈健祺, 李睿扬, 林铎儒, 等. 人工智能在眼病筛查和诊断中的研究进展[J]. 眼科学报, 2022, 37(3): 208-213.
	CHEN J Q, LI R Y, LIN D R, et al. Research progress of artificial intelligence in screening and diagnosis of eye diseases[J]. Eye Science, 2022, 37(3): 208-213.
[3]	杨安, 杨莉梅, 张志芳, 等. 基于人工智能的眼科学新进展[J]. 中国数字医学, 2023, 18(12): 68-73.
	YANG A, YANG L M, ZHANG Z F, et al. New advances of ophthalmology based on artificial intelligence[J]. China Digital Medicine, 2023, 18(12): 68-73.
[4]	LI Z W, WANG L, WU X F, et al. Artificial intelligence in ophthalmology: the path to the real-world clinic[J]. Cell Rep Med, 2023, 4(7): 101095.
[5]	LEI C Y, DANG K, SONG S F, et al. AI-assisted facial analysis in healthcare: from disease detection to comprehensive management[J]. Patterns (N Y), 2025, 6(2): 101175.
[6]	陈军, 何鲜桂, 王菁菁, 等. 2021至2030年我国6~18岁学生近视眼患病率预测分析[J]. 中华眼科杂志, 2021, 57(4): 261-267.
	CHEN J, HE X G, WANG J J, et al. Forcasting the prevalence of myopia among students aged 6‒18 years in China from 2021 to 2030[J]. Chinese Journal of Ophthalmology, 2021, 57(4): 261-267.
[7]	SHU Q, PANG J L, LIU Z J, et al. Artificial intelligence for early detection of pediatric eye diseases using mobile photos[J]. JAMA Netw Open, 2024, 7(8): e2425124.
[8]	PAVONE P, CHO S Y, PRATICÒ A D, et al. Ptosis in childhood: a clinical sign of several disorders: case series reports and literature review[J]. Medicine (Baltimore), 2018, 97(36): e12124.
[9]	SOOHOO J R, DAVIES B W, ALLARD F D, et al. Congenital ptosis[J]. Surv Ophthalmol, 2014, 59(5): 483-492.
[10]	WANG Y J, XU Y F, LIU X, et al. Amblyopia, strabismus and refractive errors in congenital ptosis: a systematic review and meta-analysis[J]. Sci Rep, 2018, 8(1): 8320.
[11]	YANG Y H, LI R Y, LIN D R, et al. Automatic identification of myopia based on ocular appearance images using deep learning[J]. Ann Transl Med, 2020, 8(11): 705.
[12]	QI Z Y, LI T Y, CHEN J, et al. A deep learning system for myopia onset prediction and intervention effectiveness evaluation in children[J]. NPJ Digit Med, 2024, 7(1): 206.
[13]	CHEN W B, LI R Y, YU Q J, et al. Early detection of visual impairment in young children using a smartphone-based deep learning system[J]. Nat Med, 2023, 29(2): 493-503.
[14]	雷超宇, 王慧, 赵辰, 等. 眼部疾病诊断评估的面部图像采集规范探讨[J]. 数字医学与健康, 2024, 2(4): 219-223.
	LEI C Y, WANG H, ZHAO C, et al. Standards in the collection of facial images for the diagnosis and assessment of ocular diseases[J]. Digital Medicine and Health, 2024, 2(4): 219-223.
[15]	ANTON N, DOROFTEI B, CURTEANU S, et al. Comprehensive review on the use of artificial intelligence in ophthalmology and future research directions[J]. Diagnostics (Basel), 2022, 13(1): 100.
[16]	HUI S Q, XIE J, DONG L, et al. Deep learning-based mobile application for efficient eyelid tumor recognition in clinical images[J]. NPJ Digit Med, 2025, 8(1): 185.
[17]	QIANG J Q, WU D N, DU H Z, et al. Review on facial-recognition-based applications in disease diagnosis[J]. Bioengineering (Basel), 2022, 9(7): 273.
[18]	YARKHEIR M, SADEGHI M, AZARNOUSH H, et al. Automated strabismus detection and classification using deep learning analysis of facial images[J]. Sci Rep, 2025, 15(1): 3910.
[19]	LI Z W, LIU F, YANG W J, et al. A survey of convolutional neural networks: analysis, applications, and prospects[J]. IEEE Trans Neural Netw Learn Syst, 2022, 33(12): 6999-7019.
[20]	SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. Int J Comput Vis, 2020, 128(2): 336-359.
[21]	ZHENG C, YAO Q, LU J W, et al. Detection of referable horizontal strabismus in children's primary gaze photographs using deep learning[J]. Transl Vis Sci Technol, 2021, 10(1): 33.
[22]	NAM Y, SONG T, LEE J, et al. Development of a neural network-based automated eyelid measurement system[J]. Sci Rep, 2024, 14(1): 1202.
[23]	LOU L X, CAO J, WANG Y Q, et al. Deep learning-based image analysis for automated measurement of eyelid morphology before and after blepharoptosis surgery[J]. Ann Med, 2021, 53(1): 2278-2285.
[24]	韦怡宁, 周慧芳. 《ATA/ETA甲状腺眼病管理共识》解读[J]. 中华实验眼科杂志, 2023, 41(11): 1111-1114.
	WEI Y N, ZHOU H F. Interpretation of management of thyroid eye disease: a consensus statement by the American Thyroid Association and the European Thyroid Association[J]. Chinese Journal of Experimental Ophthalmology, 2023, 41(11): 1111-1114.
[25]	HUANG X, JU L, LI J, et al. An intelligent diagnostic system for thyroid-associated ophthalmopathy based on facial images[J]. Front Med (Lausanne), 2022, 9: 920716.
[26]	KARLIN J, GAI L S, LAPIERRE N, et al. Ensemble neural network model for detecting thyroid eye disease using external photographs[J]. Br J Ophthalmol, 2023, 107(11): 1722-1729.
[27]	GUROVICH Y, HANANI Y, BAR O, et al. Identifying facial phenotypes of genetic disorders using deep learning[J]. Nat Med, 2019, 25(1): 60-64.
[28]	AANJANKUMAR S, SATHYAMOORTHY M, DHANARAJ R K, et al. Prediction of malnutrition in kids by integrating ResNet-50-based deep learning technique using facial images[J]. Sci Rep, 2025, 15: 7871.
[29]	LIN S, LI Z G, FU B W, et al. Feasibility of using deep learning to detect coronary artery disease based on facial photo[J]. Eur Heart J, 2020, 41(46): 4400-4411.
[30]	WEI R, JIANG C D, GAO J, et al. Deep-learning approach to automatic identification of facial anomalies in endocrine disorders[J]. Neuroendocrinology, 2020, 110(5): 328-337.
[31]	ROUXEL F, YAUY K, BOURSIER G, et al. Using deep-neural-network-driven facial recognition to identify distinct Kabuki syndrome 1 and 2 gestalt[J]. Eur J Hum Genet, 2022, 30(6): 682-686.
[32]	刘陇黔, 吴达文. 人工智能在眼病筛查和诊断应用中的挑战与展望[J]. 中华眼科杂志, 2024, 60(6): 484-489.
	LIU L Q, WU D W. Challenges and prospects in the application of artificial intelligence for ocular disease screening and diagnosis[J]. Chinese Journal of Ophthalmology, 2024, 60(6): 484-489.
[33]	李飞, 梁晓莹, 汪德明, 等. 眼科AI诊断:真实世界中的挑战与解决方案[J]. 科学观察, 2025, 20(1): 1-21.
	LI F, LIANG X Y, WANG D M, et al. Ophthalmic AI diagnostics: challenges and solutions in the real world[J]. Science Focus, 2025, 20(1): 1-21.
[34]	LI W T, YANG Y H, ZHANG K, et al. Dense anatomical annotation of slit-lamp images improves the performance of deep learning for the diagnosis of ophthalmic disorders[J]. Nat Biomed Eng, 2020, 4(8): 767-777.
[35]	KAISSIS G, ZILLER A, PASSERAT-PALMBACH J, et al. End-to-end privacy preserving deep learning on multi-institutional medical imaging[J]. Nat Mach Intell, 2021, 3: 473-484.
[36]	ZHU Y M, YIN X F, WEE-CHUNG LIEW A, et al. Privacy-preserving in medical image analysis: a review of methods and applications[M]//Parallel and distributed computing, applications and technologies. Singapore: Springer Nature Singapore, 2025: 166-178.
[37]	YANG Y H, LYU J F, WANG R X, et al. A digital mask to safeguard patient privacy[J]. Nat Med, 2022, 28(9): 1883-1892.
[38]	BHUTANI S, ELGENDI M, MENON C. Preserving privacy and video quality through remote physiological signal removal[J]. Commun Eng, 2025, 4(1): 66.
[39]	ZHU B Q, ZHANG C, SUI Y N, et al. FaceMotionPreserve: a generative approach for facial de-identification and medical information preservation[J]. Sci Rep, 2024, 14(1): 17275.