Artificial intelligence-assisted diagnosis and surgical planning in oculoplastic disorders: a systematic review
DOI:
https://doi.org/10.65759/p5a2y968Keywords:
Artificial intelligence, deep learning, machine learning, oculoplastic, thyroid eye diseaseAbstract
Background: Artificial intelligence (AI) is increasingly used to oculoplastic disorders, where diagnosis and surgical planning rely on imaging and objective periocular measurements. Our review summarizes studies on AI-assisted diagnosis, quantification, and surgical planning in oculoplastic. Methods: A systematic review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) principles. We conduct a literature search on PubMed (MEDLINE), Scopus, and Web of Science were searched from inception to the final search date for original human studies which evaluate AI for oculoplastic diagnosis, assessment, or surgical planning. Eligible studies reported quantitative performance metrics. Results: Twelve studies were included, computed tomography based thyroid eye disease models showed high discrimination for disease severity and compressive optic neuropathy screening (area under the receiver operating characteristic curve (AUC) 0.99; independent test AUC 0.92). Automated orbital segmentation achieved Dice values 0.90. Ptosis detection models achieved strong performance on high quality images (AUC 0.92) but degraded on low quality images. Automated eyelid measurement errors were sub millimeter, and postoperative appearance prediction systems reported eye overlap ratios 0.85 to 0.87. Eyelid tumor models using clinical images or histopathology shoe high diagnostic accuracy (AUCs 0.92 to 1.00). Conclusions: AI shows strong potential for oculoplastic diagnosis and planning, but external validation, and clinical impact evaluation were the important gaps.
References
1. Abascal Azanza C, Barrio-Barrio J, Ramos Cejudo J, Ybarra Arróspide B, Devoto MH. Development and validation of a convolutional neural network to identify blepharoptosis. Sci Rep. 2023;13:17585. doi:10.1038/s41598-023-44686-3.
2. Alkhadrawi AM, Lin LY, Langarica SA, Kim K, Ha SK, Lee NG, et al. Deep-learning based automated segmentation and quantitative volumetric analysis of orbital muscle and fat for diagnosis of thyroid eye disease. Invest Ophthalmol Vis Sci. 2024;65(5):6. doi:10.1167/iovs.65.5.6.
3. Chng C-L, Zheng K, Kwee AK, Lee M-HH, Ting D, Wong CP, et al. Application of artificial intelligence in the assessment of thyroid eye disease (TED) – a scoping review. Front Endocrinol (Lausanne). 2023 Dec 20;14:1300196. doi:10.3389/fendo.2023.1300196. PMCID: PMC10761414.
4. Collins GS, Moons KGM, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. 2024. PMCID: PMC11019967.
5. Davis SE, et al. Detection of Calibration Drift in Clinical Prediction Models to Inform Model Updating. 2020. PMCID: PMC8627243.
6. Fazekas B, et al. Artificial Intelligence in Oculoplastics: A Survey-Based Study on Provider Perspective. Cureus. 2025. PMCID: PMC12032587.
7. Guo X, et al. MedShift: Automated Identification of Shift Data for Medical Image Dataset Curation. 2023. PMCID: PMC10513895.
8. Huang S, Xie J, Yang B, Gao Q, Ye J. PtosisDiffusion: a training-free workflow for precisely predicting post-operative appearance in blepharoptosis patients based on diffusion models. Front Cell Dev Biol. 2024;12:1459336. doi:10.3389/fcell.2024.1459336.
9. Hui S, Dong L, Zhang K, Nie Z, Jiang X, Li H, et al. Noninvasive identification of benign and malignant eyelid tumors using clinical images via deep learning system. J Big Data. 2022;9:84. doi:10.1186/s40537-022-00634-y.
10. Hui S, Xie J, Dong L, Wei L, Dai W, Li D. Deep learning-based mobile application for efficient eyelid tumor recognition in clinical images. NPJ Digit Med. 2025;8:185. doi:10.1038/s41746-025-01539-9.
11. Hung JY, Perera C, Chen KW, Myung D, Chiu HK, Fuh CS, et al. A deep learning approach to identify blepharoptosis by convolutional neural networks. Int J Med Inform. 2021 Apr;148:104402. doi:10.1016/j.ijmedinf.2021.104402.
12. Ing E, Bondok M. Oculoplastics and Augmented Intelligence: A Literature Review. J Clin Med. 2025 Sep 28;14(19):6875. doi:10.3390/jcm14196875. PMCID: PMC12524889.
13. Jiang J, Liu H, He L, Pei M, Lin T, Yang H, et al. HM_ADET: a hybrid model for automatic detection of eyelid tumors based on photographic images. Biomed Eng Online. 2024;23:25. doi:10.1186/s12938-024-01221-3.
14. Jin K, Ye J. Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives. Adv Ophthalmol Pract Res. 2022 Aug 24;2(3):100078. doi:10.1016/j.aopr.2022.100078. PMCID: PMC10577833.
15. Khan AYR, Malik MB, Naveed M, Hussain M, Kamran H, Hussain A, et al. Artificial Intelligence in Ophthalmology: Practical Applications, Subspecialty Evidence and Real-World Deployment. Cureus. 2025 Nov 5;17(11):e96121. doi:10.7759/cureus.96121. PMCID: PMC12587209.
16. Li Z, Wang L, Zhou H, Jiang J, Ye J, Lou L, et al. Artificial intelligence in ophthalmology: The path to the real-world clinic. Cell Rep Med. 2023 Jun 28;4(7):101095. doi:10.1016/j.xcrm.2023.101095. PMCID: PMC10394169.
17. Lin LY, Zhou P, Shi M, Lu JE, Jeon S, Kim D, et al. A deep learning model for screening computed tomography imaging for thyroid eye disease and compressive optic neuropathy. Ophthalmol Sci. 2024;4:100412. doi:10.1016/j.xops.2023.100412.
18. Liu X, Rivera SC, Moher D, Calvert MJ, Denniston AK, on behalf of CONSORT-AI Group. Reporting Guidelines for Clinical Trial Reports for Interventions Involving Artificial Intelligence: The CONSORT-AI Extension. Lancet Digit Health. 2020 Sep 9;2(10):e537–e548. doi:10.1016/S2589-7500(20)30218-1. PMCID: PMC8183333.
19. Lou L, Cao J, Wang Y, Gao Z, Jin K, Xu Z, et al. Deep learning-based image analysis for automated measurement of eyelid morphology before and after blepharoptosis surgery. Ann Med. 2021;53(1):2278-2285. doi:10.1080/07853890.2021.2009127.
20. Luo Y, Zhang J, Yang Y, Rao Y, Chen X, Shi T, et al. Deep learning-based fully automated differential diagnosis of eyelid basal cell and sebaceous carcinoma using whole slide images. Quant Imaging Med Surg. 2022;12(8):4166-4175. doi:10.21037/qims-22-98.
21. Mongan J, Moy L, Kahn CE Jr. Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers. Radiology: AI. 2020. PMCID: PMC8017414.
22. Nakayama LF, et al. Unmasking biases and navigating pitfalls in the ophthalmic artificial intelligence lifecycle: A narrative review. 2024. PMCID: PMC11460710.
23. Ricci Lara MA, Echeveste R, Ferrante E. Addressing fairness in artificial intelligence for medical imaging. 2022. PMCID: PMC9357063.
24. Rivera SC, Liu X, Chan A-W, Denniston AK, Calvert MJ, on behalf of SPIRIT-AI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Lancet Digit Health. 2020 Sep 9;2(10):e549–e560. doi:10.1016/S2589-7500(20)30219-3. PMCID: PMC8212701.
25. Song X, Tong W, Lei C, Huang J, Fan X, Zhai G, et al. A clinical decision model based on machine learning for ptosis. BMC Ophthalmol. 2021;21:169. doi:10.1186/s12886-021-01923-5.
26. Srivastava O, Tennant M, Grewal P, Rubin U, Seamone M. Artificial intelligence and machine learning in ophthalmology: A review. Indian J Ophthalmol. 2022 Dec 30;71(1):11–17. doi:10.4103/ijo.IJO_1569_22. PMCID: PMC10155540.
27. Sun Y, Huang X, Zhang Q, Lee SY, Wang Y, Jin K, et al. A fully automatic postoperative appearance prediction system for blepharoptosis surgery with image-based deep learning. Ophthalmol Sci. 2022;2:100169. doi:10.1016/j.xops.2022.100169.
28. Tan W, et al. Fairer AI in ophthalmology via implicit fairness learning for mitigating sexism and ageism. 2024. PMCID: PMC11150422.
Yu AC, Mohajer B, Eng J. External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic Review. Radiology. 2022. PMCID: PMC9152694.
