山东大学耳鼻喉眼学报 ›› 2024, Vol. 38 ›› Issue (5): 153-159.doi: 10.6040/j.issn.1673-3770.0.2024.084

• 综述 • 上一篇    

人工智能在DME筛查、诊断和预后中的应用

沈嘉琪1,李潇飒2,毕燕龙1,张敬法2,3   

  1. 深圳)犇亞国际眼科转化研究所/深圳希玛林顺潮眼科医院, 广东 深圳 518000
  • 发布日期:2024-09-25
  • 基金资助:
    国家自然科学基金青年项目(32201244);国家自然科学基金面上项目(82171062)

The application of artificial intelligence in screening, diagnosis and prognosis of diabetic macular edema

SHEN Jiaqi1, LI Xiaosa2, BI Yanlong1, ZHANG Jingfa2,3   

  1. 1. Department of Ophthalmology, Tongji University Affiliated Tongji Hospital/Tongji EyeInstitute, Tongji University, Shanghai 2003332. Department of Ophthalmology, Shanghai General Hospital (Shanghai First People's Hospital)/National Clinical Research Center for Eye Diseases/Shanghai Key Laboratory of Ocular Fundus Diseases/Shanghai Engineering Center for Visual Science and Photomedicine/Shanghai Engineering Center for Precise Diagnosis and Treatment of Eye Diseases, Shanghai 2000803. Benya International Translational Eye Research Institute of The Chinese University of Hong Kong (Shenzhen)/C-MER (Shenzhen)Dennis Lam Eye Hospital, Shenzhen 518000
  • Published:2024-09-25

PDF (PC)

3

摘要： 人工智能(artificial intelligence, AI)在临床疾病的早期筛查、诊断、评估和治疗方案决策等领域展现出广阔的应用前景。糖尿病性黄斑水肿(diabetic macular edema, DME)是导致工作年龄人群视力损害的一个重要原因,鉴于DME的影像资料复杂性、疾病的高致盲率和治疗难度,探索AI在DME疾病诊疗中的应用具有重要意义。论文综述了AI技术在DME的早期筛查、精确诊断和预后预测中的应用进展,分析了AI解决方案在DME实际应用中面临的挑战,并对未来发展方向进行展望,旨为实现DME的个体化精确诊疗提供有益参考。

关键词: 糖尿病性黄斑水肿, 人工智能, 精准医疗, 眼部影像学

Abstract: Artificial intelligence(AI)has shown promising applications in the early screening, diagnosis, assessment, and treatment decision-making of clinical diseases. Diabetic macular edema(DME)is a significant cause of visual impairment among the working-age population. Given the complexity of DME imaging data, high rate of blindness, and treatment challenges associated with the disease, exploration of AI in the diagnosis and treatment of DME is of great importance. This review summarizes the advancements of AI technology in the early screening, accurate diagnosis, and prognosis prediction of DME, analyzes the challenges faced by AI solutions in practical DME applications, and offers insights into future directions, with the aim of providing valuable guidance for achieving personalized and precise diagnosis and treatment of DME.

Key words: Diabetic macular edema, Artificial intelligence, Precision medicine, Eye imaging

中图分类号: 

  • R774.5
[1] 王娇娇, 李苗. 糖尿病视网膜病变的机制和细胞模型研究进展[J]. 山东大学耳鼻喉眼学报, 2022, 36(5): 93-99. doi:10.6040/j.issn.1673-3770.0.2021.203 WANG Jiaojiao, LI Miao. Progress in diabetic retinopathy mechanisms and cellular models[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2022, 36(5): 93-99. doi:10.6040/j.issn.1673-3770.0.2021.203
[2] Yau JWY, Rogers SL, Kawasaki R, et al. Global prevalence and major risk factors of diabetic retinopathy[J]. Diabetes Care, 2012, 35(3): 556-564. doi:10.2337/dc11-1909
[3] Wells JA, Glassman AR, Ayala AR, et al. Aflibercept, bevacizumab, or ranibizumab for diabetic macular edema: two-year results from a comparative effectiveness randomized clinical trial[J]. Ophthalmology, 2016, 123(6): 1351-1359. doi:10.1016/j.ophtha.2016.02.022
[4] Prince J, Kumar D, Ghosh A, et al. Surgical Management of Diabetic Macular Edema[J]. Curr Diab Rep,2023,23(6):119-125.doi:10.1007/s11892-023-01505-3
[5] Bressler NM, Beaulieu WT, Glassman AR, et al. Persistent macular thickening following intravitreous aflibercept, bevacizumab, or ranibizumab for central-involved diabetic macular edema with vision impairment: a secondary analysis of a randomized clinical trial[J]. JAMA Ophthalmol, 2018, 136(3): 257-269. doi:10.1001/jamaophthalmol.2017.6565
[6] Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare[J]. Nat Med, 2019, 25(1): 24-29. doi:10.1038/s41591-018-0316-z
[7] Abràmoff MD, Lavin PT, Birch M, et al. Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices[J]. NPJ Digit Med, 2018, 1: 39. doi:10.1038/s41746-018-0040-6
[8] 李治玺, 张健, 何明光. 人工智能初筛分流在大规模糖尿病视网膜病变筛查中的应用[J]. 中华医学杂志, 2020, 100(48): 3835-3840. doi:10.3760/cma.j.cn112137-20200901-02526 LI Zhixi, ZHANG Jian, HE Mingguang. Using artificial intelligence as an initial triage strategy in diabetic retinopathy screening program in China[J]. National Medical Journal of China, 2020, 100(48): 3835-3840. doi:10.3760/cma.j.cn112137-20200901-02526
[9] Sahlsten J, Jaskari J, Kivinen J, et al. Deep learning fundus image analysis for diabetic retinopathy and macular edema grading[J]. Sci Rep, 2019, 9(1): 10750. doi:10.1038/s41598-019-47181-w
[10] Wang YT, Tadarati M, Wolfson Y, et al. Comparison of prevalence of diabetic macular edema based on monocular fundus photography vs optical coherence tomography[J]. JAMA Ophthalmol, 2016, 134(2): 222-228. doi:10.1001/jamaophthalmol.2015.5332
[11] Lim G, Bellemo V, Xie YC, et al. Different fundus imaging modalities and technical factors in AI screening for diabetic retinopathy: a review[J]. Eye Vis, 2020, 7: 21. doi:10.1186/s40662-020-00182-7
[12] Lam C, Wong YL, Tang ZQ, et al. Performance of artificial intelligence in detecting diabetic macular edema from fundus photography and optical coherence tomography images: a systematic review and meta-analysis[J]. Diabetes Care, 2024, 47(2): 304-319. doi:10.2337/dc23-0993
[13] Leal J, Luengo-Fernandez R, Stratton IM, et al. Cost-effectiveness of digital surveillance clinics with optical coherence tomography versus hospital eye service follow-up for patients with screen-positive maculopathy[J]. Eye, 2019, 33(4): 640-647. doi:10.1038/s41433-018-0297-7
[14] Varadarajan AV, Bavishi P, Ruamviboonsuk P, et al. Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning[J]. Nat Commun, 2020, 11(1): 130. doi:10.1038/s41467-019-13922-8
[15] Arcadu F, Benmansour F, Maunz A, et al. Deep learning predicts OCT measures of diabetic macular thickening from color fundus photographs[J]. Invest Ophthalmol Vis Sci, 2019, 60(4): 852-857. doi:10.1167/iovs.18-25634
[16] Schramm S, Dietzel A, Link D, et al. 3D retinal imaging and measurement using light field technology[J]. J Biomed Opt, 2021, 26(12): 126002. doi:10.1117/1.JBO.26.12.126002
[17] 中国医药教育协会智能医学专委会智能眼科学组, 国家重点研发计划"眼科多模态成像及人工智能诊疗系统的研发和应用"项目组. 基于眼底照相的糖尿病视网膜病变人工智能筛查系统应用指南[J]. 中华实验眼科杂志, 2019, 37(8): 593-598. doi:10.3760/cma.j.issn.2095-0160.2019.08.001
[18] Malerbi FK, Mendes G, Barboza N, et al. Diabetic macular edema screened by handheld smartphone-based retinal camera and artificial intelligence[J]. J Med Syst, 2021, 46(1): 8. doi:10.1007/s10916-021-01795-8
[19] 史雪辉, 张丛, 魏文斌. 关注糖尿病黄斑水肿的光学相干断层扫描分型及相关影像特征[J]. 中华眼科医学杂志(电子版),2021,11(1): 1-7. doi:10.3877/cma.j.issn.2095-2007.2021.01.001 SHI Xuehui, ZHANG Cong, WEI Wenbin. Pay attention to OCT-based classification and features of diabetic macular edema[J]. Chinese Journal of Ophthalmologic Medicine(Electronic Edition), 2021, 11(1): 1-7. doi:10.3877/cma.j.issn.2095-2007.2021.01.001
[20] Bhandari M, Shahi TB, Neupane A. Evaluating retinal disease diagnosis with an interpretable lightweight CNN model resistant to adversarial attacks[J]. J Imaging, 2023, 9(10): 219. doi:10.3390/jimaging9100219
[21] Tang FY, Wang X, Ran AR, et al. A multitask deep-learning system to classify diabetic macular edema for different optical coherence tomography devices: a multicenter analysis[J]. Diabetes Care, 2021, 44(9): 2078-2088. doi:10.2337/dc20-3064
[22] Wu QW, Zhang B, Hu YJ, et al. Detection of morphologic patterns of diabetic macular edema using a deep learning approach based on optical coherence tomography images[J]. Retina, 2021, 41(5): 1110-1117. doi:10.1097/IAE.0000000000002992
[23] Otani T, Kishi S, Maruyama Y. Patterns of diabetic macular edema with optical coherence tomography[J]. Am J Ophthalmol, 1999, 127(6): 688-693. doi:10.1016/s0002-9394(99)00033-1
[24] 田涛, 姚晓喜, 彭婧利, 等. 不同抗VEGF药物治疗糖尿病性黄斑水肿的疗效及其与OCT分型的关系[J]. 国际眼科杂志, 2023, 23(6): 991-995. doi:10.3980/j.issn.1672-5123.2023.6.22 TIAN Tao, YAO Xiaoxi, PENG Jingli, et al. Efficacy of different anti - vascular endothelial growth factor drugs in the treatment of diabetic macular edema and their relationship with optical coherence tomography classification[J]. International Eye Science, 2023, 23(6): 991-995. doi:10.3980/j.issn.1672-5123.2023.6.22
[25] Panozzo G, Cicinelli MV, Augustin AJ, et al. An optical coherence tomography-based grading of diabetic maculopathy proposed by an international expert panel: the European School for Advanced Studies in Ophthalmology classification[J]. Eur J Ophthalmol, 2020, 30(1): 8-18. doi:10.1177/1120672119880394
[26] Saxena S, Caprnda M, Ruia S, et al. Spectral domain optical coherence tomography based imaging biomarkers for diabetic retinopathy[J]. Endocrine, 2019, 66(3): 509-516. doi:10.1007/s12020-019-02093-7
[27] Roberts PK, Vogl WD, Gerendas BS, et al. Quantification of fluid resolution and visual acuity gain in patients with diabetic macular edema using deep learning: a post hoc analysis of a randomized clinical trial[J]. JAMA Ophthalmol, 2020, 138(9): 945-953. doi:10.1001/jamaophthalmol.2020.2457
[28] Xie S, Okuwobi IP, Li MC, et al. Fast and automated hyperreflective foci segmentation based on image enhancement and improved 3D U-net in SD-OCT volumes with diabetic retinopathy[J]. Transl Vis Sci Technol, 2020, 9(2): 21. doi:10.1167/tvst.9.2.21
[29] Tripathi A, Kumar P, Tulsani A, et al. Fuzzy logic-based system for identifying the severity of diabetic macular edema from OCT B-scan images using DRIL, HRF, and cystoids[J]. Diagnostics, 2023, 13(15): 2550. doi:10.3390/diagnostics13152550
[30] 周静琳, 李金香, 曾琦. 577 nm阈值下微脉冲激光联合抗VEGF药物治疗难治性糖尿病性黄斑水肿的疗效观察[J]. 山东大学耳鼻喉眼学报, 2024, 38(2): 18-25. doi:10.6040/j.issn.1673-3770.0.2023.313 ZHOU Jinglin, LI Jinxiang, ZENG Qi. Therapeutic effect of micro-pulse laser combined with anti-VEGF drugs under the threshold of 577nm on refractory diabetic macular edema[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2024, 38(2): 18-25. doi:10.6040/j.issn.1673-3770.0.2023.313
[31] Cao J, You K, Jin K, et al. Prediction of response to anti-vascular endothelial growth factor treatment in diabetic macular oedema using an optical coherence tomography-based machine learning method[J]. Acta Ophthalmol, 2021, 99(1): e19-e27. doi:10.1111/aos.14514
[32] Alryalat SA, Al-Antary M, Arafa Y, et al. Deep learning prediction of response to anti-VEGF among diabetic macular edema patients: treatment response analyzer system(TRAS)[J]. Diagnostics, 2022, 12(2): 312. doi:10.3390/diagnostics12020312
[33] Xu FB, Liu SP, Xiang YF, et al. Prediction of the short-term therapeutic effect of anti-VEGF therapy for diabetic macular edema using a generative adversarial network with OCT images[J]. J Clin Med, 2022, 11(10): 2878. doi:10.3390/jcm11102878
[34] Liu BY, Zhang B, Hu YJ, et al. Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning[J]. Ann Transl Med, 2021, 9(1): 43. doi:10.21037/atm-20-1431
[35] Chou HD, Wu CH, Chiang WY, et al. Optical coherence tomography and imaging biomarkers as outcome predictors in diabetic macular edema treated with dexamethasone implant[J]. Sci Rep, 2022, 12(1): 3872. doi:10.1038/s41598-022-07604-7
[36] Iglicki M, Lavaque A, Ozimek M, et al. Biomarkers and predictors for functional and anatomic outcomes for small gauge pars Plana vitrectomy and peeling of the internal limiting membrane in naïve diabetic macular edema: the VITAL Study[J]. PLoS One, 2018, 13(7): e0200365. doi:10.1371/journal.pone.0200365
[37] 徐艺, 凌赛广, 董洲, 等. 一种基于计算机视觉的眼底图像质量评估系统的开发及应用[J]. 中华眼科杂志, 2020, 56(12): 920-927. doi:10.3760/cma.j.cn112142-20200409-00257 XU Yi, LING Saiguang, DONG Zhou, et al. Development and application of a fundus image quality assessment system based on computer vision technology[J]. Chinese Journal of Ophthalmology, 2020, 56(12): 920-927. doi:10.3760/cma.j.cn112142-20200409-00257
[38] 陈健祺. 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. doi:10.3978/j.issn.1000-4432.2022.03.01 CHEN Jianqi. Research progress of artificial intelligence in screening and diagnosis of eye diseases[J]. YAN KE XUE BAO, 2022, 37(3): 208-213. doi:10.3978/j.issn.1000-4432.2022.03.01
[39] 曹晓莉, 陈羽中. 糖尿病视网膜病变眼底图像辅助诊断软件的NMPA注册经验[J]. 眼科学报, 2021, 36(1): 111-114. doi:10.3978/j.issn.1000-4432.2021.01.17 CAO Xiaoli, CHEN Yuzhong. NMPA premarket application experience for a computer aided diagnosis software using fundus images of diabetic retinopathy[J]. YAN KE XUE BAO, 2021, 36(1): 111-114. doi:10.3978/j.issn.1000-4432.2021.01.17
[40] Ruamviboonsuk P, Chantra S, Seresirikachorn K, et al. Economic evaluations of artificial intelligence in ophthalmology[J]. Asia Pac J Ophthalmol, 2021, 10(3): 307-316. doi:10.1097/APO.0000000000000403
[41] Liu HR, Li RY, Zhang Y, et al. Economic evaluation of combined population-based screening for multiple blindness-causing eye diseases in China: a cost-effectiveness analysis[J]. Lancet Glob Health, 2023, 11(3): 456-465. doi:10.1016/S2214-109X(22)00554-X
[42] Yu ZH, Yang X, Sweeting GL, et al. Identify diabetic retinopathy-related clinical concepts and their attributes using transformer-based natural language processing methods[J]. BMC Med Inform Decis Mak, 2022, 22(Suppl 3): 255. doi:10.1186/s12911-022-01996-2
[43] Lee YM, Bacchi S, Macri C, et al. Ophthalmology operation note encoding with open-source machine learning and natural language processing[J]. Ophthalmic Res, 2023, 66(1): 928-939. doi:10.1159/000530954
[1] 谢玉林,雷大鹏. 人工智能在头颈部鳞状细胞癌淋巴结转移的病理研究进展[J]. 山东大学耳鼻喉眼学报, 2024, 38(3): 124-129.
[2] 周静琳,李金香,曾琦. 577 nm阈值下微脉冲激光联合抗VEGF药物治疗难治性糖尿病性黄斑水肿的疗效观察[J]. 山东大学耳鼻喉眼学报, 2024, 38(2): 18-25.
[3] 吴丽丽,曲毅. OCTA在病理性近视脉络膜新生血管应用及其在人工智能的研究进展[J]. 山东大学耳鼻喉眼学报, 2024, 38(2): 144-149.
[4] 张一彤,李青香,石争浩,尚磊,袁钰淇,曹子讷,麻莉娜,刘海琴,任晓勇,施叶雯. 阻塞性睡眠呼吸暂停儿童睡眠结构研究及睡眠结构判读模型建立[J]. 山东大学耳鼻喉眼学报, 2023, 37(6): 126-132.
[5] 杜曰山一,王鲜,张国明. 人工智能辅助早产儿视网膜病变诊疗新进展[J]. 山东大学耳鼻喉眼学报, 2023, 37(3): 157-162.
[6] 刘佳钰,樊慧明,邹游,陈始明. 人工智能在鼻咽癌诊断与治疗中的应用研究进展[J]. 山东大学耳鼻喉眼学报, 2023, 37(2): 135-142.
[7] 姚爽,娄鸿飞. 慢性鼻窦炎的内在型研究进展及精准医疗[J]. 山东大学耳鼻喉眼学报, 2022, 36(3): 20-29.
[8] 华红利,李松，陶泽璋. 人工智能在鼻咽癌诊疗中的研究进展[J]. 山东大学耳鼻喉眼学报, 2022, 36(2): 113-119.
[9] 王迪,程金章,于丹. 基于机器学习的人工智能技术在耳鼻喉科临床诊疗中的应用进展[J]. 山东大学耳鼻喉眼学报, 2021, 35(6): 125-131.
[10] 陈海兵, 卫亚楠, 许晓泉, 陈曦. 基于XGBoost人工智能结合CT构建甲状腺癌颈部淋巴结转移预测模型[J]. 山东大学耳鼻喉眼学报, 2020, 34(3): 40-45.
[11] 朱志玲,李松,管国芳. 人工智能在耳鼻咽喉头颈外科的运用及展望[J]. 山东大学耳鼻喉眼学报, 2020, 34(2): 115-120.
[12] 邱昌余,周俊,庄德恩,杨晴,陆美萍,程雷. 人工智能技术在辅助耳鼻咽喉科医师了解过敏性鼻炎患者需求中的应用[J]. 山东大学耳鼻喉眼学报, 2019, 33(3): 88-94.
[13] 娄鸿飞,王成硕. 慢性鼻窦炎分型研究进展[J]. 山东大学耳鼻喉眼学报, 2018, 32(3): 10-13.
[14] 靳琳,潘庆敏,胡磊. 玻璃体腔注射雷珠单抗治疗CSME及NCSME的临床观察[J]. 山东大学耳鼻喉眼学报, 2017, 31(2): 96-98.
[15] 谢丽，魏伟. 糖尿病性黄斑水肿的治疗进展[J]. 山东大学耳鼻喉眼学报, 2013, 27(2): 81-85.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
网站版权所有 © 2018 《山东大学耳鼻喉眼学报》编辑部　
地址：山东省济南市山大南路27号（250100）电话：+86-0531-88366912 E-mail: ebhxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发