Share：
Share this content in WeChat
X
[Chinese][PDF]1903
• Review •
Progress in the application of artificial intelligence in the diagnosis and treatment of glaucoma: from traditional eye examination to MRI technology
WANG Yuanyuan  ZENG Xianjun 

Cite this article as: WANG Y Y, ZENG X J. Progress in the application of artificial intelligence in the diagnosis and treatment of glaucoma: from traditional eye examination to MRI technology[J]. Chin J Magn Reson Imaging, 2025, 16(1): 198-203. DOI:10.12015/issn.1674-8034.2025.01.032.


[Abstract] Artificial intelligence (AI) technology, led by deep learning, has been increasingly applied to the medical field due to its significant advantages in image processing and data analysis. The application of AI in glaucoma diagnosis and treatment spans from traditional ophthalmic examinations to MRI technology. It not only enables early screening and diagnosis, reducing the risk of visual function impairment, but also aids in predicting disease progression and prognosis. This facilitates the design of personalized treatment plans, ultimately improving patients' quality of life. This paper summarizes recent research findings on the use of AI for early screening, diagnosis and prediction of glaucoma, and discusses the advantages and challenges of its application in this field. The purpose of this review is to provide a comprehensive reference for researchers and clinicians to advance the further development of AI technology in the prevention and treatment of glaucoma, and ultimately to achieve the goal of optimizing patient management and improving eye health worldwide.
[Keywords] glaucoma；artificial intelligence；magnetic resonance imaging；deep learning；machine learning

WANG Yuanyuan1, 2   ZENG Xianjun1, 2*  

1 Department of Imaging, the First Affiliated Hospital of Nanchang University, Nanchang 330006, China

2 Clinical Research Center for Medical Imaging in Jiangxi Province, Nanchang 330006, China

Corresponding author: ZENG X J, E-mail: xianjun-zeng@126.com

Conflicts of interest   None.

Received  2024-10-12
Accepted  2025-01-10
DOI: 10.12015/issn.1674-8034.2025.01.032
Cite this article as: WANG Y Y, ZENG X J. Progress in the application of artificial intelligence in the diagnosis and treatment of glaucoma: from traditional eye examination to MRI technology[J]. Chin J Magn Reson Imaging, 2025, 16(1): 198-203. DOI:10.12015/issn.1674-8034.2025.01.032.

[1]
THAM Y C, LI X, WONG T Y, et al. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis[J]. Ophthalmology, 2014, 121(11): 2081-2090. DOI: 10.1016/j.ophtha.2014.05.013.
[2]
SOH Z, YU M, BETZLER B K, et al. The global extent of undetected glaucoma in adults: a systematic review and meta-analysis[J]. Ophthalmology, 2021, 128(10): 1393-1404. DOI: 10.1016/j.ophtha.2021.04.009.
[3]
WIEDEMAN P, HUI Y N. Artificial intelligence in ophthalmology[J]. Int Eye Sci, 2023, 23(9): 1417-1420. DOI: 10.3980/j.issn.1672-5123.2023.9.01.
[4]
LI F, SU Y D, LIN F B, et al. A deep-learning system predicts glaucoma incidence and progression using retinal photographs[J/OL]. J Clin Invest, 2022, 132(11): e157968 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/35642636/. DOI: 10.1172/JCI157968.
[5]
YANG L D, LI Q Q, CHEN Q Y, et al. Research progress of artificial intelligence in the diagnosis of glaucoma[J]. Recent Adv Ophthalmol, 2023, 43(6): 500-504. DOI: 10.13389/j.cnki.rao.2023.0102.
[6]
SRINIVAS S, YOUNG A J. Machine learning and artificial intelligence in surgical research[J]. Surg Clin North Am, 2023, 103(2): 299-316. DOI: 10.1016/j.suc.2022.11.002.
[7]
THOMPSON A C, JAMMAL A A, MEDEIROS F A. A review of deep learning for screening, diagnosis, and detection of glaucoma progression[J/OL]. Transl Vis Sci Technol, 2020, 9(2): 42 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/32855846/. DOI: 10.1167/tvst.9.2.42.
[8]
LIU W, ZHANG Y Z, WANG Q J, et al. Application prospect of artificial intelligence in corneal diseases[J]. Chin J Ocul Trauma Occup Eye Dis, 2024, 46(2): 156-160. DOI: 10.3760/cma.j.cn116022-20231008-00305.
[9]
LI M F, JIANG Y Y, ZHANG Y Z, et al. Medical image analysis using deep learning algorithms[J/OL]. Front Public Health, 2023, 11: 1273253 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/38026291/. DOI: 10.3389/fpubh.2023.1273253.
[10]
WANG M Q, ZHANG L Y, YU H X, et al. A deep learning network based on CNN and sliding window LSTM for spike sorting[J/OL]. Comput Biol Med, 2023, 159: 106879 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/37080004/. DOI: 10.1016/j.compbiomed.2023.106879.
[11]
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. DOI: 10.1109/TNNLS.2021.3084827.
[12]
SAHA S, VIGNARAJAN J, FROST S. A fast and fully automated system for glaucoma detection using color fundus photographs[J/OL]. Sci Rep, 2023, 13(1): 18408 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/37891238/. DOI: 10.1038/s41598-023-44473-0.
[13]
POPESCU PATONI S I, MUŞAT A A M, PATONI C, et al., Artificial intelligence in ophthalmology[J]. Rom J Ophthalmol. 2023, 67(3). 207-213. DOI: 10.22336/rjo.2023.37.
[14]
ALSHAWABKEH M, ALRYALAT S A, BDOUR M AL, et al. The utilization of artificial intelligence in glaucoma: diagnosis versus screening[J/OL]. Front Ophthalmol, 2024, 4: 1368081 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/38984126/. DOI: 10.3389/fopht.2024.1368081.
[15]
LIM J I, RACHITSKAYA A V, HALLAK J A, et al. Artificial intelligence for retinal diseases[J/OL]. Asia Pac J Ophthalmol, 2024, 13(4): 100096 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/39209215/. DOI: 10.1016/j.apjo.2024.100096.
[16]
XU L, WANG Y X, LI Y B, et al. Causes of blindness and visual impairment in urban and rural areas in Beijing: the Beijing Eye Study[J/OL]. Ophthalmology, 2006, 113(7): 1134.e1-1134.11 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/16647133/. DOI: 10.1016/j.ophtha.2006.01.035.
[17]
DIAZ-PINTO A, MORALES S, NARANJO V, et al. CNNs for automatic glaucoma assessment using fundus images: an extensive validation[J/OL]. Biomed Eng Online, 2019, 18(1): 29 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/30894178/. DOI: 10.1186/s12938-019-0649-y.
[18]
LI F, YAN L, WANG Y G, et al. Deep learning-based automated detection of glaucomatous optic neuropathy on color fundus photographs[J]. Graefes Arch Clin Exp Ophthalmol, 2020, 258(4): 851-867. DOI: 10.1007/s00417-020-04609-8.
[19]
XU Y L, HU M, LIU H R, et al. A hierarchical deep learning approach with transparency and interpretability based on small samples for glaucoma diagnosis[J/OL]. NPJ Digit Med, 2021, 4(1): 48 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/33707616/. DOI: 10.1038/s41746-021-00417-4.
[20]
MEDEIROS F A, JAMMAL A A, MARIOTTONI E B. Detection of progressive glaucomatous optic nerve damage on fundus photographs with deep learning[J]. Ophthalmology, 2021, 128(3): 383-392. DOI: 10.1016/j.ophtha.2020.07.045.
[21]
NAWAZ M, UVALIYEV A, BIBI K, et al. Unraveling the complexity of Optical Coherence Tomography image segmentation using machine and deep learning techniques: a review[J/OL]. Comput Med Imaging Graph, 2023, 108: 102269 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/37487362/. DOI: 10.1016/j.compmedimag.2023.102269.
[22]
LEE J, KIM Y K, PARK K H, et al. Diagnosing glaucoma with spectral-domain optical coherence tomography using deep learning classifier[J]. J Glaucoma, 2020, 29(4): 287-294. DOI: 10.1097/IJG.0000000000001458.
[23]
THOMPSON A C, JAMMAL A A, BERCHUCK S I, et al. Assessment of a segmentation-free deep learning algorithm for diagnosing glaucoma from optical coherence tomography scans[J]. JAMA Ophthalmol, 2020, 138(4): 333-339. DOI: 10.1001/jamaophthalmol.2019.5983.
[24]
RAN A R, CHEUNG C Y, WANG X, et al. Detection of glaucomatous optic neuropathy with spectral-domain optical coherence tomography: a retrospective training and validation deep-learning analysis[J/OL]. Lancet Digit Health, 2019, 1(4): e172-e182 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/33323187/. DOI: 10.1016/S2589-7500(19)30085-8.
[25]
SHI M, SUN J A, LOKHANDE A, et al. Artifact correction in retinal nerve fiber layer thickness maps using deep learning and its clinical utility in glaucoma[J/OL]. Transl Vis Sci Technol, 2023, 12(11): 12 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/37934137/. DOI: 10.1167/tvst.12.11.12.
[26]
YANG X M, YE Q Y. Diagnostic value of OCTA technology for primary angle closure glaucoma[J]. Smart Healthc, 2023, 9(18): 33-37. DOI: 10.19335/j.cnki.2096-1219.2023.18.008.
[27]
JIA F, LIU S J, REN J P, et al. Analysis of the changes of retinal blood flow density in patients with different stages of primary open-angle glaucoma by OCTA[J]. Chin J Ocul Trauma Occup Eye Dis, 2024, 46(1): 27-32. DOI: 10.3760/cma.j.cn116022-20230818-00256.
[28]
MOHAMMADZADEH V, LIANG Y W, MOGHIMI S, et al. Detection of glaucoma progression on longitudinal series of en-face macular optical coherence tomography angiography images with a deep learning model[J/OL]. Br J Ophthalmol, 2024, 108(12): 1688-1693 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/39117359/. DOI: 10.1136/bjo-2023-324528.
[29]
BOWD C, BELGHITH A, ZANGWILL L M, et al. Deep learning image analysis of optical coherence tomography angiography measured vessel density improves classification of healthy and glaucoma eyes[J/OL]. Am J Ophthalmol, 2022, 236: 298-308 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/34780803/. DOI: 10.1016/j.ajo.2021.11.008.
[30]
WANG W S, XING E M, QIN L N, et al. Automatic recognition of the open angle and angle closure of the anterior chamber angle based on deep learning[J]. Beijing Biomed Eng, 2021, 40(3): 221-226. DOI: 10.3969/j.issn.1002-3208.2021.03.001.
[31]
JIANG W Y, YAN Y L, CHENG S M, et al. Deep learning-based model for automatic assessment of anterior angle chamber in ultrasound biomicroscopy[J]. Ultrasound Med Biol, 2023, 49(12): 2497-2509. DOI: 10.1016/j.ultrasmedbio.2023.08.013.
[32]
RIVA I, MICHELETTI E, ODDONE F, et al. Anterior chamber angle assessment techniques: a review[J/OL]. J Clin Med, 2020, 9(12): 3814 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/33255754/. DOI: 10.3390/jcm9123814.
[33]
LI W Y, CHEN Q, JIANG C H, et al. Automatic anterior chamber angle classification using deep learning system and anterior segment optical coherence tomography images[J/OL]. Transl Vis Sci Technol, 2021, 10(6): 19 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/34111263/. DOI: 10.1167/tvst.10.6.19.
[34]
LI F, YANG Y F, SUN X, et al. Digital gonioscopy based on three-dimensional anterior-segment OCT: an international multicenter study[J]. Ophthalmology, 2022, 129(1): 45-53. DOI: 10.1016/j.ophtha.2021.09.018.
[35]
HOFFMANN E M, MEDEIROS F A, SAMPLE P A, et al. Relationship between patterns of visual field loss and retinal nerve fiber layer thickness measurements[J]. Am J Ophthalmol, 2006, 141(3): 463-471. DOI: 10.1016/j.ajo.2005.10.017.
[36]
GOLDBAUM M H, SAMPLE P A, WHITE H, et al. Interpretation of automated perimetry for glaucoma by neural network[J]. Invest Ophthalmol Vis Sci, 1994, 35(9): 3362-3373.
[37]
LI F, WANG Z, QU G X, et al. Automatic differentiation of Glaucoma visual field from non-glaucoma visual filed using deep convolutional neural network[J/OL]. BMC Med Imaging, 2018, 18(1): 35 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/30286740/. DOI: 10.1186/s12880-018-0273-5.
[38]
DIXIT A, YOHANNAN J, BOLAND M V. Assessing glaucoma progression using machine learning trained on longitudinal visual field and clinical data[J]. Ophthalmology, 2021, 128(7): 1016-1026. DOI: 10.1016/j.ophtha.2020.12.020.
[39]
BOWD C, HAO J C, TAVARES I M, et al. Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes[J]. Invest Ophthalmol Vis Sci, 2008, 49(3): 945-953. DOI: 10.1167/iovs.07-1083.
[40]
MURSCH-EDLMAYR A S, NG W S, DINIZ-FILHO A, et al. Artificial intelligence algorithms to diagnose glaucoma and detect glaucoma progression: translation to clinical practice[J/OL]. Transl Vis Sci Technol, 2020, 9(2): 55 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/33117612/. DOI: 10.1167/tvst.9.2.55.
[41]
XIONG J, LI F, SONG D P, et al. Multimodal machine learning using visual fields and peripapillary circular OCT scans in detection of glaucomatous optic neuropathy[J]. Ophthalmology, 2022, 129(2): 171-180. DOI: 10.1016/j.ophtha.2021.07.032.
[42]
LI J, WAN C. Non-invasive detection of intracranial pressure related to the optic nerve[J]. Quant Imaging Med Surg, 2021, 11(6): 2823-2836. DOI: 10.21037/qims-20-1188.
[43]
MARTUCCI A, DI GIULIANO F, MINOSSE S, et al. MRI and clinical biomarkers overlap between glaucoma and Alzheimer's disease[J/OL]. Int J Mol Sci, 2023, 24(19): 14932 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/37834380/. DOI: 10.3390/ijms241914932.
[44]
WANG Y Y, SHU Y Q, CAI G Q, et al. Altered static and dynamic functional network connectivity in primary angle-closure glaucoma patients[J/OL]. Sci Rep, 2024, 14(1): 11682 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/38778225/. DOI: 10.1038/s41598-024-62635-6.
[45]
PASLEY B N, MAYES L C, SCHULTZ R T. Subcortical discrimination of unperceived objects during binocular rivalry[J]. Neuron, 2004, 42(1): 163-172. DOI: 10.1016/s0896-6273(04)00155-2.
[46]
SUN Y, HUANG W B, LI F, et al. Subcortical visual pathway may be a new way for early diagnosis of glaucoma[J/OL]. Med Hypotheses, 2019, 123: 47-49 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/30696590/. DOI: 10.1016/j.mehy.2018.12.020.
[47]
QU X, WANG Q, CHEN W, et al. Combined machine learning and diffusion tensor imaging reveals altered anatomic fiber connectivity of the brain in primary open-angle glaucoma[J/OL]. Brain Res, 2019, 1718: 83-90 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/31071304/. DOI: 10.1016/j.brainres.2019.05.006.
[48]
ZHONG Y L, LIU H, HUANG X. Altered dynamic large-scale brain networks and combined machine learning in primary angle-closure glaucoma[J/OL]. Neuroscience, 2024, 558: 11-21 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/39154845/. DOI: 10.1016/j.neuroscience.2024.08.013.
[49]
SCHELL G J, LAVIERI M S, HELM J E, et al. Using filtered forecasting techniques to determine personalized monitoring schedules for patients with open-angle glaucoma[J]. Ophthalmology, 2014, 121(8): 1539-1546. DOI: 10.1016/j.ophtha.2014.02.021.
[50]
MARIOTTONI E B, DATTA S, SHIGUEOKA L S, et al. Deep learning-assisted detection of glaucoma progression in spectral-domain OCT[J]. Ophthalmol Glaucoma, 2023, 6(3): 228-238. DOI: 10.1016/j.ogla.2022.11.004.
[51]
HUSSAIN S, CHUA J, WONG D, et al. Predicting glaucoma progression using deep learning framework guided by generative algorithm[J/OL]. Sci Rep, 2023, 13(1): 19960 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/37968437/. DOI: 10.1038/s41598-023-46253-2.
[52]
ASAOKA R, MURATA H. Prediction of visual field progression in glaucoma: existing methods and artificial intelligence[J]. Jpn J Ophthalmol, 2023, 67(5): 546-559. DOI: 10.1007/s10384-023-01009-3.
[53]
ASANO S, ASAOKA R, MURATA H, et al. Predicting the central 10 degrees visual field in glaucoma by applying a deep learning algorithm to optical coherence tomography images[J/OL]. Sci Rep, 2021, 11(1): 2214 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/33500462/. DOI: 10.1038/s41598-020-79494-6.
[54]
KIHARA Y, MONTESANO G, CHEN A, et al. Policy-driven, multimodal deep learning for predicting visual fields from the optic disc and OCT imaging[J]. Ophthalmology, 2022, 129(7): 781-791. DOI: 10.1016/j.ophtha.2022.02.017.
[55]
LIU P P, ZHANG J D, BIAN H J. Risk factors and prediction model construction of ametropia after cataract extraction combined with angle separation in patients with primary angle-closure glaucoma[J]. Clin J Med Off, 2024, 52(10): 1025-1028. DOI: 10.16680/j.1671-3826.2024.10.09.
[56]
AGNIFILI L, FIGUS M, PORRECA A, et al. A machine learning approach to predict the glaucoma filtration surgery outcome[J/OL]. Sci Rep, 2023, 13(1): 18157 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/37875579/. DOI: 10.1038/s41598-023-44659-6.
[57]
BARRY S, WANG S Y. Predicting glaucoma surgical outcomes using neural networks and machine learning on electronic health records[J/OL]. Transl Vis Sci Technol, 2024, 13(6): 15 [2024-09-20]. https://pubmed.ncbi.nlm.nih.gov/38904612/. DOI: 10.1167/tvst.13.6.15.
[58]
JIA F. Correlation between preoperative nerve fiber layer thickness and postoperative visual field improvement in glaucoma patients[J]. J Med Forum, 2024, 45(10): 1079-1082, 1086. DOI: 10.20159/j.cnki.jmf.2024.10.017.

PREV Research progress on magnetic resonance imaging of chronic active lesions in multiple sclerosis
NEXT Advances in the application of ultrashort echo time sequence pulmonary function imaging
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn