Artificial Intelligence in Neovascular Age-Related Macular Degeneration

Abstract

The integration of artificial intelligence (AI) into the management of neovascular age-related macular degeneration (nAMD) presents a transformative opportunity in ophthalmology. In particular, deep learning (DL) models have shown remarkable accuracy in detecting nAMD, predicting disease progression and forecasting treatment outcomes. This review provides a comprehensive analysis of current AI applications in nAMD, focusing on the performance of these models in diagnostic tasks, including classification, object detection, and segmentation, as well as their potential to outperform human experts in specific domains. The review further explores how AI-driven predictive models can personalize treatment strategies by forecasting individual responses to therapies, such as anti-VEGF, and predicting the conversion from intermediate AMD to nAMD. Despite these promising developments, significant challenges remain, including the need for extensive datasets, seamless integration into clinical workflows, and ensuring the generalizability of AI predictions across diverse populations. Continued validation and the development of user-friendly AI tools are crucial for broader adoption and improved patient outcomes. In conclusion, identifying effective pathways to overcome these challenges will be essential as the field continues to evolve.

Zusammenfassung

Die Integration von künstlicher Intelligenz (KI) in das Management der neovaskulären altersbedingten Makuladegeneration (nAMD) bietet eine transformative Chance in der Augenheilkunde. Insbesondere Deep-Learning-Modelle (DL) zeigen eine bemerkenswerte Genauigkeit bei der Erkennung von nAMD, der Vorhersage des Krankheitsverlaufs und der Prognose von Behandlungsergebnissen. Diese Übersicht gibt einen umfassenden Einblick in aktuelle KI-Anwendungen bei nAMD, mit Fokus auf die Leistungsfähigkeit dieser Modelle bei diagnostischen Aufgaben wie Klassifikation, Objekterkennung und Segmentierung sowie deren Potenzial, in bestimmten Bereichen besser abzuschneiden als menschliche Experten. Weiterhin wird untersucht, wie KI-basierte Vorhersagemodelle personalisierte Behandlungsstrategien ermöglichen können, indem sie individuelle Therapieantworten – etwa auf Anti-VEGF – vorhersagen und die Umwandlung von intermediärer AMD in nAMD prognostizieren. Trotz dieser vielversprechenden Entwicklungen bleiben Herausforderungen bestehen: große Datensätze, nahtlose Integration in den klinischen Alltag und die Sicherstellung zuverlässiger Vorhersagen bei unterschiedlichen Patientengruppen. Kontinuierliche Validierung und die Entwicklung benutzerfreundlicher KI-Tools sind entscheidend, um die breite Anwendung zu ermöglichen und die Behandlungsergebnisse zu verbessern. Effektive Lösungswege für diese Hürden sind essenziell, damit sich das Feld weiterentwickeln kann.

Keywords

artificial intelligence - neovascular age-related macular degeneration - deep learning - machine learning - disease prediction - anti-VEGF

Schlüsselwörter

künstliche Intelligenz - neovaskuläre altersbedingte Makuladegeneration - Deep Learning - maschinelles Lernen - Krankheitsvorhersage - Anti-VEGF

Publication History

Received: 23 July 2024

Accepted: 08 September 2024

Accepted Manuscript online:
11 September 2024

Article published online:
15 August 2025

• References

• 1 Guymer RH, Campbell TG. Age-related macular degeneration. Lancet 2023; 401: 1459-1472
• 2 Wong WL, Su X, Li X. et al. Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis. Lancet Glob Health 2014; 2: e106-e116
• 3 Fleckenstein M, Schmitz-Valckenberg S, Chakravarthy U. Age-Related Macular Degeneration: A Review. JAMA 2024; 331: 147-157
• 4 Kumar A, Ferro Desideri L, Ting MYL. et al. Perspectives on the currently available pharmacotherapy for wet macular degeneration. Expert Opin Pharmacother 2024; 25: 755-767
• 5 Ferro Desideri L, Traverso CE, Nicolò M. et al. Faricimab for the Treatment of Diabetic Macular Edema and Neovascular Age-Related Macular Degeneration. Pharmaceutics 2023; 15: 1413
• 6 Viola P, Testa V, Ferro Desideri L. et al. Aflibercept, ranibizumab and bevacizumab upcoming biosimilars: a general overview. Drugs Today (Barc) 2021; 57: 689-697
• 7 Rosenberg D, Deonarain DM, Gould J. et al. Efficacy, safety, and treatment burden of treat-and-extend versus alternative anti-VEGF regimens for nAMD: a systematic review and meta-analysis. Eye (Lond) 2023; 37: 6-16
• 8 Nicolo M, Morlacchi A, Cappelli F. et al. Real-Life Data in the Treatment of Neovascular Age-Related Macular Degeneration: Results from the Imaculaweb Registry Evaluated in a Single Italian Medical Retina Center. Ophthalmologica 2020; 243: 453-460
• 9 Ferrara D, Newton EM, Lee AY. Artificial intelligence-based predictions in neovascular age-related macular degeneration. Curr Opin Ophthalmol 2021; 32: 389-396
• 10 Ting DSW, Pasquale LR, Peng L. et al. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol 2019; 103: 167-175
• 11 Daich Varela M, Sen S, De Guimaraes TAC. et al. Artificial intelligence in retinal disease: clinical application, challenges, and future directions. Graefes Arch Clin Exp Ophthalmol 2023; 261: 3283-3297
• 12 He M, Li Z, Liu C. et al. Deployment of Artificial Intelligence in Real-World Practice: Opportunity and Challenge. Asia Pac J Ophthalmol (Phila) 2020; 9: 299-307
• 13 Mintz Y, Brodie R. Introduction to artificial intelligence in medicine. Minim Invasive Ther Allied Technol 2019; 28: 73-81
• 14 Martins TGDS, Schor P. Machine learning in image analysis in ophthalmology. Einstein (Sao Paulo) 2022; 19: eED6860
• 15 Chen JS, Baxter SL. Applications of natural language processing in ophthalmology: present and future. Front Med (Lausanne) 2022; 9: 906554
• 16 Keel S, Li Z, Scheetz J. et al. Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs. Clin Exp Ophthalmol 2019; 47: 1009-1018
• 17 Ayhan MS, Faber H, Kühlewein L. et al. Multitask Learning for Activity Detection in Neovascular Age-Related Macular Degeneration. Transl Vis Sci Technol 2023; 12: 12
• 18 Heo TY, Kim KM, Min HK. et al. Development of a Deep-Learning-Based Artificial Intelligence Tool for Differential Diagnosis between Dry and Neovascular Age-Related Macular Degeneration. Diagnostics (Basel) 2020; 10: 261
• 19 Thakoor KA, Yao J, Bordbar D. et al. A multimodal deep learning system to distinguish late stages of AMD and to compare expert vs. AI ocular biomarkers. Sci Rep 2022; 12: 2585
• 20 Lee CS, Tyring AJ, Deruyter NP. et al. Deep-learning based, automated segmentation of macular edema in optical coherence tomography. Biomed Opt Express 2017; 8: 3440-3448
• 21 Schmidt-Erfurth U, Waldstein SM, Klimscha S. et al. Prediction of Individual Disease Conversion in Early AMD Using Artificial Intelligence. Invest Ophthalmol Vis Sci 2018; 59: 3199-3208
• 22 Russakoff DB, Lamin A, Oakley JD. et al. Deep Learning for Prediction of AMD Progression: A Pilot Study. Invest Ophthalmol Vis Sci 2019; 60: 712-722
• 23 Banerjee I, de Sisternes L, Hallak JA. et al. Prediction of age-related macular degeneration disease using a sequential deep learning approach on longitudinal SD-OCT imaging biomarkers. Sci Rep 2020; 10: 15434
• 24 Yim J, Chopra R, Spitz T. et al. Predicting conversion to wet age-related macular degeneration using deep learning. Nat Med 2020; 26: 892-899
• 25 Schmidt-Erfurth U, Bogunovic H, Sadeghipour A. et al. Machine Learning to Analyze the Prognostic Value of Current Imaging Biomarkers in Neovascular Age-Related Macular Degeneration. Ophthalmol Retina 2018; 2: 24-30
• 26 Kawczynski MG, Bengtsson T, Dai J. et al. Development of Deep Learning Models to Predict Best-Corrected Visual Acuity from Optical Coherence Tomography. Transl Vis Sci Technol 2020; 9: 51
• 27 Rohm M, Tresp V, Müller M. et al. Predicting Visual Acuity by Using Machine Learning in Patients Treated for Neovascular Age-Related Macular Degeneration. Ophthalmology 2018; 125: 1028-1036
• 28 Bogunovic H, Waldstein SM, Schlegl T. et al. Prediction of Anti-VEGF Treatment Requirements in Neovascular AMD Using a Machine Learning Approach. Invest Ophthalmol Vis Sci 2017; 58: 3240-3248
• 29 Romo-Bucheli D, Erfurth US, Bogunovic H. End-to-End Deep Learning Model for Predicting Treatment Requirements in Neovascular AMD From Longitudinal Retinal OCT Imaging. IEEE J Biomed Health Inform 2020; 24: 3456-3465
• 30 Pfau M, Sahu S, Rupnow RA. et al. Probabilistic Forecasting of Anti-VEGF Treatment Frequency in Neovascular Age-Related Macular Degeneration. Transl Vis Sci Technol 2021; 10: 30
• 31 Gallardo M, Munk MR, Kurmann T. et al. Machine Learning Can Predict Anti-VEGF Treatment Demand in a Treat-and-Extend Regimen for Patients with Neovascular AMD, DME, and RVO Associated Macular Edema. Ophthalmol Retina 2021; 5: 604-624
• 32 Leung EH, Stout JT. Antibiotics and antifungals in silicone oil. Int J Retina Vitreous 2019; 5: 50
• 33 Feng D, Chen X, Zhou Z. et al. A Preliminary Study of Predicting Effectiveness of Anti-VEGF Injection Using OCT Images Based on Deep Learning. Annu Int Conf IEEE Eng Med Biol Soc 2020; 2020: 5428-5431
• 34 Lee H, Kim S, Kim MA. et al. Post-Treatment Prediction of Optical Coherence Tomography Using a Conditional Generative Adversarial Network in Age-Related Macular Degeneration. Retina 2021; 41: 572-580
• 35 Zhao X, Zhang X, Lv B. et al. Optical coherence tomography-based short-term effect prediction of anti-vascular endothelial growth factor treatment in neovascular age-related macular degeneration using sensitive structure guided network. Graefes Arch Clin Exp Ophthalmol 2021; 259: 3261-3269