Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2025 Jul;263(7):1789-1800.
doi: 10.1007/s00417-025-06790-0. Epub 2025 Mar 10.

Imaging biomarkers and artificial intelligence for diagnosis, prediction, and therapy of macular fibrosis in age-related macular degeneration: Narrative review and future directions

Rishikesh Gandhewar  1 , Thales Guimaraes  2   3 , Sagnik Sen  2   3 , Nikolas Pontikos  2   3 , Ismail Moghul  2 , Theodoros Empeslidis  4   5 , Michel Michaelides  2   3 , Konstantinos Balaskas  6   7
Affiliations
Review

Imaging biomarkers and artificial intelligence for diagnosis, prediction, and therapy of macular fibrosis in age-related macular degeneration: Narrative review and future directions

Rishikesh Gandhewar et al. Graefes Arch Clin Exp Ophthalmol. 2025 Jul.

Abstract

Macular fibrosis is an end-stage complication of neovascular Age-related Macular Degeneration (nAMD) with a complex and multifactorial pathophysiology that can lead to significant visual impairment. Despite the success of anti-vascular endothelium growth factors (anti-VEGF) over the last decade that revolutionised the management and visual prognosis of nAMD, macular fibrosis develops in a significant proportion of patients and, along with macular atrophy (MA), is a main driver of long-term vision deterioration. There remains an unmet need to better understand macular fibrosis and develop anti-fibrotic therapies. The use of imaging biomarkers in combination with novel Artificial Intelligence (AI) algorithms holds significant potential for improving the accuracy of diagnosis, disease monitoring, and therapeutic discovery for macular fibrosis. In this review, we aim to provide a comprehensive overview of the current state of knowledge regarding the various imaging modalities and biomarkers for macular fibrosis alongside outlining potential avenues for AI applications. We discuss manifestations of macular fibrosis and its precursors with diagnostic and prognostic significance on various imaging modalities, including Optical Coherence Tomography (OCT), Colour Fundus Photography (CFP), Fluorescein Angiography (FA), OCT-Angiography (OCTA) and collate data from prospective and retrospective research on known biomarkers. The predominant role of OCT for biomarker identification is highlighted. The review coincides with a resurgence of intense research interest in academia and industry for therapeutic discovery and clinical testing of anti-fibrotic molecules.

Keywords: Age-related Macular Degeneration; Anti-Vascular Endothelium Growth Factors; Artificial Intelligence; Biomarkers; Colour Fundus Photography; Fluorescein Angiography; Macular Fibrosis; Optical Coherence Tomography.

PubMed Disclaimer

Conflict of interest statement

Declarations. Informed consent: Not applicable. Conflict of interest: Nikolas Pontikos is the non-salaried co-founder and director of Phenopolis Ltd. Ismail Moghul has equity in READ AI Konstantinos Balaskas has equity in READ AI received speaker fees from Novartis, Bayer, Alimera, Allergan, Roche, and Heidelberg; meeting or travel fees from Novartis, Bayer and Boehringer-Ingelheim; compensation for being on an advisory board from Novartis, Bayer and Apellis; consulting fees from Novartis, Roche and Google; and research support from Apellis, Novartis, and Bayer. All other authors declare no relevant conflicts of interest. Research involving human participants and/or animals: This article does not contain any studies with humans or animals performed by any of the authors.

Figures

Fig. 1
Fig. 1
(A) Flowchart outlining literature review strategy (B) Summary of study types included
Fig. 2
Fig. 2
Optical Coherence Tomography b-scans from Baseline visit (pre-treatment) of patient with neovascular Age-related Macular Degeneration (nAMD) at Erie, PA (A-D). (A) b-scan 11, shallow PED with presence of SHRM and Sub-RPE HRM overlying Sub-RPE fluid. (B) b-scan 13, PED with HRM overlying a pocket of sub-RPE fluid with ill-defined SHRM. (C) b-scan 16, higher PED area with HRM overlying a small pocked of sub-RPE fluid and area of more clearly defined SHRM and presence of SRF. (D) b-scan 19, shallower area of hyper-reflective PED with higher reflectivity SHRM and modest definition with presence of SRF. Automated AI delineation of nAMD features* on corresponding OCT b-scans (E–H). (E) Shallower PEDs, SHRM and hyper-reflective PED, Sub-RPE fluid (F) PED with small pocket of sub-RPE fluid, larger area of SHRM (G) PED with hyper reflective content with small pocket of sub-RPE fluid, SHRM and SRF. Key. (A-D) Green arrow: Pigment Epithelium Detachments (PED), Orange arrow: Sub-Retinal Hyper-reflective Material (SHRM), Yellow asterisk: Sub-RPE Fluid, Blue asterisk: Subretinal fluid (SRF). (E–H) Pink area: PED, Purple area: HRM (including SHRM), Red area: Sub-RPE fluid, Blue area: SRF
Fig. 3
Fig. 3
Central macular Optical Coherence Tomography b-scan from a patient with neovascular Age-related Macular Degeneration receiving treatment at Erie, PA (A-C). (A) Baseline visit, small fibrovascular PEDs with marked Intraretinal Fluid (IRF). (B) After 12 injections of anti-VEGF, large fibrovascular PED with area of marked hyper-reflectivity, SHRM and pocket of SRF. (C) After 36 injections of anti-VEGF, shallow PED with fibrotic content, extensive well-defined SHRM with increased reflectivity indicative of Macular Fibrosis. Automated AI delineation of nAMD features* on corresponding OCT b-scans (D-F). (D) IRF and PEDs (E) PEDs, SHRM and SRF (F) Shallow PED and extensive SHRM. Key. (A-D) Green arrow: Pigment Epithelium Detachment (PED), Orange arrow: Sub-Retinal Hyper-Reflective Material (SHRM), Pink asterisk: Intraretinal fluid (IRF), Yellow asterisk: Subretinal Fluid (SRF). (E–H) Green area: IRF, Red area: PED, Yellow area: SHRM, Blue area: SRF. *Automated OCT segmentation of nAMD features performed using proprietary deep-learning segmentation algorithm developed by the RAID Ophthalmic reading Centre, NV, USA. The report on the development and validation of RAID AI is under peer-review. Figures 2 & 3 are provided as illustrative examples of AI potential in the study of macular fibrosis
See this image and copyright information in PMC

References

    1. Flaxman SR et al (2017) Global causes of blindness and distance vision impairment 1990–2020: a systematic review and meta-analysis. Lancet Glob Health 5(12):e1221–e1234 - PubMed
    1. Wong WL et al (2014) Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis. Lancet Glob Health 2(2):e106–e116 - PubMed
    1. Rosenfeld PJ et al (2006) Ranibizumab for neovascular age-related macular degeneration. N Engl J Med 355(14):1419–1431 - PubMed
    1. Rakic JLA, Brié H, Denhaerynck K, Pacheco C, Vancayzeele S, Hermans C, MacDonald K, Abraham I (2013) Real-world variability in ranibizumab treatment and associated clinical, quality of life, and safety outcomes over 24 months in patients with neovascular age-related macular degeneration: the HELIOS study. Clin Ophthalmol 7:1849–1858 - PMC - PubMed
    1. Brown DM et al (2009) Ranibizumab versus verteporfin photodynamic therapy for neovascular age-related macular degeneration: Two-year results of the ANCHOR study. Ophthalmology 116(1):57-65.e5 - PubMed

MeSH terms

LinkOut - more resources