AI-Based Response Classification After Anti-VEGF Loading in Neovascular Age-Related Macular Degeneration

Basit Öğe Kaydı
dc.contributor.authorFirat, Murat
dc.contributor.authorFirat, Ilknur Tuncer
dc.contributor.authorUstundag, Ziynet Fadillioglu
dc.contributor.authorOzturk, Emrah
dc.contributor.authorTuncer, Taner
dc.date.accessioned2026-04-04T13:31:09Z
dc.date.available2026-04-04T13:31:09Z
dc.date.issued2025
dc.departmentİnönü Üniversitesi
dc.description.abstractBackground/Objectives: Wet age-related macular degeneration (AMD) is a progressive retinal disease characterized by macular neovascularization (MNV). Currently, the standard treatment for wet AMD is intravitreal anti-VEGF administration, which aims to control disease activity by suppressing neovascularization. In clinical practice, the decision to continue or discontinue treatment is largely based on the presence of fluid on optical coherence tomography (OCT) and changes in visual acuity. However, discrepancies between anatomic and functional responses can occur during these assessments. Methods: This article presents an artificial intelligence (AI)-based classification model developed to objectively assess the response to anti-VEGF treatment in patients with AMD at 3 months. This retrospective study included 120 patients (144 eyes) who received intravitreal bevacizumab treatment. After bevacizumab loading treatment, the presence of subretinal/intraretinal fluid (SRF/IRF) on OCT images and changes in visual acuity (logMAR) were evaluated. Patients were divided into three groups: Class 0, active disease (persistent SRF/IRF); Class 1, good response (no SRF/IRF and >= 0.1 logMAR improvement); and Class 2, limited response (no SRF/IRF but with <0.1 logMAR improvement). Pre-treatment and 3-month post-treatment OCT image pairs were used for training and testing the artificial intelligence model. Based on this grouping, classification was performed with a Siamese neural network (ResNet-18-based) model. Results: The model achieved 95.4% accuracy. The macro precision, macro recall, and macro F1 scores for the classes were 0.948, 0.949, and 0.948, respectively. Layer Class Activation Map (LayerCAM) heat maps and Shapley Additive Explanations (SHAP) overlays confirmed that the model focused on pathology-related regions. Conclusions: In conclusion, the model classifies post-loading response by predicting both anatomic disease activity and visual prognosis from OCT images.
dc.identifier.doi10.3390/diagnostics15172253
dc.identifier.issn2075-4418
dc.identifier.issue17
dc.identifier.orcid0000-0003-0526-4526
dc.identifier.orcid0000-0001-6040-9332
dc.identifier.pmid40941740
dc.identifier.scopus2-s2.0-105015685771
dc.identifier.scopusqualityQ2
dc.identifier.urihttps://doi.org/10.3390/diagnostics15172253
dc.identifier.urihttps://hdl.handle.net/11616/108613
dc.identifier.volume15
dc.identifier.wosWOS:001571509500001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherMdpi
dc.relation.ispartofDiagnostics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250329
dc.subjectage-related macular degeneration
dc.subjectanti-VEGF therapy
dc.subjectSiamese network
dc.subjectLayerCam
dc.titleAI-Based Response Classification After Anti-VEGF Loading in Neovascular Age-Related Macular Degeneration
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu