EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Spatially Grounded Neurosymbolic AI for Explainable Retinal Disease Classification From OCT Images

Leandro Inferrera, Alessandro Biscontin, Miloš Ajcevic, Agostino Accardo, Alessandro Drigo, Daniele Tognetto, Aleksandar Miladinovic

Translational Vision Science & Technology · 2026

DOI: 10.1167/tvst.15.10.36 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2026. Verfasst von Leandro Inferrera und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine, Surgery and Health Sciences, Ophthalmology Clinic, University of Trieste, Italy. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Retinal Diseases, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To develop and evaluate a spatially grounded neurosymbolic AI framework for explainable multilabel retinal disease classification from optical coherence tomography (OCT) images, integrating convolutional neural network (CNN)-based retinal sign extraction, symbolic clinical reasoning, and retinal-layer spatial information.

Methods

Spectral-domain OCT B-scans were retrospectively collected and classified into ten categories: dry and wet age-related macular degeneration, central serous chorioretinopathy, myopic chorioretinopathy, epiretinal membrane, pseudomacular hole, lamellar macular hole, full-thickness macular hole, diabetic retinopathy, and normal retina. The model combined a CNN backbone with SegFormer-derived retinal-layer maps and mask-guided attention to estimate continuous OCT sign probabilities, which were propagated through expert-defined symbolic rules. Performance was evaluated using multilabel precision, recall, F1-score, confusion matrices, and receiver operating characteristic analysis. Inference was also performed on 402 OCT images from pathologies outside the target taxonomy.

Results

Micro-average precision, recall, and F1-score were 0.91, 0.81, and 0.86, respectively; weighted-average values were 0.91, 0.81, and 0.85, and macro-average values were 0.78, 0.71, and 0.74. The micro-average AUC was 0.98. None of the 402 out-of-taxonomy pathological OCT images received a positive Normal-class prediction at the predefined 0.5 threshold.

Conclusions

The spatially grounded neurosymbolic framework provided interpretable multilabel OCT classification and showed conservative behavior on pathological images outside the modeled taxonomy. This should not be interpreted as diagnostic recognition of unseen diseases. Translational Relevance: The framework may support transparent, sign-based, and anatomically grounded AI-assisted OCT interpretation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceRetinal DiseasesArtificial IntelligenceHumansConvolutional Neural NetworksRetrospective StudiesROC CurveRetina

Autor:innen und Institutionen

  • Department of Medicine, Surgery and Health Sciences, Ophthalmology Clinic, University of Trieste, Italy.
  • Institute for Maternal and Child Health IRCCS "Burlo Garofolo," Italy.
  • Department of Engineering and Architecture, University of Trieste, Italy.

Zitieren

APA

Inferrera, L., Biscontin, A., Ajcevic, M., Accardo, A., Drigo, A., Tognetto, D., & Miladinovic, A. (2026). Spatially Grounded Neurosymbolic AI for Explainable Retinal Disease Classification From OCT Images. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.15.10.36

Vancouver

Inferrera L, Biscontin A, Ajcevic M, Accardo A, Drigo A, Tognetto D, et al. Spatially Grounded Neurosymbolic AI for Explainable Retinal Disease Classification From OCT Images. Translational Vision Science & Technology. 2026. doi:10.1167/tvst.15.10.36

BibTeX
@article{Inferrera2026,
  author = {Inferrera, Leandro and Biscontin, Alessandro and Ajcevic, Miloš and Accardo, Agostino and Drigo, Alessandro and Tognetto, Daniele and Miladinovic, Aleksandar},
  title = {Spatially Grounded Neurosymbolic AI for Explainable Retinal Disease Classification From OCT Images},
  journal = {Translational Vision Science & Technology},
  year = {2026},
  doi = {10.1167/tvst.15.10.36}
}
Kostenlos starten →