A neuro-symbolic framework for cross-hospital glaucoma detection from fundus images

Article Open access Published: 11 November 2026 Scientific Reports ( 2026 ) Cite this article We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record.

All legal disclaimers apply. Abstract In 2020, an estimated 79.6 million people were affected by glaucoma, which is expected to increase to 111.8 million by 2040. Early identification is critical, but most automatic detection systems do not generalize well across hospitals and imaging devices.

In this paper, we present the neuro-symbolic glaucoma detection framework (NSC), which combines an efficient network (EfficientNet-B4) using dual spatial-channel attention, a six-node anatomical graph attention network (GAT-GNN), and a differentiable symbolic constraint module that applies four clinical fuzzy logic rules involving cup-to-disc ratio (CDR), rim thinning, defects in retinal nerve fiber layer (RNFL), and vessel density.

The framework is trained on 9100 fundus images drawn from a curated corpus of 12,619 images across eight datasets and eight countries. The 12,134 non-holdout images were split 75%/12.5%/12.5% into 9100 training, 1517 validation and 1517 test images; the 485-image RIM-ONE DL set was held out entirely as a never-seen cross-hospital test set.

Augmentation is applied during training and does not alter the number of distinct images in any split. Among the evaluated variants the highest cross-hospital AUC is obtained by EfficientNet-B4+Symbolic (B4, 0.6997, 95% CI 0.649–0.750); the differences between B2, B3 and B4 on the cross-hospital holdout are small and not statistically significant.

EfficientNet-B4+GAT-GNN (B3) is proposed as the deployment configuration on the basis of in-distribution performance and inference cost rather than cross-hospital AUC. The full NSC model achieves a test AUC of 0.946 (95% CI 0.934–0.958) and sensitivity of 0.900, while B3 achieves the highest in-distribution AUC among the evaluated variants at 0.9612 (95% CI 0.951–0.972).

Ablation studies show that adding the GAT-GNN to EfficientNet-B4 improved in-distribution test AUC by 1.4 percentage points in the single-seed ablation (0.9472–0.9612) and the performance of GNN-symbolic interaction in terms of cross-hospital AUC is reduced by 8.1 points (z = − 3.08, p = 0.002).

Across three independent training runs (seeds 42, 1337, and 2024), B3 achieved a mean test AUC of 0.9602 ± 0.0002, compared with 0.9492 ± 0.0015 for B2. On images excluded from training, agreement between the CDR proxy and expert-measured cup-to-disc ratio is weak and inconsistent across datasets ( \(\rho = 0.549\) , \(n = 26\) on DRISHTI-GS; \(\rho = 0.081\) , \(n = 100\) on REFUGE2), so anatomical grounding of the CDR proxy is not established.

Validation of the CDR, RNFL, rim and vessel latent representations against segmentation ground truth remains future work. To the best of the authors’ knowledge, this is the first neuro-symbolic framework for glaucoma detection from fundus images, combining differentiable fuzzy constraints with anatomical graph reasoning, evaluated in a strict cross-hospital holdout setting (Canon CR-2 to Nidek AFC-210) without using segmentation masks.

Acknowledgements The authors sincerely thank Manipal University Jaipur for supporting this research and covering the Article Processing Charges (APC). Funding Open access funding provided by Manipal University Jaipur. Open access APC funding provided by Manipal University Jaipur.

This research received no external funding. Author information Author notes These authors contributed equally to this work: Prashant Hemrajani, Khushboo Aggarwal, Manoj Kumar Bohra, Satpal Singh Kushwaha and Varsha Himthani. Authors and Affiliations Department of IoT and Intelligent Systems, Manipal University Jaipur, Dehmi Kalan, Off Jaipur-Ajmer Expressway, Jaipur, Rajasthan, 303007, India Prashant Hemrajani & Manoj Kumar Bohra Department of Computer Science and Engineering, Manipal University Jaipur, Dehmi Kalan, Off Jaipur-Ajmer Expressway, Jaipur, Rajasthan, 303007, India Khushboo Aggarwal & Satpal Singh Kushwaha School of Computer Science and Engineering, Bennett University, TechZone II, Greater Noida, Uttar Pradesh, 201310, India Varsha Himthani Authors Prashant Hemrajani Khushboo Aggarwal Varsha Himthani Manoj Kumar Bohra Satpal Singh Kushwaha Corresponding authors Correspondence to Varsha Himthani or Satpal Singh Kushwaha .

Ethics declarations Competing interests The authors declare that they have no competing interests. Third party material The datasets used in this study are publicly available, de-identified retinal fundus image datasets. All datasets have been used within the bounds of the public licenses attached to each.

Ethical approval was not applicable. Additional information Publisher's note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Rights and permissions Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material.

You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material.

If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/ .

Reprints and permissions About this article Cite this article Hemrajani, P., Aggarwal, K., Himthani, V. et al. A neuro-symbolic framework for cross-hospital glaucoma detection from fundus images. Sci Rep (2026). https://doi.org/10.1038/s41598-026-75977-0 Download citation Received : 08 June 2026 Accepted : 11 October 2026 Published : 11 November 2026 DOI : https://doi.org/10.1038/s41598-026-75977-0 Keywords