# Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification

arXiv: https://arxiv.org/abs/2607.21068 · HTML: https://mlsanity.com/paper/2607.21068/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning](https://mlsanity.com/paper/2012.11905/) (2020)
- [Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging](https://mlsanity.com/paper/2008.02766/) (2020)
- [Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning](https://mlsanity.com/paper/2005.14284/) (2020)
- [Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder](https://mlsanity.com/paper/2408.01571/) (2024)
- [Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis](https://mlsanity.com/paper/2206.00390/) (2022)
- [Residual-CycleGAN based Camera Adaptation for Robust Diabetic Retinopathy Screening](https://mlsanity.com/paper/2007.15874/) (2020)
- [Selective Synthetic Augmentation with Quality Assurance](https://mlsanity.com/paper/1912.03837/) (2019)
- [Counterfactual Explanation and Instance-Generation using Cycle-Consistent Generative Adversarial Networks](https://mlsanity.com/paper/2301.08939/) (2023)

## Abstract (arXiv)

Automated detection of vision impairing retina-based ocular conditions from fundus images is important for early screening, timely referral and reducing dependency on specialist-only assessment, for which neural network-based deep learning (DL) models have been widely utilized. However, explainability of the DL frameworks remains a major bottleneck for clinical adoption, particularly when model decisions are not linked to retinal regions that are clinically meaningful. To address this issue, this study presents CounterFundus, a novel CycleGAN-driven counterfactual explainability framework, integrating EfficientNet-B5-based retinal disease detection with visually interpretable disease-to-normal fundus image translation. For each pathological image, the counterfactual yielded by the CycleGAN generator represents an estimated healthy counterpart and the resultant difference map is utilized to localize disease-associated retinal changes. Unlike conventional post-hoc saliency methods, CounterFundus provides counterfactual explanations through visually plausible disease-to-normal retinal translation. Thereafter, to quantify the spatial agreement between counterfactual difference maps and classifier saliency, the Counterfactual-Classifier Alignment Score (CCAS) is introduced, embedding Spearman correlation, binary IoU and pointing accuracy into a single assessment protocol. To this end, EigenCAM-aligned evaluation demonstrates that the generated counterfactual explanations remain spatially consistent with classifier-relevant retinal evidence across all CCAS dimensions. Along with that, ablation studies further confirm that CCAS-filtered counterfactual augmentation improves the downstream classification performance in fundus images, establishing CounterFundus as a clinically-grounded, explainable artificially intelligence (XAI) framework for retinal disease detection.