Interpretable Fundus Image Classification via Ring-Based Retinal Vasculature Features

Xiaoyan Li; Shixin Xu; Arvind Gupta; Huaxiong Huang

cs.CVAug 25, 2026

Interpretable Fundus Image Classification via Ring-Based Retinal Vasculature Features

Authors: Xiaoyan Li, Shixin Xu, Arvind Gupta, Huaxiong Huang

Organizations: Computer Science, University of Toronto, 27 King’s College Cir., Toronto, M5S 1A1, Ontario, Canada. · Zu Chongzhi Center, Duke Kunshan University, No.8 Duke Ave., Kunshan, 215300, Jiangsu, China. · Mathematics and Statistics, York University, 4700 Keele St., Toronto, M3J 1P3, Ontario, Canada. · Mathematics, Analytics, and Data Science Lab, Fields Institute for Research in Mathematical Sciences, 222 College Street, Toronto, M5T 3J1, Ontario, Canada.

Abstract

Retinal fundus photography is widely used for screening and monitoring ocular diseases, but many modern classification pipelines rely on deep latent representations and provide limited interpretability. This study develops an interpretable fundus image classification framework based on a ring-structured representation of the retinal vasculature centered on the optic disc. The method quantifies vessel geometry, color appearance, oxygenation-related vascular appearance, and vessel--background entropy within concentric retinal regions. These physiologically motivated descriptors are derived from vessel masks, image intensities, and optical-density measurements and aggregated across rings to capture spatial variation in vascular properties. Using only quantitative vascular descriptors, the proposed method achieved strong classification performance across three public fundus datasets. On HRF, it achieved 91.1% accuracy using automatically generated vessel masks, matching RETFound, a vision transformer pretrained on large-scale retinal fundus image data, under the same evaluation setting. Additional analyses suggest that pretrained image models are sensitive to acquisition-related spatial cues, including fundus scale and retinal position within the field of view, as well as broader non-vessel image characteristics. This framework may support interpretable disease classification, quantitative retinal phenotyping, and retinal biomarker discovery without requiring large task-specific training datasets.

Figures & tables

Dataset	Method	Acc.	Macro-F1	ROC-AUC	95% CI
HRF	Proposed (GT)	1.000	1.000	1.000	[0.921, 1.000]
	Proposed (Pred.)	0.911	0.910	0.964	[0.793, 0.965]
	RETFound	0.911	0.911	0.966	[0.793, 0.965]
	ViT-B/16	0.800	0.800	0.920	[0.662, 0.891]
	ConvNeXt-B	0.867	0.868	0.958	[0.738, 0.937]
	ResNet-50	0.778	0.780	0.901	[0.637, 0.875]

Table 1: Classification performance of the proposed method and pretrained image-based baselines. 0 0 footnotetext: Note: HRF and FIVES were evaluated using leave-one-out cross-validation, whereas SYSU was evaluated using stratified five-fold cross-validation. Accuracy and its 95% Wilson confidence interval were computed from aggregated out-of-fold predictions. Macro-F1 and ROC-AUC were also computed from the aggregated out-of-fold predictions. GT, ground-truth vessel masks; Pred., predicted vessel masks; SYSU, SUSTech-SYSU. For RETFound, the fine-tuned result is reported on HRF, whereas frozen-feature results are reported on FIVES and SYSU. On FIVES, all pretrained image-based baselines were evaluated using the FOV-standardized images described in Section 2.2 .

Panel of Figure 1 — Figure 1: Acquisition-related spatial characteristics in the FIVES dataset. (a) Distribution of the inscribed fundus FOV radius. (b) Spatial distribution of FOV centers. (c) Spatial distribution of optic-disc centers.

Panel of Figure 2 — Figure 2: Qualitative and quantitative comparison of explanation maps for a representative healthy fundus image. Both methods correctly classify the image as healthy. The RETFound map shows patch-level positive Integrated Gradients attributions for the predicted-versus-runner-up logit margin. Warmer colors indicate stronger positive contributions to the model’s preference for the predicted class over the runner-up class. The proposed heatmap shows signed evidence for the predicted class relative to the runner-up class ( $\Delta=\mathrm{Predicted}-\mathrm{Runner\text{-}up}$ ), aggregated by ring and visualized on the retinal vasculature. Panel (d) summarizes the top ring-wise feature contributions supporting the predicted class over the runner-up class.

Figure 3: Representative image-level examples linking selected ring-wise vascular descriptors to clinically relevant retinal vasculature abnormalities. Cyan indicates the vessel mask, and the yellow band indicates the highlighted optic-disc-centered annulus. Each row compares a disease example with a healthy reference image for the same feature and annular region. The examples show reduced vessel area fraction in glaucoma, reduced artery–vein caliber ratio in diabetic retinopathy, and increased caliber variability in diabetic retinopathy. Feature values are compared with the healthy reference distribution for the same ring and descriptor.

Segment. Method	HRF			FIVES			SUSTech-SYSU
Segment. Method	Acc.	F1	95% CI	Acc.	F1	95% CI	Acc.	F1	95% CI
FR-UNet	0.844	0.844	[0.712, 0.923]	0.685	0.653	[0.637, 0.730]	0.896	0.888	[0.876, 0.914]
SA-UNetv2	0.800	0.800	[0.662, 0.891]	0.722	0.695	[0.675, 0.764]	0.893	0.884	[0.872, 0.910]
RIP-AV	0.911	0.909	[0.793, 0.965]	0.724	0.700	[0.677, 0.766]	0.896	0.888	[0.875, 0.913]

Table 2: Comparison of the proposed ring-based method using vessel masks obtained from three segmentation algorithms: FR-UNet Liu et al. (2022a) , SA-UNetv2 Guo et al. (2026) , and RIP-AV Dai et al. (2024) . Results are reported as mean accuracy, macro F1, and 95% confidence intervals.

Model	Acc.	Macro-F1	ROC-AUC	95% CI (Acc.)
ResNet-50	0.356	0.248	0.637	[0.232, 0.502]
ViT-B/16	0.333	0.167	0.694	[0.214, 0.479]
ConvNeXt-B	0.356	0.211	0.596	[0.232, 0.502]
RETFound	0.333	0.167	0.524	[0.214, 0.479]
Proposed without RGB color and SO 2 -proxy features	0.733	0.731	0.844	[0.590, 0.840]
Proposed with normalized SO 2 -proxy descriptor	0.778	0.780	0.849	[0.637, 0.875]

Table 3: FIVES-to-HRF external validation. Models were trained on FIVES and evaluated directly on HRF. Ground-truth vessel masks were used for the proposed method in both datasets to assess feature transfer independently of vessel-segmentation errors.

Figure 4: Overview of the proposed ring-based classification framework. Concentric annular regions are defined around the optic disc, and vessel geometry, red–green color, OD-derived SO 2 -proxy, and vessel–background entropy features are extracted within each ring. The resulting descriptors are concatenated, standardized, and classified using logistic regression.

Panel of Figure 5 — Figure 5: Representative ring-wise vascular feature extraction. (a) Vessel branch points extracted from the skeletonized vasculature; yellow dots indicate skeleton pixels with more than two 8-connected neighbors. (b) Local vessel-diameter estimation along representative centerline segments. Red and blue indicate arterial and venous segments, respectively; orange indicates uncertain or unknown vessel labels; transverse markers indicate sampled local diameters. (c) Estimated OD-derived SO 2 -proxy values along the retinal vasculature of a representative healthy image.

Explore similar work

Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images
May 12, 2024Fatema Tuj Johora Faria, Mukaffi Bin Moin, Pronay Debnath +2Image Segmentation Retinal Vessel Segmentation
aDepartment of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka, Bangladesh
Towards Interpretable Foundation Models for Retinal Fundus Images
Mar 19, 2026Samuel Ofosu Mensah, Camila Roa, Kerol Djoumessi +1Medical Imaging Medical Imaging Foundation Models
Hertie Institute for AI in Brain Health, University of Tübingen, Germany · Tübingen AI Center, University of Tübingen, Germany
Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representations
Feb 23, 2025Laurin Lux, Alexander H. Berger, Maria Romeo Tricas +8Medical Imaging Diabetic Retinopathy Grading
Munich Center for Machine Learning (MCML), Munich, Germany · School of Medicine and Health, TUM University Hospital, Munich, Germany · School of Computation, Information and Technology, TUM, Munich, Germany

May 12, 2024J/K move · Enter open · S save

Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Pronay Debnath, Asif Iftekher Fahim+1

aDepartment of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka, Bangladesh

Image Segmentation Retinal Vessel Segmentation Hybrid CNN-Transformer Architectures U-Net Medical Image Classification Medical Image Segmentation+3

Open paper AskPDF arXiv

Early detection of vision-threatening conditions such as diabetic retinopathy, glaucoma, and age-related macular degeneration depends on retinal fundus image analysis, but manual assessment is slow and expert-dependent. Automated convolutional neural networks classify fundus images accurately yet act as black boxes, and existing retinal vessel segmentation methods lose discriminative power under pathology and seldom exploit attention or transformer backbones. Using the FIVES and DRIVE fundus datasets, we develop a two-pipeline framework that pairs four-class disease classification with attention- and transformer-based vessel segmentation, organised in three stages: (1) FIVES images are augmented by rotation and horizontal and vertical flips and used to fine-tune eight ImageNet-pretrained CNNs: ResNet101, DenseNet169, Xception, InceptionV3, DenseNet121, InceptionResNetV2, ResNet50, and EfficientNetB0. (2) Five gradient-based explanation methods, Grad-CAM, Grad-CAM++, Score-CAM, Faster Score-CAM, and Layer-CAM, are computed on the final convolutional block of each classifier and compared qualitatively across architectures. (3) Ten U-Net variants are benchmarked for vessel segmentation: TransUNet (hybrid CNN--Transformer encoder) and Attention U-Net (gated skip connections), evaluated with ResNet50V2, ResNet101V2, and ResNet152V2 backbones, along with additional Attention U-Net configurations using DenseNet backbones, and the fully transformer-based Swin-UNet. ResNet101 gives the highest classification accuracy: 94.17% (F1 0.942)

>

88.33% for EfficientNetB0. For segmentation, the architecture ranking is consistent on both datasets: Attention U-Net

>

TransUNet

>

Swin-UNet. The strongest configuration is Attention U-Net with a ResNet101V2 backbone: FIVES IoU 0.722, Dice 0.838; DRIVE IoU 0.648, Dice 0.787, lifting DRIVE IoU 60.80

\rightarrow

64.83 over a prior custom U-Net.

Abstract

Explore similar work

Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images

Towards Interpretable Foundation Models for Retinal Fundus Images

Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representations