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

arXiv: https://arxiv.org/abs/2405.07338 · HTML: https://mlsanity.com/paper/2405.07338/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 58 references that are in the map.
- First posted on arXiv 12 May 2024.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy](https://mlsanity.com/paper/1809.04430/) (2018)
- [SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation](https://mlsanity.com/paper/2004.03696/) (2020)
- [Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations](https://mlsanity.com/paper/1906.11031/) (2019)

## Built on by (most cited first, 6 of 6)

- [VR-FuseNet: A Fusion of Heterogeneous Fundus Data and Explainable Deep Network for Diabetic Retinopathy Classification](https://mlsanity.com/paper/2504.21464/) (2025)
- [An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI](https://mlsanity.com/paper/2505.16033/) (2025)
- [An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection](https://mlsanity.com/paper/2505.16039/) (2025)
- [Lightweight Convolutional Neural Networks for Retinal Disease Classification](https://mlsanity.com/paper/2506.03186/) (2025)
- [Transfer Learning and Explainable AI for Brain Tumor Classification: A Study Using MRI Data from Bangladesh](https://mlsanity.com/paper/2506.07228/) (2025)
- [LightVesselNet: An Ultra-Lightweight Sub-100K Parameter Network for Retinal Blood Vessel Segmentation](https://mlsanity.com/paper/2606.05354/) (2026)

## Abstract (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.