# Learning to Address Intra-segment Misclassification in Retinal Imaging

arXiv: https://arxiv.org/abs/2104.12138 · HTML: https://mlsanity.com/paper/2104.12138/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 25 Apr 2021.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Semantic Segmentation using Adversarial Networks](https://mlsanity.com/paper/1611.08408/) (2016)
- [Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step](https://mlsanity.com/paper/1710.08446/) (2017)
- [Towards a glaucoma risk index based on simulated hemodynamics from fundus images](https://mlsanity.com/paper/1805.10273/) (2018)
- [Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks](https://mlsanity.com/paper/1706.09318/) (2017)
- [Multi-Task Neural Networks with Spatial Activation for Retinal Vessel Segmentation and Artery/Vein Classification](https://mlsanity.com/paper/2007.09337/) (2020)
- [TR-GAN: Topology Ranking GAN with Triplet Loss for Retinal Artery/Vein Classification](https://mlsanity.com/paper/2007.14852/) (2020)
- [Joint Learning of Vessel Segmentation and Artery/Vein Classification with Post-processing](https://mlsanity.com/paper/2005.13337/) (2020)

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

- [LUNet: Deep Learning for the Segmentation of Arterioles and Venules in High Resolution Fundus Images](https://mlsanity.com/paper/2309.05780/) (2023)
- [Deep Learning for Ophthalmology: The State-of-the-Art and Future Trends](https://mlsanity.com/paper/2501.04073/) (2025)
- [Improve Retinal Artery/Vein Classification via Channel Couplin](https://mlsanity.com/paper/2508.03738/) (2025)
- [VAFO-Loss: VAscular Feature Optimised Loss Function for Retinal Artery/Vein Segmentation](https://mlsanity.com/paper/2203.06425/) (2022)
- [Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling](https://mlsanity.com/paper/2503.01190/) (2025)
- [GrInAdapt: Scaling Retinal Vessel Structural Map Segmentation Through Grounding, Integrating and Adapting Multi-device, Multi-site, and Multi-modal Fundus Domains](https://mlsanity.com/paper/2503.05991/) (2025)

## Abstract (arXiv)

Accurate multi-class segmentation is a long-standing challenge in medical imaging, especially in scenarios where classes share strong similarity. Segmenting retinal blood vessels in retinal photographs is one such scenario, in which arteries and veins need to be identified and differentiated from each other and from the background. Intra-segment misclassification, i.e. veins classified as arteries or vice versa, frequently occurs when arteries and veins intersect, whereas in binary retinal vessel segmentation, error rates are much lower. We thus propose a new approach that decomposes multi-class segmentation into multiple binary, followed by a binary-to-multi-class fusion network. The network merges representations of artery, vein, and multi-class feature maps, each of which are supervised by expert vessel annotation in adversarial training. A skip-connection based merging process explicitly maintains class-specific gradients to avoid gradient vanishing in deep layers, to favor the discriminative features. The results show that, our model respectively improves F1-score by 4.4%, 5.1%, and 4.2% compared with three state-of-the-art deep learning based methods on DRIVE-AV, LES-AV, and HRF-AV data sets. Code: https://github.com/rmaphoh/Learning-AVSegmentation