# Hard Exudate Segmentation Supplemented by Super-Resolution with Multi-scale Attention Fusion Module

arXiv: https://arxiv.org/abs/2211.09404 · HTML: https://mlsanity.com/paper/2211.09404/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Region Mutual Information Loss for Semantic Segmentation](https://mlsanity.com/paper/1910.12037/) (2019)
- [SROBB: Targeted Perceptual Loss for Single Image Super-Resolution](https://mlsanity.com/paper/1908.07222/) (2019)
- [Channel Splitting Network for Single MR Image Super-Resolution](https://mlsanity.com/paper/1810.06453/) (2018)
- [Is Image Super-resolution Helpful for Other Vision Tasks?](https://mlsanity.com/paper/1509.07009/) (2015)
- [Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification](https://mlsanity.com/paper/1812.11560/) (2018)
- [Machine Learning for Cataract Classification and Grading on Ophthalmic Imaging Modalities: A Survey](https://mlsanity.com/paper/2012.04830/) (2020)
- [SuperVessel: Segmenting High-resolution Vessel from Low-resolution Retinal Image](https://mlsanity.com/paper/2207.13882/) (2022)
- [Benefiting from Multitask Learning to Improve Single Image Super-Resolution](https://mlsanity.com/paper/1907.12488/) (2019)
- [Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentation](https://mlsanity.com/paper/2205.15720/) (2022)

## Built on by (most cited first, 3 of 3)

- [Learnable Ophthalmology SAM](https://mlsanity.com/paper/2304.13425/) (2023)
- [Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space Model](https://mlsanity.com/paper/2409.04356/) (2024)
- [When SAM Meets Sonar Images](https://mlsanity.com/paper/2306.14109/) (2023)

## Abstract (arXiv)

Hard exudates (HE) is the most specific biomarker for retina edema. Precise HE segmentation is vital for disease diagnosis and treatment, but automatic segmentation is challenged by its large variation of characteristics including size, shape and position, which makes it difficult to detect tiny lesions and lesion boundaries. Considering the complementary features between segmentation and super-resolution tasks, this paper proposes a novel hard exudates segmentation method named SS-MAF with an auxiliary super-resolution task, which brings in helpful detailed features for tiny lesion and boundaries detection. Specifically, we propose a fusion module named Multi-scale Attention Fusion (MAF) module for our dual-stream framework to effectively integrate features of the two tasks. MAF first adopts split spatial convolutional (SSC) layer for multi-scale features extraction and then utilize attention mechanism for features fusion of the two tasks. Considering pixel dependency, we introduce region mutual information (RMI) loss to optimize MAF module for tiny lesions and boundary detection. We evaluate our method on two public lesion datasets, IDRiD and E-Ophtha. Our method shows competitive performance with low-resolution inputs, both quantitatively and qualitatively. On E-Ophtha dataset, the method can achieve ≥3% higher dice and recall compared with the state-of-the-art methods.