SuperVessel: Segmenting High-resolution Vessel from Low-resolution Retinal Image

TL;DR

SuperVessel is a novel algorithm that enhances low-resolution retinal images to produce high-resolution vessel segmentation, accurately capturing tiny vessels while reducing computational load.

Contribution

The paper introduces a new super-resolution based segmentation method with specialized modules to improve tiny vessel detection from low-resolution images.

Findings

Achieves over 6% higher IoU than state-of-the-art methods.

Effectively captures tiny vessels in retinal images.

Demonstrates stronger stability across datasets.

Abstract

Vascular segmentation extracts blood vessels from images and serves as the basis for diagnosing various diseases, like ophthalmic diseases. Ophthalmologists often require high-resolution segmentation results for analysis, which leads to super-computational load by most existing methods. If based on low-resolution input, they easily ignore tiny vessels or cause discontinuity of segmented vessels. To solve these problems, the paper proposes an algorithm named SuperVessel, which gives out high-resolution and accurate vessel segmentation using low-resolution images as input. We first take super-resolution as our auxiliary branch to provide potential high-resolution detail features, which can be deleted in the test phase. Secondly, we propose two modules to enhance the features of the interested segmentation region, including an upsampling with feature decomposition (UFD) module and a feature interaction module (FIM) with a constraining loss to focus on the interested features. Extensive experiments on three publicly available datasets demonstrate that our proposed SuperVessel can segment more tiny vessels with higher segmentation accuracy IoU over 6%, compared with other state-of-the-art algorithms. Besides, the stability of SuperVessel is also stronger than other algorithms. We will release the code after the paper is published.