Coarse-to-Fine Covid-19 Segmentation via Vision-Language Alignment

TL;DR

This paper introduces C2FVL, a novel coarse-to-fine segmentation framework that leverages vision-language alignment with text descriptions to improve COVID-19 lesion segmentation accuracy on X-ray and CT images.

Contribution

The paper presents a new vision-language aligned segmentation method that incorporates textual lesion information to enhance COVID-19 image segmentation performance.

Findings

Outperforms state-of-the-art segmentation methods

Effective on both chest X-ray and CT datasets

Improves prediction accuracy on challenging datasets

Abstract

Segmentation of COVID-19 lesions can assist physicians in better diagnosis and treatment of COVID-19. However, there are few relevant studies due to the lack of detailed information and high-quality annotation in the COVID-19 dataset. To solve the above problem, we propose C2FVL, a Coarse-to-Fine segmentation framework via Vision-Language alignment to merge text information containing the number of lesions and specific locations of image information. The introduction of text information allows the network to achieve better prediction results on challenging datasets. We conduct extensive experiments on two COVID-19 datasets including chest X-ray and CT, and the results demonstrate that our proposed method outperforms other state-of-the-art segmentation methods.