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

Dandan Shan; Zihan Li; Wentao Chen; Qingde Li; Jie Tian; Qingqi Hong

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

Image and Video Processing 2023-03-02 v1 Computation and Language Computer Vision and Pattern Recognition Information Retrieval

Authors: Dandan Shan , Zihan Li , Wentao Chen , Qingde Li , Jie Tian , Qingqi Hong

View on arXiv ↗ PDF ↗

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.

Keywords

covid-19 detection and diagnosis medical image segmentation deep learning segmentation

Cite

@article{arxiv.2303.00279,
  title  = {Coarse-to-Fine Covid-19 Segmentation via Vision-Language Alignment},
  author = {Dandan Shan and Zihan Li and Wentao Chen and Qingde Li and Jie Tian and Qingqi Hong},
  journal= {arXiv preprint arXiv:2303.00279},
  year   = {2023}
}

Comments

Accepted by ICASSP 2023

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

Abstract

Keywords

Cite

Comments

Related papers