LCFNet: A lightweight context fusion network for COVID-19 segmentation

Qing Wang; Weijie Hu; Jiayi Wang; Lingli Luo; Xiaolong Ge; Junxi Chen; Lingna Chen

doi:10.1117/12.2640063

23 May 2022 LCFNet: A lightweight context fusion network for COVID-19 segmentation

Qing Wang, Weijie Hu, Jiayi Wang, Lingli Luo, Xiaolong Ge, Junxi Chen, Lingna Chen

Proceedings Volume 12254, International Conference on Electronic Information Technology (EIT 2022); 122541R (2022) https://doi.org/10.1117/12.2640063
Event: International Conference on Electronic Information Technology (EIT 2022), 2022, Chengdu, China

Abstract

The rapid and uncontrollable spread of COVID-19 has seriously threatened global public health. Rapid and accurate diagnosis of COVID-19 is the main key to control and manage the epidemic. COVID-19 segmentation can provide great insights to accelerate clinical decisions. COVID-19 segmentation based on deep learning method has attracted extensive research in the field of medical image analysis. However, most existing networks are heavyweight networks, which causes structural redundancy and expensive computational cost. Moreover, the segmentation problem of low-contrast COVID-19 image and the obscure boundary between the infected area and normal tissues affects accuracy of segmentation. To solve the problems, we propose a lightweight contextual information fusion network, LCFNet, for COVID-19 segmentation. We introduce a contextual information fusion strategy combining multiple global pyramid guidance (GPG) with scale-aware pyramid fusion (SAPF) module and deep supervision (DS) module, which can capture more fine-grained image features. We conduct experiments on two COVID-19 datasets. We perform the ablation studies, demonstrating the effectiveness of key components of the proposed method. Compared with traditional segmentation methods, LCFNet model match more consistently with the ground-truth boundary, which shows the superiority of the proposed method. Moreove, LCFNet has 1.68M parameters, which demonstrates the robustness of the proposed method. Our proposed method can further induce the number of model parameters. Compared with the state-of-the-art methods, the proposed approach has achieved significant improvements and is also superior to other segmentation methods.

Citation Download Citation

Qing Wang, Weijie Hu, Jiayi Wang, Lingli Luo, Xiaolong Ge, Junxi Chen, and Lingna Chen "LCFNet: A lightweight context fusion network for COVID-19 segmentation", Proc. SPIE 12254, International Conference on Electronic Information Technology (EIT 2022), 122541R (23 May 2022); https://doi.org/10.1117/12.2640063

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image segmentation

Data modeling

Information fusion

Performance modeling

Computer programming

Surface plasmons

Computed tomography

Show All Keywords

Keywords/Phrases

Search In:

Publication Years