Attention-RefNet: Interactive Attention Refinement Network for Infected Area Segmentation of COVID-19
Authors:
- Titinunt KitrungrotsakulTKTitinunt Kitrungrotsakul
- Qingqing ChenQCQingqing Chen
- Huitao WuHWHuitao Wu
- Yutaro IwamotoYIYutaro Iwamoto
- Hongjie HuHHHongjie Hu
- Wenchao ZhuWZWenchao Zhu
- Chao ChenCCChao Chen
- Fangyi XuFXFangyi Xu
- Yong ZhouYZYong Zhou
- Lanfen LinLLLanfen Lin
- Ruofeng TongRTRuofeng Tong
- Jingsong LiJLJingsong Li
- 25 May 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 25 (7) , 2363-2373
Abstract
COVID-19 pneumonia is a disease that causes an existential health crisis in many people by directly affecting and damaging lung cells. The segmentation of infected areas from computed tomography (CT) images can be used to assist and provide useful information for COVID-19 diagnosis. Although several deep learning-based segmentation methods have been proposed for COVID-19 segmentation and have achieved state-of-the-art results, the segmentation accuracy is still not high enough (approximately 85%) due to the variations of COVID-19 infected areas (such as shape and size variations) and the similarities between COVID-19 and non-COVID-infected areas. To improve the segmentation accuracy of COVID-19 infected areas, we propose an interactive attention refinement network (Attention RefNet). The interactive attention refinement network can be connected with any segmentation network and trained with the segmentation network in an end-to-end fashion. We propose a skip connection attention module to improve the important features in both segmentation and refinement networks and a seed point module to enhance the important seeds (positions) for interactive refinement. The effectiveness of the proposed method was demonstrated on public datasets (COVID-19CTSeg and MICCAI) and our private multicenter dataset. The segmentation accuracy was improved to more than 90%. We also confirmed the generalizability of the proposed network on our multicenter dataset. The proposed method can still achieve high segmentation accuracy.Keywords
Funding Information
- China Postdoctoral Science Foundation (2020M671826)
- Zhejiang Lab Program (2020ND8AD01, 2020ND0AA01, 2018DG0ZX01)
- Zhejiang University special scientific research fund for COVID-19 prevention (2020XGZX051)
This publication has 42 references indexed in Scilit:
- Automatic segmentation and automatic seed point selection of nasopharyngeal carcinoma from microscopy images using region growing based approachJournal of Computational Science, 2017
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- Deep Residual Learning for Image Recognition2016
- Active contour model based on local and global intensity information for medical image segmentationNeurocomputing, 2016
- Segmentation of liver and spleen based on computational anatomy modelsComputers in Biology and Medicine, 2015
- Fully convolutional networks for semantic segmentation2015
- Automated Segmentation of the Liver from 3D CT Images Using Probabilistic Atlas and Multilevel Statistical Shape ModelAcademic Radiology, 2008
- Graph Cuts and Efficient N-D Image SegmentationInternational Journal of Computer Vision, 2006
- Random Walks for Interactive Organ Segmentation in Two and Three Dimensions: Implementation and Validation2005
- Seeded region growingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994