GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
Authors:
- Zhanwei XuZXZhanwei Xu
- Yukun CaoYCYukun Cao
- Cheng JinCJCheng Jin
- Guozhu ShaoGSGuozhu Shao
- Xiaoqing LiuXLXiaoqing Liu
- Jie ZhouJZJie Zhou
- Heshui ShiHSHeshui Shi
- Jianjiang FengJFJianjiang Feng
Preprint
Abstract
Segmentation of infected areas in chest CT volumes is of great significance for further diagnosis and treatment of COVID-19 patients. Due to the complex shapes and varied appearances of lesions, a large number of voxel-level labeled samples are generally required to train a lesion segmentation network, which is a main bottleneck for developing deep learning based medical image segmentation algorithms. In this paper, we propose a weakly-supervised lesion segmentation framework by embedding the Generative Adversarial training process into the Segmentation Network, which is called GASNet. GASNet is optimized to segment the lesion areas of a COVID-19 CT by the segmenter, and to replace the abnormal appearance with a generated normal appearance by the generator, so that the restored CT volumes are indistinguishable from healthy CT volumes by the discriminator. GASNet is supervised by chest CT volumes of many healthy and COVID-19 subjects without voxel-level annotations. Experiments on three public databases show that when using as few as one voxel-level labeled sample, the performance of GASNet is comparable to fully-supervised segmentation algorithms trained on dozens of voxel-level labeled samples.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Label-Free Segmentation of COVID-19 Lesions in Lung CTIEEE Transactions on Medical Imaging, 2021
- JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and SegmentationIEEE Transactions on Image Processing, 2021
- Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology ImagesIEEE Transactions on Medical Imaging, 2020
- Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed TomographyCell, 2020
- ADCM: attention dropout convolutional moduleNeurocomputing, 2020
- Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT ImagesIEEE Transactions on Medical Imaging, 2020
- Radiological findings from 81 patients with COVID-19 pneumonia in Wuhan, China: a descriptive studyThe Lancet Infectious Diseases, 2020
- Adversarial Confidence Learning for Medical Image Segmentation and SynthesisInternational Journal of Computer Vision, 2020
- Abstract: nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation2019
- DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural NetworksIEEE Transactions on Medical Imaging, 2016