Next Article in Journal
Can Magnetic Resonance Radiomics Analysis Discriminate Parotid Gland Tumors? A Pilot Study
Next Article in Special Issue
A Performance Comparison between Automated Deep Learning and Dental Professionals in Classification of Dental Implant Systems from Dental Imaging: A Multi-Center Study
Previous Article in Journal
Chest CT Findings after 4 Months from the Onset of COVID-19 Pneumonia: A Case Series
Previous Article in Special Issue
Automated Segmentation and Severity Analysis of Subdural Hematoma for Patients with Traumatic Brain Injuries
Open AccessArticle

CoSinGAN: Learning COVID-19 Infection Segmentation from a Single Radiological Image

1
School of Life Science, Beijing Institute of Technology, Haidian District, Beijing 100081, China
2
Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Haidian District, Beijing 100081, China
*
Author to whom correspondence should be addressed.
Diagnostics 2020, 10(11), 901; https://doi.org/10.3390/diagnostics10110901
Received: 13 October 2020 / Revised: 29 October 2020 / Accepted: 30 October 2020 / Published: 3 November 2020
(This article belongs to the Special Issue Deep Learning for Computer-Aided Diagnosis in Biomedical Imaging)
Computed tomography (CT) images are currently being adopted as the visual evidence for COVID-19 diagnosis in clinical practice. Automated detection of COVID-19 infection from CT images based on deep models is important for faster examination. Unfortunately, collecting large-scale training data systematically in the early stage is difficult. To address this problem, we explore the feasibility of learning deep models for lung and COVID-19 infection segmentation from a single radiological image by resorting to synthesizing diverse radiological images. Specifically, we propose a novel conditional generative model, called CoSinGAN, which can be learned from a single radiological image with a given condition, i.e., the annotation mask of the lungs and infected regions. Our CoSinGAN is able to capture the conditional distribution of the single radiological image, and further synthesize high-resolution (512 × 512) and diverse radiological images that match the input conditions precisely. We evaluate the efficacy of CoSinGAN in learning lung and infection segmentation from very few radiological images by performing 5-fold cross validation on COVID-19-CT-Seg dataset (20 CT cases) and an independent testing on the MosMed dataset (50 CT cases). Both 2D U-Net and 3D U-Net, learned from four CT slices by using our CoSinGAN, have achieved notable infection segmentation performance, surpassing the COVID-19-CT-Seg-Benchmark, i.e., the counterparts trained on an average of 704 CT slices, by a large margin. Such results strongly confirm that our method has the potential to learn COVID-19 infection segmentation from few radiological images in the early stage of COVID-19 pandemic. View Full-Text
Keywords: covid19 infection segmentation; generative model; single radiological image; conditional distribution covid19 infection segmentation; generative model; single radiological image; conditional distribution
Show Figures

Figure 1

MDPI and ACS Style

Zhang, P.; Zhong, Y.; Deng, Y.; Tang, X.; Li, X. CoSinGAN: Learning COVID-19 Infection Segmentation from a Single Radiological Image. Diagnostics 2020, 10, 901. https://doi.org/10.3390/diagnostics10110901

AMA Style

Zhang P, Zhong Y, Deng Y, Tang X, Li X. CoSinGAN: Learning COVID-19 Infection Segmentation from a Single Radiological Image. Diagnostics. 2020; 10(11):901. https://doi.org/10.3390/diagnostics10110901

Chicago/Turabian Style

Zhang, Pengyi; Zhong, Yunxin; Deng, Yulin; Tang, Xiaoying; Li, Xiaoqiong. 2020. "CoSinGAN: Learning COVID-19 Infection Segmentation from a Single Radiological Image" Diagnostics 10, no. 11: 901. https://doi.org/10.3390/diagnostics10110901

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop