Tags

Type your tag names separated by a space and hit enter

COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation.
J Med Internet Res. 2020 06 29; 22(6):e19569.JM

Abstract

BACKGROUND

Coronavirus disease (COVID-19) has spread explosively worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) is a relevant screening tool due to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely occupied fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians.

OBJECTIVE

We aimed to rapidly develop an AI technique to diagnose COVID-19 pneumonia in CT images and differentiate it from non-COVID-19 pneumonia and nonpneumonia diseases.

METHODS

A simple 2D deep learning framework, named the fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning using one of four state-of-the-art pretrained deep learning models (VGG16, ResNet-50, Inception-v3, or Xception) as a backbone. For training and testing of FCONet, we collected 3993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and nonpneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training set and a testing set at a ratio of 8:2. For the testing data set, the diagnostic performance of the four pretrained FCONet models to diagnose COVID-19 pneumonia was compared. In addition, we tested the FCONet models on an external testing data set extracted from embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers.

RESULTS

Among the four pretrained models of FCONet, ResNet-50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100.00%, and accuracy 99.87%) and outperformed the other three pretrained models in the testing data set. In the additional external testing data set using low-quality CT images, the detection accuracy of the ResNet-50 model was the highest (96.97%), followed by Xception, Inception-v3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively).

CONCLUSIONS

FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing data set, the FCONet model based on ResNet-50 appears to be the best model, as it outperformed other FCONet models based on VGG16, Xception, and Inception-v3.

Authors+Show Affiliations

Department of Biomedical Engineering, Wonkwang University College of Medicine, Iksan-si, Republic of Korea.Department of Biomedical Engineering, Wonkwang University College of Medicine, Iksan-si, Republic of Korea.Department of Trauma Surgery, Wonkwang University Hospital, Iksan-si, Republic of Korea.Department of Radiology and Research Institute of Radiology, Asan Image Metrics, Clinical Trial Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.Department of Radiology and Research Institute of Radiology, Asan Image Metrics, Clinical Trial Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.Department of Internal Medicine, Chonnam National University Medical School, Gwangju-si, Republic of Korea.Department of Internal Medicine, Wonkwang University Hospital, Iksan-si, Republic of Korea.Department of Internal Medicine, Wonkwang University Hospital, Iksan-si, Republic of Korea.Department of Trauma Surgery, Wonkwang University Hospital, Iksan-si, Republic of Korea.Department of Radiology, Wonkwang University Hospital, Iksan-si, Republic of Korea.Department of Biomedical Engineering, Wonkwang University College of Medicine, Iksan-si, Republic of Korea.

Pub Type(s)

Journal Article
Validation Study

Language

eng

PubMed ID

32568730

Citation

Ko, Hoon, et al. "COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation." Journal of Medical Internet Research, vol. 22, no. 6, 2020, pp. e19569.
Ko H, Chung H, Kang WS, et al. COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation. J Med Internet Res. 2020;22(6):e19569.
Ko, H., Chung, H., Kang, W. S., Kim, K. W., Shin, Y., Kang, S. J., Lee, J. H., Kim, Y. J., Kim, N. Y., Jung, H., & Lee, J. (2020). COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation. Journal of Medical Internet Research, 22(6), e19569. https://doi.org/10.2196/19569
Ko H, et al. COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation. J Med Internet Res. 2020 06 29;22(6):e19569. PubMed PMID: 32568730.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation. AU - Ko,Hoon, AU - Chung,Heewon, AU - Kang,Wu Seong, AU - Kim,Kyung Won, AU - Shin,Youngbin, AU - Kang,Seung Ji, AU - Lee,Jae Hoon, AU - Kim,Young Jun, AU - Kim,Nan Yeol, AU - Jung,Hyunseok, AU - Lee,Jinseok, Y1 - 2020/06/29/ PY - 2020/04/23/received PY - 2020/06/21/accepted PY - 2020/05/31/revised PY - 2020/6/23/pubmed PY - 2020/7/8/medline PY - 2020/6/23/entrez KW - COVID-19 KW - CT KW - artificial intelligence KW - chest CT KW - convolutional neural networks, transfer learning KW - deep learning KW - diagnosis KW - neural network KW - pneumonia KW - scan SP - e19569 EP - e19569 JF - Journal of medical Internet research JO - J Med Internet Res VL - 22 IS - 6 N2 - BACKGROUND: Coronavirus disease (COVID-19) has spread explosively worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) is a relevant screening tool due to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely occupied fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE: We aimed to rapidly develop an AI technique to diagnose COVID-19 pneumonia in CT images and differentiate it from non-COVID-19 pneumonia and nonpneumonia diseases. METHODS: A simple 2D deep learning framework, named the fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning using one of four state-of-the-art pretrained deep learning models (VGG16, ResNet-50, Inception-v3, or Xception) as a backbone. For training and testing of FCONet, we collected 3993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and nonpneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training set and a testing set at a ratio of 8:2. For the testing data set, the diagnostic performance of the four pretrained FCONet models to diagnose COVID-19 pneumonia was compared. In addition, we tested the FCONet models on an external testing data set extracted from embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS: Among the four pretrained models of FCONet, ResNet-50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100.00%, and accuracy 99.87%) and outperformed the other three pretrained models in the testing data set. In the additional external testing data set using low-quality CT images, the detection accuracy of the ResNet-50 model was the highest (96.97%), followed by Xception, Inception-v3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS: FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing data set, the FCONet model based on ResNet-50 appears to be the best model, as it outperformed other FCONet models based on VGG16, Xception, and Inception-v3. SN - 1438-8871 UR - https://www.unboundmedicine.com/medline/citation/32568730/COVID_19_Pneumonia_Diagnosis_Using_a_Simple_2D_Deep_Learning_Framework_With_a_Single_Chest_CT_Image:_Model_Development_and_Validation_ L2 - https://www.jmir.org/2020/6/e19569/ DB - PRIME DP - Unbound Medicine ER -