Assisting Scalable Diagnosis Automatically via CT Images in the Combat against COVID-19

Bohan Liu, Pan Liu, Lutao Dai, Yan-Lin Yang, Peng Xie, Yiqing Tan, Jicheng Du, Wei Shan, Chenghui Zhao, Qin Zhong, Xixiang Lin, Xizhou Guan, Ning Xing, Yuhui Sun, Wenjun Wang, Zhibing Zhang, Xia Fu, Yanqing Fan, Meifang Li, Na Zhang, Lin Li, Yaou Liu, Lin Xu, Jingbo Du, Zhenhua Zhao, Xuelong Hu, Weipeng Fan, Rongpin Wang, Chongchong Wu, Yongkang Nie, Liuquan Cheng, Lin Ma, Zongren Li, Jia Qian, Minchao Liu, Huayuan Guo, Gao Huang, Haipeng Shen, Weimin An, Hao Li, Jianxin Zhou, Kunlun HemedRxiv 2020 · DOI

Introduction

The global pandemic of Coronavirus Disease 2019 (COVID-19) has caused unprecedented loss of life and strain on healthcare systems worldwide. Rapid and accurate case identification is the cornerstone of effective pandemic management. While real-time reverse transcription PCR (rRT-PCR) assays remain the reference method for diagnosis, they are often limited by long turnaround times, supply chain shortages, and a notable rate of false negatives.

Chest computed tomography (CT) scans have emerged as a highly sensitive alternative, frequently revealing pulmonary abnormalities such as Ground Glass Opacities (GGO) even before the onset of clinical symptoms. However, the manual review of hundreds of CT slices per patient is labor-intensive and subject to human error, especially under the high-pressure conditions of a pandemic. To address this, we developed COVIDNet, a deep learning (DL) model designed to automatically differentiate COVID-19 from other types of pneumonia using 3D CT images.

Methodology

Architecture: COVIDNet

Unlike many traditional computer vision models that process 2D slices independently, COVIDNet utilizes a modified DenseNet-264 architecture optimized for 3D volume analysis. This approach allows the model to extract spatial features directly from the entire CT volume, capturing the complex three-dimensional nature of viral pneumonia manifestations.

Preprocessing and Training

To ensure consistency across varying scan protocols, the researchers normalized voxel intensities and resized 3D volumes into a standardized stack of 64 axial images with a resolution of 384x384. The model employs four dense blocks with instance normalization and ReLU activation. Training was conducted using the Adam optimizer to minimize binary cross-entropy loss. To improve interpretability, the team utilized t-SNE (t-Distributed Stochastic Neighbor Embedding) to visualize feature clustering, confirming that the model was identifying distinct patterns unique to COVID-19.

Datasets and Validation

The study leveraged a large-scale dataset involving 2,800 patients:

  • Development Set: 920 COVID-19 patients (sourced from 10 hospitals) and 1,073 non-COVID-19 pneumonia patients (historical data from 2010–2020).
  • External Validation Set: An independent cohort of 233 COVID-19 and 289 non-COVID-19 patients to test the model's generalizability.

The data included a diverse range of CT scanners and settings to ensure the model remained robust across different clinical environments.

Key Results

Diagnostic Accuracy

COVIDNet demonstrated exceptional performance, achieving an accuracy of 96.0% on internal testing and 94.3% on external validation. The model’s Area Under the Curve (AUC) reached 0.98, indicating a very high discriminative power between COVID-19 and other pneumonias. In the external cohort, the system maintained a sensitivity of 93.1% and a specificity of 95.1%.

Human vs. Machine Performance

In a comparative study, COVIDNet outperformed eight expert radiologists with experience ranging from 6 to 23 years. Beyond accuracy, the model offered a significant advantage in efficiency: while a radiologist typically requires 3 to 5 minutes to review a scan, COVIDNet processes a patient volume in just 3 seconds (0.05 minutes).

Real-World Deployment

The system was not merely a theoretical exercise; by late March 2020, it had been deployed in 104 hospitals across China. During this period, it processed over 23,000 scans and successfully identified nearly 6,000 COVID-19 cases, demonstrating its scalability as a triage tool during infection surges.

Discussion and Limitations

While COVIDNet shows great promise for long-term surveillance and case detection, several challenges remain for clinical integration:

  • Disease Progression: CT manifestations change significantly over the course of the infection. Patterns in very early or late stages may not align with the "typical" features learned by the AI.
  • Clinical Context: The authors emphasize that AI-generated scores should not be used in isolation. Diagnosis must be integrated with epidemiological history and other clinical markers.
  • The "Black Box" Problem: Although t-SNE provides some insight into feature separation, the specific logic used for individual classifications remains difficult to interpret fully, which is a common hurdle for DL models in medicine.

Conclusion

COVIDNet represents a significant step forward in the application of deep learning to medical imaging. By providing a rapid, accurate, and scalable method for identifying COVID-19 from 3D CT scans, this technology can bridge the expertise gap between specialized and general medical centers, ultimately improving the efficiency of pandemic response and patient care.

Summary updated

Abstract

Introductory paragraph The pandemic of coronavirus Disease 2019 (COVID-19) caused enormous loss of life globally. 1-3 Case identification is critical. The reference method is using real-time reverse transcription PCR (rRT-PCR) assays, with limitations that may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that application of deep learning (DL) to the 3D CT images could help identify COVID-19 infections. Using the data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 patients. COVIDNet achieved an accuracy rate of 94.3% and an area under the curve (AUC) of 0.98. Application of DL to CT images may improve both the efficiency and capacity of case detection and long-term surveillance.
BibTeX
@misc{liu2020assisting,
  author = {Bohan Liu and Pan Liu and Lutao Dai and Yan-Lin Yang and Peng Xie and Yiqing Tan and Jicheng Du and Wei Shan and Chenghui Zhao and Qin Zhong and Xixiang Lin and Xizhou Guan and Ning Xing and Yuhui Sun and Wenjun Wang and Zhibing Zhang and Xia Fu and Yanqing Fan and Meifang Li and Na Zhang and Lin Li and Yaou Liu and Lin Xu and Jingbo Du and Zhenhua Zhao and Xuelong Hu and Weipeng Fan and Rongpin Wang and Chongchong Wu and Yongkang Nie and Liuquan Cheng and Lin Ma and Zongren Li and Jia Qian and Minchao Liu and Huayuan Guo and Gao Huang and Haipeng Shen and Weimin An and Hao Li and Jianxin Zhou and Kunlun He},
  title = {{Assisting Scalable Diagnosis Automatically via CT Images in the Combat against COVID-19}},
  year = {2020},
  doi = {10.1101/2020.05.11.20093732},
  howpublished = {medRxiv},
}
Figure