Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography

Abstract

Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. We aimed to construct a system based on deep learning for detecting COVID-19 pneumonia on high resolution CT. For model development and validation, 46,096 anonymous images from 106 admitted patients, including 51 patients of laboratory confirmed COVID-19 pneumonia and 55 control patients of other diseases in Renmin Hospital of Wuhan University were retrospectively collected. Twenty-seven prospective consecutive patients in Renmin Hospital of Wuhan University were collected to evaluate the efficiency of radiologists against 2019-CoV pneumonia with that of the model. An external test was conducted in Qianjiang Central Hospital to estimate the system's robustness. The model achieved a per-patient accuracy of 95.24% and a per-image accuracy of 98.85% in internal retrospective dataset. For 27 internal prospective patients, the system achieved a comparable performance to that of expert radiologist. In external dataset, it achieved an accuracy of 96%. With the assistance of the model, the reading time of radiologists was greatly decreased by 65%. The deep learning model showed a comparable performance with expert radiologist, and greatly improved the efficiency of radiologists in clinical practice.

Figure 1

Workflow diagram for the development and evaluation of the model for detecting COVID19 pneumonia.

Figure 2

Representative images of COVID19 pneumonia. More than six common Computed tomography (CT) features of COVID19 pneumonia were covered in selected images. 1(a–d), the lesions were mainly ground-glass-like, with thickened blood vessels walking and including gas-bronchial signs in 1(c); 2(a–d), the lesions were mainly ground glass changes, and paving stone-like changes were observed on 2(d); 3(a–c), the lesions become solid with a large range, and air-bronchial signs are seen inside; 4, the lesion is located in the lower lobe of both lungs, and is mainly grid-like change with ground glass lesion; 5(a,b), the lesions are mainly consolidation; 6(a,b), the lesions are mainly large ground glass shadows, showing white lung-like changes, with air-bronchial signs.

Figure 3

The network architecture of UNet++. UNet++ consists of encoder and decoder connecting through a series of nested dense convolutional blocks. The semantic gap between the feature maps of the encoder and decoder is bridged prior to fusion. The encoder extract features by down-sampling; the decoder map features to the original image by up-sampling, make classification by pixels, and thus achieve the purpose of segmentation. Resnet-50 was used as backbone of UNet++, and all the pre-training parameters of ResNet-50 are loaded to UNet++.

Figure 4

Processing and prediction schematic of the model. Raw images were firstly input into the model, and after processing of the model, prediction boxes framing suspicious lesions were output. Valid areas were further extracted and unnecessary fields were filter out to avoid possible false positives. To predict by case, a logic linking the prediction results of consecutive images was added. Computed tomography (CT) images with the above prediction results were divided into four quadrants, and results would be output only when three consecutive images were predicted to have lesions in the same quadrant.

Figure 5

Representative images of the model’s predictions. (A) Computed tomography (CT) images of COVID19 pneumonia. The predictions between the artificial intelligence model and radiologists were consistent. Green boxes, labels from radiologists; red boxes, labels from the model. (B) CT images of the control. The first image is an ordinary bacterial pneumonia, showing a consolidation of the right lower lobe. The second image has a tumorous lesion in the lung, showing a mass in the left upper lobe, with spiculation sign seen at the edges, and showing leaf-like growth with vacuoles inside. The third image is a secondary pulmonary tuberculosis, showing a left apical fibrous cord. The fourth image is a bronchiectasis complicated with infection, showing bronchodilation and expansion, cystic changes, and surrounding patches of infection. The fifth image shows normal lungs.

Figure 6

Main interface of the open-access artificial intelligence platform which provides fast and sensitive assistance for detecting COVID19 pneumonia.

Figure 7

Abstract diagram. Computed tomography (CT) is the most efficient modality for screening and clinically diagnosing COVID-19 pneumonia. However, compared to the needs of the patients, the number of radiologists is quite small. After enrolling artificial intelligence in identifying COVID-19 pneumonia in CT images, the efficiency of diagnosis is greatly improved. The artificial intelligence holds great potential to relieve the pressure of frontline radiologists, accelerates the diagnosis, isolation and treatment of COVID19 patients, and therefore contribute to the control of the epidemic.