Novel Deep Learning Technique Used in Management and Discharge of Hospitalized Patients with COVID-19 in China

Figures & data

Figure 1 Unet architecture, the boxes represent feature map consist of multi-channels, the number of channels in each layer is on the top of each box. The arrows colored by five colors corresponds to five kinds of convolutional operation which can be found on the right bottom of the figure.

Table 1 Initial CT Findings of 270 Patients with Coronavirus Disease 2019 (COVID-19)

CT Findings	No (%) of Patients
Normal	57(21.1)
Pneumonia	213(78.9)
Interstitial fibrosis
Mild	100(46.9)
Moderate	15(7.0)
Lesion range
One lobe	16(7.5)
Two lobe	31(14.6)
Multiple lobe	166(77.9)
Lesion distribution
Peripheral zone	136(63.8)
Central zone	2(0.9)
Diffusion distribution	75(35.2)
Vascular enlargement	21(9.9)
Thicken pleura	33(15.5)
Nodule	4(1.9)
Mediastinal lymphadenopathy	4(1.9)

Abbreviations: COVID-19, coronavirus disease 2019; CT, computed tomography.

Figure 2 IOU distribution for all lesions. As shown in this figure, there are two peaks in the distribution, which means most predictions may have high IOU value or very low IOU value, and the average IOU is 0.7894.

Abbreviations: IOU, intersection over union, GGO, ground glass opacity.

Figure 3 Predict results of the AI system. (A, C): predicted by AI system, (B, D): labeled by radiologist.

Figure 4 Volume distribution for all lesions.

Figure 5 The working model of DL on chest CT for a forty-nine years old woman. The upper right panel shows the ratio of the total volume of lesions to lung volume, which was more than 95%. The three-dimensional display and the density of lesions were shown in the middle and the inferior of right panel. This COVID-19 patient was hospitalized again and presented with a positive nucleic acid test again.

Abbreviation: DL, deep learning.