Analysis of clinical features and imaging signs of COVID-19 with the assistance of artificial intelligence.

OBJECTIVE: To explore the CT imaging features/signs of patients with different clinical types of Coronavirus Disease 2019 (COVID-19) via the application of artificial intelligence (AI), thus improving the understanding of COVID-19. PANTIENTS AND METHODS: Clinical data and chest CT imaging features of 58 patients confirmed with COVID-19 in the Fifth Medical Center of PLA General Hospital were retrospectively analyzed. According to the Guidelines on Novel Coronavirus-Infected Pneumonia Diagnosis and Treatment (Provisional 6th Edition), COVID-19 patients were divided into mild type (7), common type (34), severe type (7) and critical type (10 patients). The CT imaging features of the patients with different clinical types of COVID-19 types were analyzed, and the volume percentage of pneumonia lesions with respect to the lung lobes (where the lesion was located) and to the whole lung was calculated with the use of AI software. SPSS 21.0 software was used for statistical analysis. RESULTS: Common clinical manifestations of COVID-19 patients: fever was found in 47 patients (81.0%), cough in 31 (53.4%) and weakness in 10 (17.2%). Laboratory examinations: normal or decreased white blood cell (WBC) counts were observed in 52 patients (89.7%), decreased lymphocyte counts (LCs) in 14 (24.1%) and increased C-reactive protein (CRP) levels in 18 (31.0%). CT imaging features: there were 48 patients (94.1%) with lesions distributed in both lungs and 46 patients (90.2%) had lesions most visible in the lower lungs; the primary manifestations in patients with common type COVID-19 were ground-glass opacities (GGOs) (23/34, 67.6%) or mixed type (17/34, 50.0%), with lesions mainly distributed in the periphery of the lungs (28/34, 82.4%); the primary manifestations of patients with severe/critical type COVID-19 were consolidations (13/17, 76.5%) or mixed type (14/17, 82.4%), with lesions distributed in both the peripheral and central areas of lungs (14/17,82.4%); other common signs, including pleural parallel signs, halo signs, vascular thickening signs, crazy-paving signs and air bronchogram signs, were visible in patients with different clinical types, and pleural effusion was found in 5 patients with severe/critical COVID-19. AI software was used to calculate the volume percentages of pneumonia lesions with respect to the lung lobes (where the lesion was located) and to the whole lung. There were significant differences in the volume percentages of pneumonia lesions for the superior lobe of the left lung, the inferior lobe of the left lung, the superior lobe of the right lung, the inferior lobe of the right lung and the whole lung among patients with different clinical types (p<0.05). The area under the ROC curve (AUC) of the volume percentage of pneumonia lesions for the whole lung for the diagnosis of severe/critical type COVID-19 was 0.740, with sensitivity and specificity of 91.2% and 58.8%, respectively. CONCLUSIONS: The clinical and CT imaging features of COVID-19 patients were characteristic to a certain degree; thus, the clinical course and severity of COVID-19 could be evaluated with a combination of an analysis of clinical features and CT imaging features and assistant diagnosis by AI software.

[Quantitative comparison of diffusion weighted image in liver at two field strengths for chronic hepatitis B].

Objective: To evaluate whether there were differences between apparent diffusion coefficient (ADC) values derived from 3.0 T and 1.5 T MR diffusion-weighted imaging (DWI) in liver of patients with chronic hepatitis B. Methods: From January 2016 to November 2016, a total of 40 chronic hepatitis B prospectively underwent both 1.5 T and 3.0 T DWI before liver biopsy, the interval between two scans was within 15 minutes, the protocol was respiratory-triggered DWI(RT-DWI). The ADC values were measured at both field strengths using ROI method. Bland-Altman tests and paired t-tests were used to compare ADC values obtained at 1.5 T and 3.0 T. Results: The ADC values of different b values for patients with mild inflammation at 1.5 T were(1.22-1.48(1.35±0.08)×10(-3) mm(2)/s), the ADC values of different b values for patients with mild inflammation at 3.0 T were(1.18-1.45(1.30±0.08)×10(-3) mm(2)/s); the ADC values of different b values for patients with moderate to severe inflammation at 1.5 T were(1.11-1.37(1.25±0.06)×10(-3) mm(2)/s), the ADC values of different b values for patients with moderate to severe inflammation at 3.0 T were(1.08-1.31(1.20±0.06)×10(-3) mm(2)/s). There were significantly differences between the ADC values of different b values for patients with chronic hepatitis B obtained at two field strengths (P<0.01). Conclusions: Different field strengths have influence on ADC values in liver, the ADC values derived from 3.0 T are lower than the ADC values derived from 1.5 T.

[Study of diffusion weighted imaging in combination with conventional MRI signs for inflammation activity of chronic hepatitis B].

Objective: To study the correlation between ADC values of diffusion weighted imaging (DWI) and the pathological grading in inflammation activity of chronic hepatitis B, and combined with conventional MRI features to predict the diagnosis effectiveness. Methods: A total of 142 cases of patients with chronic hepatitis B were selected as inflammatory group in 302 Hospital of PLA from January 2014 to December 2015, while 20 cases of healthy subjects without history of liver disease were chosen as control group.All patients underwent MR plain scan and dynamic contrast enhancement and DWI examinations (b=0, 800 s/mm(2)) for liver, and were performed liver biopsy within two days.According to the degree of inflammation activity (G), the inflammation group was divided into G1, G2 and G3-4 level.The apparent diffusion coefficient (ADC) value, and the MRI features of each group were analyzed. Results: The ADC values showed statistical difference (F=8.392, P<0.01) within inflammation group of chronic hepatitis B from different pathologic grading, and there was significant negative correlation between ADC values and liver inflammation activity grading (r=-0.613, P<0.01). The ADC value of inflammation group and control group was (1.31±0.16), (1.12±0.15)×10(-3) mm(2)/s, the difference was statistically significant (P<0.05). The ADC value of G1, G2 and G3-4 level was (1.22±0.12), (1.05±0.12), (0.98±0.10)×10(-3) mm(2)/s respectively, and there was statistical difference (P<0.05) between G1 and G2, G1 and G3-4. The receiver operating characteristic (ROC) curve in diagnosis of equal and above G2 level showed the area under the curve (AUC) was 0.880, the sensitivity and the specificity was 82.4% and 76.8% respectively, the diagnostic cut-off value was 1.09×10(-3) mm(2)/s.Besides, the detection rate of portal around its orbit and gallbladder wall edema in inflammation group had statistical difference (P<0.05), and there was no statistical difference in the detection rate of abnormal liver arterial enhancement, hilus lymph node increases and ascites in inflammation group(P>0.05). The ROC in diagnosis of equal and above G2 level by ADC values combined with the MRI characteristic signs showed AUC was 0.938, the sensitivity and the specificity was 88.4% and 88.9% respectively. Conclusions: ADC values can predict the inflammation activity of chronic hepatitis B with quantitatively and non-invasively.Combining with characteristic MRI signs, ADC values can improve the diagnosis efficiency.