Objective:To explore the application value of artificial intelligence (AI)in quantita-tive evaluation of CT images of different clinical types of COVID-19.Methods:A total of 169 pa-tients with COVID-19 who underwent chest CT examination between October 2021 and June 2022 were included in the study,and were divided into a severe group of 14 cases and a non-severe group of 155 cases.The general data and imaging information of the COVID-19 patients were collected and analyzed retrospectively.The lesion volume fraction,GGO volume fraction,consolidation volume frac-tion,GGO +consolidation volume fraction and crazy-paving pattern volume fraction were measured and calculated with the assistance of the"AI qualitative auxiliary diagnosis system for CT images of COVID-19"provided by BIOMIND.Mann-whitney U test was used to compare the data of the two groups.The receiver operating characteristic curve (ROC)was used to evaluate the diagnostic efficacy of the above indexes in severe patients.Results:There were significant differences in lesion volume fraction and GGO volume fraction between the two groups (P＜0.05).However,there was no signifi-cant difference in the volume fraction of consolidation,GGO +consolidation and crazy-paving pat-tern (P＞0.05).The sensitivity of lesion volume fraction and GGO volume fraction for clinical classi-fication of COVID-19 was 1 and 0.6,and the specificity was 0.822 and 0.923,respectively.Con-clusion:The lesion volume fraction and GGO volume fraction calculated with the assistance of AI are sensitive indicators for clinical classification of COVID-19.
维普
万方数据