ABSTRACT
For diagnosis of COVID-19, a SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction (RT-PCR) test is routinely used. However, this test can take up to two days to complete, serial testing may be required to rule out the possibility of false negative results, and there is currently a shortage of RT-PCR test kits, underscoring the urgent need for alternative methods for rapid and accurate diagnosis of COVID-19 patients. Chest computed tomography (CT) is a valuable component in the evaluation of patients with suspected SARS-CoV-2 infection. Nevertheless, CT alone may have limited negative predictive value for ruling out SARS-CoV-2 infection, as some patients may have normal radiologic findings at early stages of the disease. In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symptoms, exposure history, and laboratory testing to rapidly diagnose COVID-19 positive patients. Among a total of 905 patients tested by real-time RT-PCR assay and next-generation sequencing RT-PCR, 419 (46.3%) tested positive for SARSCoV-2. In a test set of 279 patients, the AI system achieved an AUC of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of RT-PCR positive COVID-19 patients who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.
ABSTRACT
Objective To investigate the CT features of clear cell renal carcinoma (ccRCC)and angiomyolipoma with minimal fat (AMLmf)and to improve the CT diagnostic accuracy of these two diseases.Methods The CT features of 55 patients with pathologically-confirmed ccRCC and 1 2 patients with pathologically-confirmed AMLmf were analyzed retrospectively,including the CT value in both plain and tri-phase enhanced CT scan,tumor enhancement rate(△R1,△R2,△R3),maximum diameter,enhanced homogeneity,location of the main tumor,cortex raising signs,etc.The statistical analysis was carried on.Results The maximum diameter,the CT value in parenchymal phase,enhancement rate (△R1,△R2,△R3)of tumors in ccRCC group were significantly higher than those of tumors in AMLmf group,and the CT value in plain CT scan in ccRCC group was significantly lower than that in AMLmf group (all P<0.05).No statistically significant difference was found in the CT value of the tumor in corticomedullary phase and in excretion phase (both P>0.05).The rate of extrarenally-located main tumors of AMLmf group was significantly higher than that of ccRCC group (P=0.020),the location of main tumors and cortex raising signs showed no statistically significant difference with the maximum tumor diameter(both P>0.05).The enhanced homogeneity of the tumor in corticomedullary phase,parenchymal phase and excretion phase in ccRCC group was lower than that in AMLmf group (all P<0.05).Conclusion The CT value in plain CT scan in ccRCC group is lower than that in AMLmf group;the enhancement rate of the ccRCC group is higher than that of the AMLmf group;the enhanced homogeneity of the ccRCC group is worse than that of the AMLmf group.The extrarenally-located main tumors are more commonly seen in AMLmf than in ccRCC,and the cortex raising signs and the location of main tumors are unrelated to the size of the tumor.
