Human identification plays a significant role in the investigations of disasters and criminal cases. Human identification could be achieved quickly and efficiently via 3D sphenoid sinus models by customized convolutional neural networks. In this retrospective study, a deep learning neural network was proposed to achieve human identification of 1475 noncontrast thin-slice CT scans. A total of 732 patients were retrieved and studied (82% for model training and 18% for testing). By establishing an individual recognition framework, the anonymous sphenoid sinus model was matched and cross-tested, and the performance of the framework also was evaluated on the test set using the recognition rate, ROC curve and identification speed. Finally, manual matching was performed based on the framework results in the test set. Out of a total of 732 subjects (mean age 46.45 years ± 14.92 (SD); 349 women), 600 subjects were trained, and 132 subjects were tested. The present automatic human identification has achieved Rank 1 and Rank 5 accuracy values of 93.94% and 99.24%, respectively, in the test set. In addition, all the identifications were completed within 55 s, which manifested the inference speed of the test set. We used the comparison results of the MVSS-Net to exclude sphenoid sinus models with low similarity and carried out traditional visual comparisons of the CT anatomical aspects of the sphenoid sinus of 132 individuals with an accuracy of 100%. The customized deep learning framework achieves reliable and fast human identification based on a 3D sphenoid sinus and can assist forensic radiologists in human identification accuracy.
BackgroundPneumonia caused by the 2019 novel Coronavirus (COVID‐2019) shares overlapping signs and symptoms, laboratory findings, imaging features with influenza A pneumonia. We aimed to identify their clinical characteristics to help early diagnosis.MethodsWe retrospectively retrieved data for laboratory‐confirmed patients admitted with COVID‐19–induced or influenza A–induced pneumonia from electronic medical records in Ningbo First Hospital, China. We recorded patients'' epidemiological and clinical features, as well as radiologic and laboratory findings.ResultsThe median age of influenza A cohort was higher and it exhibited higher temperature and higher proportion of pleural effusion. COVID‐19 cohort exhibited higher proportions of fatigue, diarrhea and ground‐glass opacity and higher levels of lymphocyte percentage, absolute lymphocyte count, red‐cell count, hemoglobin and albumin and presented lower levels of monocytes, c‐reactive protein, aspartate aminotransferase, alkaline phosphatase, serum creatinine. Multivariate logistic regression analyses showed that fatigue, ground‐glass opacity, and higher level of albumin were independent risk factors for COVID‐19 pneumonia, while older age, higher temperature, and higher level of monocyte count were independent risk factors for influenza A pneumonia.ConclusionsIn terms of COVID‐19 pneumonia and influenza A pneumonia, fatigue, ground‐glass opacity, and higher level of albumin tend to be helpful for diagnosis of COVID‐19 pneumonia, while older age, higher temperature, and higher level of monocyte count tend to be helpful for the diagnosis of influenza A pneumonia. 相似文献