RESUMO
The global spread of COVID-19 seriously endangers human health and even lives. By predicting patients individualized disease development and further performing intervention in time, we may rationalize scarce medical resources and reduce mortality. Based on 1337 multi-stage ([≥]3) high-resolution chest computed tomography (CT) images of 417 infected patients from three centers in the epidemic area, we proposed a random forest + cellular automata (RF+CA) model to forecast voxel-level lesion development of patients with COVID-19. The model showed a promising prediction performance (Dice similarity coefficient [DSC] = 71.1%, Kappa coefficient = 0.612, Figure of Merit [FoM] = 0.257, positional accuracy [PA] = 3.63) on the multicenter dataset. Using this model, multiple driving factors for the development of lesions were determined, such as distance to various interstitials in the lung, distance to the pleura, etc. The driving processes of these driving factors were further dissected and explained in depth from the perspective of pathophysiology, to explore the mechanism of individualized development of COVID-19 disease. The complete codes of the forecast system are available at https://github.com/keyunj/VVForecast_covid19.
RESUMO
Early detection of COVID-19 based on chest CT will enable timely treatment of patients and help control the spread of the disease. With rapid spreading of COVID-19 in many countries, however, CT volumes of suspicious patients are increasing at a speed much faster than the availability of human experts. We proposed an artificial intelligence (AI) system for fast COVID-19 detection and performed extensive statistical analysis of CTs of COVID-19 based on the AI system. We developed and evaluated our system on a large dataset with more than 10 thousand CT volumes from COVID-19, influenza-A/B, non-viral community acquired pneumonia (CAP) and non-pneumonia subjects. In such a difficult multi-class diagnosis task, our deep convolutional neural network-based system is able to achieve an area under the receiver operating characteristic curve (AUC) of 97.17%, a sensitivity of 90.19%, and a specificity of 95.76% for COVID-19 on internal test cohort of 3,203 scans and AUC of 97.77% on the publicly available CC-CCII database with 1,943 test samples. In a reader study involving five radiologists, the AI system outperforms all of radiologists in more challenging tasks at a speed of two orders of magnitude above them. Diagnosis performance of chest x-ray (CXR) is compared. Detailed interpretation of deep network is also performed to relate AI results with CT findings. The code is available at https://github.com/ChenWWWeixiang/diagnosis_covid19.
RESUMO
Objective To analyze the image features and prognosis of primary central airway salivary gland-type tumor (SGT).Methods The clinical and imaging data of 25 cases with SGT confirmed by histopathology were retrospectively analyzed in our hospital from October 2009 to November 2017.Follow up of patients for survival was performed.Among 25 cases of SGT,there were 14 cases of adenoid cystic carcinoma (ACC),ten cases of mucoepidermoid carcinoma (MEC) and one case of mucoepidermoid carcinoma (EMC).All cases had non-enhanced CT scans (among which 20 cases underwent CT scan with contrast).Post-processing were performed to evaluate the location,range,density,degree of enhancement of the lesions and involvement of hilar or mediastinal lymph nodes.Eight cases underwent PET/CT imaging and one underwent MR imaging,respectively.Independent sample t test was used to compare difference in ages between ACC group and MEC group.Nonparametric test was performed to compare difference in tumor's diameter between ACC group and MEC group.Comparison of genders,history of smoking,tumor-node-metastasis (TNM) stage and CT features between ACC group and MEC group were tested using Fisher's exact tests.Survival was calculated using the Kaplan-Meier method,and the survival curves were compared by the log-rank test.Results Compared to MEC,patients with ACC were older.There were significant difference between the two groups (t=3.154,P＜0.05).ACC tended to involved trachea or main bronchi (13/14) while MEC were mostly located at lobar or segment bronchi (6/10).The shape of ACC tumors were mainly lobulated or presented as circumferential wall thickening (13/14),while MECs were smoothly oval (7/10).On contrast-enhanced CT scans,ACC mainly showed mild or moderate enhancement (9/10),While most of MEC had shown avid enhancement (8/10).CT findings suggestive of airway obstructive disease were seen more with MEC (9/10) than ACC (4/14).There were significant differences of the above CT features between ACC and MEC group (P＜0.05).A case of EMC in an 43 years old female presented rounded nodule in tracheal;The SUVmax in 6 of 8 cases of PET/CT exceeded 2.2;Overall survival (OS) was 87.5％ in all cases.No significant difference was found between ACC and MEC groups regarding OS (x2=0,P=1.000).Ages,surgical and nonsurgical patients and TNM stage were found to be related to OS (x2=13.799,13.799,13.171,respectively,P＜0.05).Conclusions Primary central airway salivary gland-type tumors are commonly occurred in patients at a low age,with weak invasive feature and good prognosis.The predominant site and CT characteristics between ACC and MEC were significantly different.
RESUMO
Aim To investigate the effect of U50488H(a selective κ-opioid receptor agonist)and isoproterenol(ISO,a β-adrenergic receptor agonist)on ventricular arrhythmias and Cx43 during myocardial ischemia and reperfusion in rats.Methods 60 rats were randomly divided into five groups,ie,normal control group,I/R group,ISO+I/R group,U50488H+ISO+I/R group,Nor-BNI+U50488H+ISO+I/R group.The incidence of ventricular arrhythmias and arrhythmia score were determined. The expression of Cx43mRNA was tested by RT-PCR.The expression of Cx43 protein in myocardial cell was tested by an immunohistochemical approach with a quantitative imaging system.Results ① Compared with the I/R group,arrhythmia score was increased with administration of ISO(P<0.05).U50488H intravenously injected before ISO significantly decreased the arrhythmia score(P<0.05).② Compared with the normal control group,the expression of Cx43 mRNA was decreased in the I/R group(P<0.05).With administration of ISO,the amount of Cx43 mRNA was not significantly increased.③ Compared with normal control group,total and phosphorylated Cx43 proteins were significantly decreased in the I/R group(P<0.05),and the phosphorylated Cx43 was also decreased with administration of ISO.Compared with ISO+I/R group,phosphorylated Cx43 was increased with administration of U50488H (P<0.05).Conclusion κ-opioid receptor agonist U50488 H antagonizes the arrhythmias through the regulation of Cx43 during myocardial ischemia and reperfusion via inhibiting β-adrenergic receptor pathway.
