Objective To develop and validate a deep learning model for automatic identification of liver CT contrast-enhanced phases.Methods A total of 766 patients with liver CT contrast-enhanced images were retrospectively collected.A three-phase classification model and an arterial phase(AP)classification model were developed,so as to automatically identify liver CT contrast-enhanced phases as early arterial phase(EAP)or late arterial phase(LAP),portal venous phase(PVP),and equilibrium phase(EP).In addition,221 patients with liver CT contrast-enhanced images in 5 different hospitals were used for external validation.The annotation results of radiologists were used as a reference standard to evaluate the model performances.Results In the external validation datasets,the accuracy in identifying each enhanced phase reached to 90.50%-99.70%.Conclusion The automatic identification model of liver CT contrast-enhanced phases based on residual network may provide an efficient,objective,and unified image quality control tool.

ObjectiveTo analyze the data of hospitalized accidental injuries with registered residence in Yangpu District， Shanghai， to describe their characteristics， and to provide an evidence for formulating accidental injuries prevention and control strategies. MethodsStatistic analysis was conducted on the data of accidental hospitalized injury cases in Yangpu District. The incidence rate （per 100 000 population） and the hospital stay were used to analyze the characteristics of hospitalized accidental injuries. ResultsA total of 4 924 hospitalized accidental injury cases were reported in Yangpu District， Shanghai. The incidence rate was 468.77/10⁵， the ratio of male to female was 1∶1.41. Among them， the age ≥65 group had the highest incidence rate， accounting for 55.83% of all cases. The incidence rate of female was 1.97 times higher than that of male （χ²=287.61， P<0.05）. The top five causes of injuries were falls， traffic-related， accident blunt injuries， injury by sharp instrument and fire or burns. The incidence rate of falls in female was higher than in male （χ²=176.65， P<0.05）. The incidence rates of sharp instrument and blunt injuries in male were higher than in female（sharp instrument χ²=13.45， P<0.05； blunt injuries χ²=9.10， P<0.05）. Altogether， the incidence rates of falls and traffic-related accident increased with age group （falls χ²_trend=1 593.07， P<0.05； traffic related χ²_trend=106.82， P<0.05）. Fire or burns and drowning had a median length of hospital stay of 8 and 14 days， respectively. ConclusionFalls is the leading cause of hospitalized accidental injuries （accounting for about 74% of the total number of hospitalized accidental injury cases）， with a higher incidence rate among elderly people aged ≥65 years old， and higher female than in male. Although the incidence rates of burns and drowning are not high， the hospital stay is relatively long. Therefore， accidental injury prevention and intervention should be targeted at key accidental injuries （such as falls， fire or burns， and drowning） and key populations （such as elderly female aged ≥65 years old）， to reduce the likelihood and the related loss of accidental injuries.