Objective To study the effect of recombinant human endostatin hormone combined with transcatheter arterial chemoembolization (TACE) for the treatment of primary hepatocellular carcinoma (HCC).Methods Fifty-two primary HCC patients were divided into combined group (26 patients) and control group (26 patients) by random digits table method.The patients in combined group received TACE and recombinant human endostatin hormone added in embolism emulsion.The recent curative effect,level of serum vascular endothelial growth factor (VEGF),adverse reactions,recurrence rate and survival rate were compared between two groups.Results The response rate(RR) and clinical benefit rate(DCR) in combined group were 57.69％(15/26),84.62％(22/26),in control group were 34.62％(9/26),73.08％(19/26),there were significant differences (x2 =5.237,P ＜ 0.05 ; x2 =4.284,P ＜ 0.05).The 7th,14th,28th day after TACE,the level of VEGF in two groups was first increased and then a downward trend,the difference were statistically significant (P ＜ 0.05).The level of VEGF in combined group was significantly lower than that in control group (P＜ 0.05).The follow up rate was 94.23％(49/52),the 1-year and 2-year recurrence rate in combined group was significantly lower than that in control group (P＜ 0.05).The 2-year and 3-year survival rate in combined group was significantly higher than that in control group (P ＜ 0.05).Conclusion With TACE plus recombinant human endostatin hormone can effectively inhibit the increase of serum VEGF level,improve curative effect and disease control rate,reduce tumor recurrence and improve survival rate.

Objective To evaluate the potency of applying an artificial intelligence(AI)based model for classifying vertebral fractures in lumbar X-ray images.Methods Patients who underwent lateral lumbar X-ray and MRI were retrospectively selected.Based on MRI results,the vertebrae were categorized as fresh fractures,old fractures,and normal vertebrae.A ResNet-18 classification model was constructed using delineated region of interest(ROI)on the X-ray images,and the model's performance was evaluated.Results A total of 272 patients(662 vertebrae)were included in this study.The vertebrae were randomly divided into training(n=529)and validation(n=133)sets.The model's performance in discerning normal vertebrae,fresh fractures,and old fractures revealed accuracy of 0.91,0.42,and 0.75,and the sensitivity were 0.91,0.408,and 0.72,while the specificity were 0.796,0.892,and 0.796,respectively.Conclusion The X-ray-based ResNet-18 AI model has significant accuracy for distinguishing old fractures and normal vertebrae;However,the model's accuracy needs further improvement for distinguishing fresh fractures.