Objective To propose a method for abdominal multi-organ segmentation assisted by multi-phase CT synthesis.Methods Multi-phase CT synthesis for synthesizing high-quality CT images was used to increase the information details for image segmentation.A transformer block was introduced to help to capture long-range semantic information in cooperation with perceptual loss to minimize the differences between the real image and synthesized image.Results The model was trained using multi-phase CT dataset of 526 total cases from Nanfang Hospital.The mean maximum absolute error(MAE)of the synthesized non-contrast CT,venous phase contrast-enhanced CT(CECT),and delay phase CECT images from arterial phase CECT was 19.192±3.381,20.140±2.676 and 22.538±2.874,respectively,which were better than those of images synthesized using other methods.Validation of the multi-phase CT synthesis-assisted abdominal multi-organ segmentation method showed an average dice coefficient of 0.847 for the internal validation set and 0.823 for the external validation set.Conclusion The propose method is capable of synthesizing high-quality multi-phase CT images to effectively reduce the errors in registration between different phase CT images and improve the performance for segmentation of 13 abdominal organs.

Objective To propose a method for abdominal multi-organ segmentation assisted by multi-phase CT synthesis.Methods Multi-phase CT synthesis for synthesizing high-quality CT images was used to increase the information details for image segmentation.A transformer block was introduced to help to capture long-range semantic information in cooperation with perceptual loss to minimize the differences between the real image and synthesized image.Results The model was trained using multi-phase CT dataset of 526 total cases from Nanfang Hospital.The mean maximum absolute error(MAE)of the synthesized non-contrast CT,venous phase contrast-enhanced CT(CECT),and delay phase CECT images from arterial phase CECT was 19.192±3.381,20.140±2.676 and 22.538±2.874,respectively,which were better than those of images synthesized using other methods.Validation of the multi-phase CT synthesis-assisted abdominal multi-organ segmentation method showed an average dice coefficient of 0.847 for the internal validation set and 0.823 for the external validation set.Conclusion The propose method is capable of synthesizing high-quality multi-phase CT images to effectively reduce the errors in registration between different phase CT images and improve the performance for segmentation of 13 abdominal organs.

Objective·To investigate the relation between urinary excretion of protein-bound uremic toxins(PBUTs)and upper urinary tract calculus.Methods·Residents aged 18?80 years in the community of Haitou,Danzhou city in Hainan Province were recruited.Basic information and diet for the last 3 d of the subjects were recorded.Their fasting sera and 24-hour urine samples were collected,and they also underwent ultrasound examination of kidneys and ureters.The subjects with upper urinary calculi detected by ultrasound or a clear history of upper urinary calculi were selected as the calculus group,and the others as the non-calculus group.The biochemical indicators related to the formation of calculus in blood and urine were detected,and the levels of PBUTs,including indoxyl sufate(IS),indole-3-acetic acid(IAA),and p-cresol sulfate(PCS)in blood and urine,as well as oxalic acid and citric acid in urine were detected by high-performance liquid chromatography.The related factors of upper urinary tract calculus formation were analyzed by multivariate Logistic regression.The correlations of urine PBUTs with urine uric acid,oxalic acid,and citric acid were analyzed by Spearman correlation test.Results·A total of 117 participants were screened out with 54 people in the calculus group and 63 people in the non-calculus group.There were no significant differences between the two groups in terms of gender,age,serum indicators,and prevalence of complications such as hypertension,diabetes,and hyperuricemia/gout.The 24-hour urine pH,calcium,uric acid,and chlorine in the calculus group were significantly higher than those in the non-calculus group(all P<0.05),while IS was significantly lower than that in the non-calculus group(P<0.05).Multivariate Logistic regression analysis showed that urinary IS(OR=0.929,95%CI 0.875?0.986,P=0.016)was related to the calculus formation independently,in addition to urinary calcium.The Spearman correlation analysis results showed that the levels of IAA(r=0.420,P=0.000)and PCS(r=0.307,P=0.001)in 24-hour urine were positively correlated with oxalic acid,PCS was positively correlated with uric acid(r=0.297,P=0.002),and IS was positively correlated with citric acid(r=0.289,P=0.002).Conclusion·In the population,a decrease in urinary excretion of IS may be an independent risk factor for the formation of upper urinary tract calculus,and PBUTs levels are correlated with levels of uric acid,oxalic acid,and citric acid.