ObjectiveTo investigate the changes in gut microbiota after transjugular intrahepatic portosystemic shunt (TIPS) in cirrhotic patients with mild hepatic encephalopathy (MHE) in different prognosis groups. MethodsA total of 28 MHE cirrhotic patients who were hospitalized and underwent TIPS in Xijing Hospital of Digestive Diseases from July 2016 to July 2017 were enrolled. Fecal samples and related clinical data were collected on days 1-3 before surgery and at 1 month after surgery. According to the prognosis after surgery, the patients were divided into none-hepatic encephalopathy (HE) group with 8 patients, MHE group with 12 patients, and overt hepatic encephalopathy (OHE) group with 8 patients. Fecal samples were analyzed by 16S rRNA sequencing to obtain the relative abundance of gut microbiota, and SPSS and R packages were used to analyze the biodiversity, postoperative changes, and differences in such changes of gut microbiota at the genus level between groups. The chi-square test was used for comparison of categorical data between groups; the Kruskal-Wallis H test was used for comparison of continuous data between three groups; the Bonferroni method was used for multiple comparisons of multiple samples; the Wilcoxon signed-rank test was used for comparison before and after surgery within each group. For microbiome beta-diversity analyses, a principal coordinate analysis (PCoA) was performed based on Bray-Curtis distance matrix, and the Adonis method (PerMANOVA) was used for comparison between groups. ResultsPCoA based on Bray-Curtis distance matrix showed that only the MHE group had a significant change in beta diversity after surgery (F=2.71, P=0.049). After surgery, the non-HE group had significant increases in the abundance of the native flora Dialister, Coprococcus, Ruminococcaceae_uncultured, Flavonifractor, and Clostridium_sensu_stricto_1 (Z=2.521, 2.1, 2.1, 2.1, and 1.96, all P＜0.05); the MHE group had significant reductions in the abundance of the harmful flora Granulicatella（Z=2.521,P=0.012）, Enterococcus（Z=2.51,P=0.012）, Streptococcus（Z=2.432,P=0.015）, and Rothia（Z=2.001,P=0.045） and significant increases in the abundance of Veillonella（Z=2.353,P=0.019） and Megasphaera（Z=1.955,P=0.05）; the OHE group only had a significant increase in the abundance of Veillonella after surgery (Z=2.38, P=0.017). There was a significant difference in the change in gut microbiota (postoperative abundance/preoperative abundance) between the non-HE group, the MHE group, and the OHE group ［2.00 (1.11-91.61) vs 1.21 (0.26-679) vs 0.09 (0.01-0.92), χ2=6.249, P=0.043］. ConclusionThere is a significant difference in the change in gut microbiota after TIPS between patients with different prognoses, and the increase in the abundance of native flora may have a certain influence on the remission of MHE.

BACKGROUND:MRI is important for the diagnosis of early knee osteoarthritis.MRI image recognition and intelligent segmentation of knee osteoarthritis using deep learning method is a hot topic in image diagnosis of artificial intelligence. OBJECTIVE:Through deep learning of MRI images of knee osteoarthritis,the segmentation of femur,tibia,patella,cartilage,meniscus,ligaments,muscles and effusion of knee can be automatically divided,and then volume of knee fluid and muscle content were measured. METHODS:100 normal knee joints and 100 knee osteoarthritis patients were selected and randomly divided into training dataset(n=160),validation dataset(n=20),and test dataset(n=20)according to the ratio of 8:1:1.The Coarse-to-Fine sequential training method was used to train the 3D-UNET network deep learning model.A Coarse MRI segmentation model of the knee sagittal plane was trained first,and the rough segmentation results were used as a mask,and then the fine segmentation model was trained.The T1WI and T2WI images of the sagittal surface of the knee joint and the marking files of each structure were input,and DeepLab v3 was used to segment bone,cartilage,ligament,meniscus,muscle,and effusion of knee,and 3D reconstruction was finally displayed and automatic measurement results(muscle content and volume of knee fluid)were displayed to complete the deep learning application program.The MRI data of 26 normal subjects and 38 patients with knee osteoarthritis were screened for validation. RESULTS AND CONCLUSION:(1)The 26 normal subjects were selected,including 13 females and 13 males,with a mean age of(34.88±11.75)years old.The mean muscle content of the knee joint was(1 051 322.94±2 007 249.00)mL,the mean median was 631 165.21 mL,and the mean volume of effusion was(291.85±559.59)mL.The mean median was 0 mL.(2)There were 38 patients with knee osteoarthritis,including 30 females and 8 males.The mean age was(68.53±9.87)years old.The mean muscle content was(782 409.18±331 392.56)mL,the mean median was 689 105.66 mL,and the mean volume of effusion was(1 625.23±5 014.03)mL.The mean median was 178.72 mL.(3)There was no significant difference in muscle content between normal people and knee osteoarthritis patients.The volume of effusion in patients with knee osteoarthritis was higher than that in normal subjects,and the difference was significant(P<0.05).(4)It is indicated that the intelligent segmentation of MRI images by deep learning can discard the defects of manual segmentation in the past.The more accuracy evaluation of knee osteoarthritis was necessary,and the image segmentation was processed more precisely in the future to improve the accuracy of the results.