ABSTRACT
Background/Aims@#The accuracy of endosonographers in diagnosing gastric subepithelial lesions (SELs) using endoscopic ultrasonography (EUS) is influenced by experience and subjectivity. Artificial intelligence (AI) has achieved remarkable development in this field. This study aimed to develop an AI-based EUS diagnostic model for the diagnosis of SELs, and evaluated its efficacy with external validation. @*Methods@#We developed the EUS-AI model with ResNeSt50 using EUS images from two hospitals to predict the histopathology of the gastric SELs originating from muscularis propria. The diagnostic performance of the model was also validated using EUS images obtained from four other hospitals. @*Results@#A total of 2,057 images from 367 patients (375 SELs) were chosen to build the models, and 914 images from 106 patients (108 SELs) were chosen for external validation. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the model for differentiating gastrointestinal stromal tumors (GISTs) and non-GISTs in the external validation sets by images were 82.01%, 68.22%, 86.77%, 59.86%, and 78.12%, respectively. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in the external validation set by tumors were 83.75%, 71.43%, 89.33%, 60.61%, and 80.56%, respectively. The EUS-AI model showed better performance (especially specificity) than some endosonographers.The model helped improve the sensitivity, specificity, and accuracy of certain endosonographers. @*Conclusions@#We developed an EUS-AI model to classify gastric SELs originating from muscularis propria into GISTs and non-GISTs with good accuracy. The model may help improve the diagnostic performance of endosonographers. Further work is required to develop a multi-modal EUS-AI system.
ABSTRACT
Objective To investigate the molecular background of the New Delhi-metallo-1 (NDM-1)-producing Morganella morganii.Methods Two carbapenem-resistant M.morganii named 1 and 2 were isolated in the Second Hospital of Jiaxing,Zhejiang on October 4th and 29th,respectively.Antimicrobial susceptibility was determined by agar dilution method.Pulsed-field gel electrophoresis (PFGE) was performed to analyse the homololgy of isolates.Amplification with specific primers,DNA sequencing,conjugation experiments and genetic environment analysis were conducted to investigate the molecular mechanisms of resistance.Results The two M.morganii isolates were resistant to carbapenem and fluoroquinolones,while susceptible to aztreonam.PFGE analysis indicated that the two isolates were distinguishable.Amplification and DNA sequencing confirmed the coexistence of blaNDM-1,blasHv-12,qnrS1 and aac(6')-Ib-cr in both isolates.Transconjugants were detected with blaNDM.1 and qnrS1 simultaneously.Genetic environment analysis demonstrated that the blaNDM-1-bleMBL-trpF-dsbC-cutA1 structure was in consistence with those from known blaNDM-1-carrying Klebsiella pneumoniae.Conclusion The blaNDM-1 in M.morganii isolates possiblely obtained from K.pneumoniae through translatable plasmids.
ABSTRACT
Objective To investigate the pathological significance of expression of IL-23 in colon tissues of patients with steroid-dependent uncreative colitis at remission.Methods Expression of IL-23 was measured by means of Western Blot and immunohistochemistry SABC in inflammation repairing areas from 15 patients with steroid-dependent ulcerative colitis at remission, 30 patients with common ulcerative colitis at remission (15 treated with SASP and 15 with prednisone) and 10 normal colon tissues.The results were analyzed by SPSS 16.0.Results Compared with normal control, expression of IL-23 in patients of SASP maintenance therapy and prednisone with common ulcerative colitis were slightly increased ( P > 0.05), which was significantly lower that of steroid-dependent specimens ( P < 0.01).Conclusion Over-expression of IL-23 may plas a key role in the pathogenesis of steroid-dependent ulcerative colitis.