Artificial intelligence-aided diagnostic imaging: A state-of-the-art technique in precancerous screening.

BACKGROUND AND AIM: Chromoendoscopy with the use of indigo carmine (IC) dye is a crucial endoscopic technique to identify gastrointestinal neoplasms. However, its performance is limited by the endoscopist's skill, and no standards are available for lesion identification. Thus, we developed an artificial intelligence (AI) model to replace chromoendoscopy. METHODS: This pilot study assessed the feasibility of our novel AI model in the conversion of white-light images (WLI) into virtual IC-dyed images based on a generative adversarial network. The predictions of our AI model were evaluated against the assessments of five endoscopic experts who were blinded to the purpose of this study with a staining quality rating from 1 (unacceptable) to 4 (excellent). RESULTS: The AI model successfully transformed the WLI of polyps with different morphologies and different types of lesions in the gastrointestinal tract into virtual IC-dyed images. The quality ratings of the real IC-dyed and AI images did not significantly differ concerning surface structure (AI vs IC: 3.08 vs 3.00), lesion border (3.04 vs 2.98), and overall contrast (3.14 vs 3.02) from 10 sets of images (10 AI images and 10 real IC-dyed images). Although the score depended significantly on the evaluator, the staining methods (AI or real IC) and evaluators had no significant interaction (P > 0.05) with each other. CONCLUSION: Our results demonstrated the feasibility of employing AI model's virtual IC staining, increasing the possibility of being employed in daily practice. This novel technology may facilitate gastrointestinal lesion identification in the future.

Open-label randomised controlled trial about application of bundle care in prevention of unplanned extubation of nasobiliary drainage catheter after endoscopic retrograde cholangiopancreatography.

AIMS AND OBJECTIVES: To observe the effects of bundle care on preventing unplanned extubation of nasobiliary drainage catheter after endoscopic retrograde cholangiopancreatography. BACKGROUND: Preventing unplanned extubation has become a difficult problem for nursing staff because the catheter is stiff, fine and long. DESIGN: A total of 114 cases that experienced nasobiliary drainage after endoscopic retrograde cholangiopancreatography for the first time in our hospital from April 2015-July 2016 were enrolled in this study. According to receiving routine nurse or bundle nurse, these cases were randomly divided into control (n = 56) and intervention (n = 58) group. METHOD: The unplanned extubation incidence, contact area between tape and catheter and tensile resistance were compared between the two groups. RESULTS: The contact area was one square centimetre in the control group and 5 cm2 in the intervention group. Tensile resistance was significantly higher in the intervention group than in the control (all p < .05). Unplanned extubation incidence was significantly lower in the intervention group (1.72%, 1/58) than in the control (12.5%, 7/56) (p = .0305). CONCLUSION: Bundle care can effectively decrease unplanned extubation incidence after endoscopic retrograde cholangiopancreatography. RELEVANCE TO CLINICAL PRACTICE: This study provides a basis for decreasing unplanned extubation incidence.

Updated meta-analysis of pancreatic stent placement in preventing post-endoscopic retrograde cholangiopancreatography pancreatitis.

AIM: To investigate the efficacy and safety profile of pancreatic duct (PD) stent placement for prevention of post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP). METHODS: We performed a search of MEDLINE, EMBASE, and Cochrane Library to identify randomized controlled clinical trials of prophylactic PD stent placement after ERCP. RevMan 5 software provided by Cochrane was used for the heterogeneity and efficacy analyses, and a meta-analysis was performed for the data that showed homogeneity. Categorical data are presented as relative risks and 95% confidence intervals (CIs), and measurement data are presented as weighted mean differences and 95%CIs. RESULTS: The incidence rates of severe pancreatitis, operation failure, complications and patient pain severity were analyzed. Data on pancreatitis incidence were reported in 14 of 15 trials. There was no significant heterogeneity between the trials (I(2) = 0%, P = 0.93). In the stent group, 49 of the 1233 patients suffered from PEP, compared to 133 of the 1277 patients in the no-stent group. The results of this meta-analysis indicate that it may be possible to prevent PEP by placing a PD stent. CONCLUSION: PD stent placement can reduce postoperative hyperamylasemia and might be an effective and safe option to prevent PEP if the operation indications are well controlled.

Prevention of post-endoscopic retrograde cholangiopancreatography pancreatitis by epinephrine sprayed on the papilla.

BACKGROUND AND AIM: Epinephrine sprayed on the papilla may reduce papillary edema and prevent acute pancreatitis after endoscopic retrograde cholangiopancreatography (ERCP). The aim of this study was to evaluate the effects of localized irrigation with epinephrine saline for prevention of post-ERCP pancreatitis (PEP). METHODS: A total of 941 patients who were scheduled for ERCP were recruited into this study. We randomized the patients to have 20 mL of either 0.02% epinephrine or saline sprayed on the papilla after diagnostic ERCP to prevent post-ERCP pancreatitis. We recorded duct visualization, presence of pancreatic acinarization, number of injections into the pancreatic duct, total volume of contrast used, and procedure duration. The serum amylase levels were measured at 6, 24 and 48 h after ERCP. We counted the patients of PEPs and compared whether there was significant difference between the pancreatitis group and the no pancreatitis group. RESULTS: A univariate analysis of the explanatory variables between the epinephrine and control groups, the pancreatitis and no pancreatitis groups revealed the treatment to be effective, but most of the groups were not statistically significant. PEPs occurred in 40 of the 941 patients (4.25%), the incidence of pancreatitis tended to be higher in the control group (31/480, 6.45%) than in the epinephrine group (9/461, 1.95%) (P = 0.0086). CONCLUSIONS: Epinephrine sprayed on the papilla may be effective to prevent PEP. Female patients (aged ≥ 18 years and < 35 years) (7/40, 17.5%), common bile duct diameter < 10 mm (27/40, 67.5%), previous cholangitis (3/40, 7.5%), body mass index ≥ 24 (22/40, 55%), and/or serum triglycerides ≥ 5.65 mmol/L (6/40, 15%), might be risk factors for post-ERCP pancreatitis, but are not statistically significant in the study.

[HCCR-2 enhances the division and proliferation of SMMC 7721 via PI3K/Akt pathway].

OBJECTIVE: To observe the biological changes of SMMC 7721 cell line which was stably transfected with HCCR-2 gene and to study the molecular mechanism of HCCR-2 expression in SMMC 7721 cell line. METHODS: SMMC7721 cells were transfected with HCCR-2-pEGFP-N1 and pEGFP-N1 by lipofectmine 2000 and the transfectants were selected and confirmed using Western-blot technique. Cell cycles were tested by flow cytometry. The reproductive activity was detected by MTT assay. SMMC 7721 cells were routinely cultured with treatment of increasing concentrations (0, 50, 100, 200 ng/ml) of EGF for 24 h. Cells were pretreated with the specific inhibitor of PI3K (LY294002) and then cultured with EGF (100 ng/ml) for 24h and the expression of HCCR protein in these cells were measured by Western blot. Another set of SMMC 7721 cells were transfected with DN-Akt-pcDNA3.1 (dominant negative Akt kinase) and pcDNA3.1 by lipofectmine 2000. The transfectants were selected and confirmed using Western-blot technique as before. HCCR-2 and bcl-2 were measured on protein level by Western blot. RESULTS: SMMC 7721 cells were stably transfected with HCCR-2 gene. HCCR-2 gene transfection can increase the proportion of S-phase cells (21.62%+/-1.33% vs 15.76%+/-0.73%, P<0.01) and decrease the cell apoptosis (1.28%+/-0.16% vs 7.72%+/-0.23%, P<0.01). MTT assay showed the growth of HCCR-2 gene transfected cells was faster than that of empty vecter transfected cells. The HCCR-2 protein was up-regulated in a dose-dependent manner in the cells cultured with different concentrations of EGF for 24 h. Treatment of SMMC 7721 cells with specific inhibitor of PI3K (LY294002) suppressed EGF-induced HCCR-2 expression. HCCR-2 protein was down-regulated in dominant negative Akt transfectants. CONCLUSIONS: EGF upregulated HCCR-2 protein expression in SMMC 7721 cell line via PI3K/Akt pathway. The overexpression of HCCR-2 could enhance the division and proliferation of SMMC 7721.