The features of gastric epithelial reactive hyperplastic lesions under magnifying endoscopy combined with narrow-band imaging.

BACKGROUND AND PURPOSE: Gastric reactive hyperplasia (RH) is a common benign lesion of the gastric mucosa that can be resolved by conservative treatment without endoscopic intervention. Some RH lesions are indistinguishable from low-grade intraepithelial neoplasia (LGIN) lesions of gastric mucosa under endoscopy. The aim of this study was to investigate the morphological features of RH lesions under magnifying endoscopy combined with narrow-band imaging (ME-NBI). METHODS: A retrospective study of 653 patients with superficial suspicious lesions of gastric mucosa was performed. According to the pathological results of biopsies, the final included lesions were divided into the RH group (n = 88) and LGIN group (n = 138). We analysed the microvascular and microsurface patterns of these lesions under ME-NBI, extracted the most significant combination of endoscopic features of RH lesions, and evaluated their diagnostic performance. RESULTS: ME-NBI characteristics that could distinguish RH lesions from LGIN lesions after univariate analysis were included in multivariate logistic regression. The results showed that ten characteristics, including intervening part (IP) length homogeneity, type III gastric pit pattern and homogeneity of marginal crypt epithelium (MCE), were statistically significant. Receiver operating characteristic (ROC) analysis showed that the triad of these features was the best combination for diagnosing RH lesions with an AUC of 0.886 (95% confidence interval; 0.842-0.929), the sensitivity of 85.5% and specificity of 79.5%. CONCLUSIONS: The triad of IP length homogeneity, type III pit pattern and MCE homogeneity under ME-NBI helps endoscopists to identify gastric RH lesions, thereby avoiding unnecessary biopsy and repeat endoscopy due to misjudgment of neoplastic lesions.

Intestinal Stem Cells Damaged by Deoxycholic Acid via AHR Pathway Contributes to Mucosal Barrier Dysfunction in High-Fat Feeding Mice.

High-fat exposure leads to impaired intestinal barrier function by disrupting the function of intestinal stem cells (ISCs); however, the exact mechanism of this phenomenon is still not known. We hypothesize that high concentrations of deoxycholic acid (DCA) in response to a high-fat diet (HFD) affect aryl hydrocarbon receptor (AHR) signalling in ISCs and the intestinal barrier. For this purpose, C57BL/6J mice feeding on a low-fat diet (LFD), an HFD, an HFD with the bile acid binder cholestyramine, and a LFD with the DCA were studied. We found that high-fat feeding induced an increase in faecal DCA concentrations. An HFD or DCA diet disrupted the differentiation function of ISCs by downregulating AHR signalling, which resulted in decreased goblet cells (GCs) and MUC2, and these changes were reversed by cholestyramine. In vitro experiments showed that DCA downregulated the differentiation function of ISCs, which was reversed by the AHR agonist 6-formylindolo [3,2-b]carbazole (FICZ). Mechanistically, DCA caused a reduction in indoleamine 2,3-dioxygenase 1 (IDO1) in Paneth cells, resulting in paracrine deficiency of the AHR ligand kynurenine in crypts. We demonstrated for the first time that DCA disrupts intestinal mucosal barrier function by interfering with AHR signalling in ISCs. Supplementation with AHR ligands may be a new therapeutic target for HFD-related impaired intestinal barrier function.

A deep learning model based on magnifying endoscopy with narrow-band imaging to evaluate intestinal metaplasia grading and OLGIM staging: A multicenter study.

BACKGROUND AND PURPOSE: Patients with stage III or IV of operative link for gastric intestinal metaplasia assessment (OLGIM) are at a higher risk of gastric cancer (GC). We aimed to construct a deep learning (DL) model based on magnifying endoscopy with narrow-band imaging (ME-NBI) to evaluate OLGIM staging. METHODS: This study included 4473 ME-NBI images obtained from 803 patients at three endoscopy centres. The endoscopic expert marked intestinal metaplasia (IM) regions on endoscopic images of the target biopsy sites. Faster Region-Convolutional Neural Network model was used to grade IM lesions and predict OLGIM staging. RESULTS: The diagnostic performance of the model for IM grading in internal and external validation sets, as measured by the area under the curve (AUC), was 0.872 and 0.803, respectively. The accuracy of this model in predicting the high-risk stage of OLGIM was 84.0%, which was not statistically different from that of three junior (71.3%, p = 0.148) and three senior endoscopists (75.3%, p = 0.317) specially trained in endoscopic images corresponding to pathological IM grade, but higher than that of three untrained junior endoscopists (64.0%, p = 0.023). CONCLUSION: This DL model can assist endoscopists in predicting OLGIM staging using ME-NBI without biopsy, thereby facilitating screening high-risk patients for GC.

Diagnosis and segmentation effect of the ME-NBI-based deep learning model on gastric neoplasms in patients with suspected superficial lesions - a multicenter study.

Background: Endoscopically visible gastric neoplastic lesions (GNLs), including early gastric cancer and intraepithelial neoplasia, should be accurately diagnosed and promptly treated. However, a high rate of missed diagnosis of GNLs contributes to the potential risk of the progression of gastric cancer. The aim of this study was to develop a deep learning-based computer-aided diagnosis (CAD) system for the diagnosis and segmentation of GNLs under magnifying endoscopy with narrow-band imaging (ME-NBI) in patients with suspected superficial lesions. Methods: ME-NBI images of patients with GNLs in two centers were retrospectively analysed. Two convolutional neural network (CNN) modules were developed and trained on these images. CNN1 was trained to diagnose GNLs, and CNN2 was trained for segmentation. An additional internal test set and an external test set from another center were used to evaluate the diagnosis and segmentation performance. Results: CNN1 showed a diagnostic performance with an accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 90.8%, 92.5%, 89.0%, 89.4% and 92.2%, respectively, and an area under the curve (AUC) of 0.928 in the internal test set. With CNN1 assistance, all endoscopists had a higher accuracy than for an independent diagnosis. The average intersection over union (IOU) between CNN2 and the ground truth was 0.5837, with a precision, recall and the Dice coefficient of 0.776, 0.983 and 0.867, respectively. Conclusions: This CAD system can be used as an auxiliary tool to diagnose and segment GNLs, assisting endoscopists in more accurately diagnosing GNLs and delineating their extent to improve the positive rate of lesion biopsy and ensure the integrity of endoscopic resection.