| Fig. 2 Proposed management for patients with atrophic gastritis, gastric intestinal metaplasia, or gastric epithelial dysplasia. OLGA, Operative Link on Gastritis Assessment; OLGIM, Operative Link on Gastritis Assessment based on Intestinal Metaplasia.

| Fig. 1 Conventional peroral endoscopic myotomy (POEM) is completed at the anterior wall of the esophagus. Next, the peritoneal cavity is accessed through the submucosal tunnel. a Schematic drawing of POEM with fundoplication (POEM + F) procedure (Step 1). The endoscope is advanced into the peritoneal cavity, just after passing the diaphragmatic crus.

| Fig. 2 The green line represents the receiver operating characteristic (ROC) curve (with 95 % confidence intervals; blue lines) for endoscopic grading of gastric intestinal metaplasia (EGGIM) scores compared to operative link on gastric intestinal metaplasia (OLGIM) stages III and IV for the presence of extensive intestinal metaplasia, giving an area under the curve (AUC) of 0.96.

| Fig. 1 Flowchart of the data preparation and training/testing procedure of the deep convolutional neural network (DCNN) model. The functions of networks 1, 2, and 3 are filtering blurry images, early gastric cancer identification, and classification of gastric location, respectively. The three networks were independently trained. Blurry images and some clear images were used for the training of the network 1. Clear images were further classified into malignant or benign depending on the pathology evidence for the training and testing of network 2. Parallelly, clear images were classified into 10 or 26 gastric locations by two endoscopists with more than 10 years of esophagogastroduodenoscopy (EGD) experience for the training and testing of network 3. When running on the videos, all frames will be first filtered via network 1, so only clear images can enter into networks 2 and 3.