Objectives Endoscopists' abilities to diagnose early gastric cancers (EGCs) vary, especially between specialists and nonspecialists. We developed an artificial intelligence (AI)‐based diagnostic support tool “Tango” to differentiate EGCs and compared its performance with that of endoscopists. Methods The diagnostic performances of Tango and endoscopists (34 specialists, 42 nonspecialists) were compared using still images of 150 neoplastic and 165 non‐neoplastic lesions. Neoplastic lesions included EGCs and adenomas. The primary outcome was to show the noninferiority of Tango (based on sensitivity) over specialists. The secondary outcomes were the noninferiority of Tango (based on accuracy) over specialists and the superiority of Tango (based on sensitivity and accuracy) over nonspecialists. The lower limit of the 95% confidence interval (CI) of the difference between Tango and the specialists for sensitivity was calculated, with >−10% defined as noninferiority and >0% defined as superiority in the primary outcome. The comparable differences between Tango and the endoscopists for each performance were calculated, with >10% defined as superiority and >0% defined as noninferiority in the secondary outcomes. Results Tango achieved superiority over the specialists based on sensitivity (84.7% vs. 65.8%, difference 18.9%, 95% CI 12.3–25.3%) and demonstrated noninferiority based on accuracy (70.8% vs. 67.4%). Tango achieved superiority over the nonspecialists based on sensitivity (84.7% vs. 51.0%) and accuracy (70.8% vs. 58.4%). Conclusions The AI‐based diagnostic support tool for EGCs demonstrated a robust performance and may be useful to reduce misdiagnosis.

Background and study aims Endoscopic submucosal dissection (ESD) of superficial gastric lesions involving the pyloric ring is difficult. The pocket-creation method (PCM) with a small-caliber-tip transparent hood can overcome this difficulty by compressing the pyloric sphincter applying both traction and counter-traction. The aim of this study is to clarify the usefulness of the PCM for ESD of superficial gastric neoplasms involving the pyloric ring compared to the conventional method (CM). Patients and methods From October 2006 to August 2019, 66 gastric lesions requiring duodenal submucosal dissection beyond the pyloric ring in 66 patients were resected. The CM was mainly performed in the first period (CM group, n = 46) and the PCM in the second period (PCM group, n = 20). We retrospectively reviewed their medical records. Results Although no significant differences were observed in en bloc resection rates between the two groups, the PCM group had a significantly higher R0 resection rate than the CM group (P = 0.047). There were no holes in resected specimens in the PCM group while three specimens in the CM group had a hole. The dissection speed in the PCM group tended to be higher than in the CM group, although it did not reach statistical significance (P = 0.148). No significant differences were observed for the incidence of adverse events. Conclusions This is the first study reporting the advantages of the PCM over the CM for ESD of gastric lesions involving the pyloric ring. We believe that the PCM is an effective strategy to compress the pyloric sphincter and facilitates R0 resection.

Possible interaction between eosinophils and other immune cells in the pathomechanism of eosinophilic pustular folliculitis Dear Editor, A 49-year-old man with a history of diffuse large B-cell lymphoma (DLBCL) was referred to us for exacerbation of atopic dermatitis (AD). He was diagnosed with DLBCL at the age of 46 years. He received CHASER therapy (cyclophosphamide, etoposide, cytarabine, dexamethasone sodium phosphate, and rituximab) for recurrent DLBCL lesions in the liver, lung,

No abstract

A 62-year-old man with a flat early esophageal cancer was referred for endoscopic treatment. White light imaging revealed a pale red lesion, whereas linked color imaging (LCI) and blue laser imaging (BLI) yielded purple and brown images, respectively. Iodine staining demonstrated a large unstained area with a homogenous but very weak pink-color sign. This area appeared more clearly as purple and green on LCI and BLI, respectively; however, a different colored portion was observed at the 4 o'clock position inside the iodineunstained area. Histopathology findings of the resected specimen revealed squamous intraepithelial neoplasia at the 4 o'clock position and an esophageal squamous cell carcinoma in the remaining iodine-unstained area. LCI and BLI combined with iodine staining produce characteristic images that overcomes the pink-color sign, reflecting the histological features of a flat esophageal neoplasm. This new method is useful for detailed evaluation of early flat squamous cell neoplasms.