Background There are several types of pancreatic mass, so it is important to distinguish between them before treatment. Artificial intelligence (AI) is a mathematical technique that automates learning and recognition of data patterns. This study aimed to investigate the efficacy of our AI model using endoscopic ultrasonography (EUS) images of multiple types of pancreatic mass (pancreatic ductal adenocarcinoma [PDAC], pancreatic adenosquamous carcinoma [PASC], acinar cell carcinoma [ACC], metastatic pancreatic tumor [MPT], neuroendocrine carcinoma [NEC], neuroendocrine tumor [NET], solid pseudopapillary neoplasm [SPN], chronic pancreatitis, and autoimmune pancreatitis [AIP]). Methods Patients who underwent EUS were included in this retrospective study. The included patients were divided into training, validation, and test cohorts. Using these cohorts, an AI model that can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions was developed using a deep-learning architecture and the diagnostic performance of the AI model was evaluated. Results 22 000 images were generated from 933 patients. The area under the curve, sensitivity, specificity, and accuracy (95 %CI) of the AI model for the diagnosis of pancreatic carcinomas in the test cohort were 0.90 (0.84–0.97), 0.94 (0.88–0.98), 0.82 (0.68–0.92), and 0.91 (0.85–0.95), respectively. The per-category sensitivities (95 %CI) of each disease were PDAC 0.96 (0.90–0.99), PASC 1.00 (0.05–1.00), ACC 1.00 (0.22–1.00), MPT 0.33 (0.01–0.91), NEC 1.00 (0.22–1.00), NET 0.93 (0.66–1.00), SPN 1.00 (0.22–1.00), chronic pancreatitis 0.78 (0.52–0.94), and AIP 0.73 (0.39–0.94). Conclusions Our developed AI model can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions, but external validation is needed.

Objectives: This consensus was developed by the Asian EUS Group (AEG), who aimed to formulate a set of practice guidelines addressing various aspects of endoscopic ultrasound‐guided tissue acquisition (EUS‐TA).Methods: The AEG initiated the development of consensus statements and formed an expert panel comprising surgeons, gastroenterologists, and pathologists. Three online consensus meetings were conducted to consolidate the statements and votes. The statements were presented and discussed in the first two consensus meetings and revised according to comments. Final voting was conducted at a third consensus meeting. The Grading of Recommendations, Assessment, Development, and Evaluation system was adopted to define the strength of the recommendations and quality of evidence.Results: A total of 20 clinical questions and statements regarding EUS‐TA were formulated. The committee recommended that fine‐needle biopsy (FNB) needles be preferred over conventional fine‐needle aspiration (FNA) needles for EUS‐TA of subepithelial lesions. For solid pancreatic masses, rapid on‐site evaluation is not routinely recommended when FNB needles are used. For dedicated FNB needles, fork‐tip and Franseen‐tip needles have essentially equivalent performance.Conclusion: This consensus provides guidance for EUS‐TA, thereby enhancing the quality of EUS‐TA.

The prognostic significance of sarcopenia in unresectable advanced esophageal cancer remains unclear. Our study retrospectively evaluated 176 consecutive Japanese patients with esophageal squamous cell carcinoma who had been diagnosed with unresectable advanced cancer in Aichi Cancer Center Hospital between January 2007 and December 2014. Skeletal muscle mass was calculated from abdominal computed tomography (CT) scans before treatment, and patients were divided into sarcopenic and non-sarcopenic groups. Sarcopenia was present in 101 patients (57.4%). Eighty-two patients in the sarcopenic group and 63 patients in the non-sarcopenic group died during follow-up (mean: 20.3 months). The overall survival (OS) rate was significantly lower in the sarcopenic group compared to the non-sarcopenic group (2-year OS: 9.8% vs. 23.7%, p < 0.01). Cox regression analysis revealed only pretreatment sarcopenia as an independent prognostic factor (hazard ratio (HR): 1.48, 95% confidence interval (CI): 1.04–2.10, p = 0.03). In the sarcopenic group, withdrawn cases, for whom the planned treatment was discontinued for some reason, showed a significantly lower OS rate compared to complete cases (1-year OS: 11.0% vs. 59.9%, p < 0.01). The most common reason for discontinuation was aspiration pneumonia (64.5%). Presence of sarcopenia was an independent prognostic factor for unresectable advanced esophageal cancer. Identifying the presence of sarcopenia prior to treatment may improve the prognosis.