No abstract

The biopsy‐based diagnosis of autoimmune pancreatitis (AIP) is difficult but is becoming imperative for pathologists due to the increased amount of endoscopic ultrasound‐guided biopsy tissue. To cope with this challenge, we propose guidance for the biopsy diagnosis of type 1 AIP. This guidance is for pathologists and comprises three main parts. The first part includes basic issues on tissue acquisition, staining, and final diagnosis, and is intended for gastroenterologists as well. The second part is a practical guide for diagnosing type 1 AIP based on the AIP clinical diagnostic criteria 2018. Inconsistent histological findings, tips for evaluating IgG4 immunostaining and key histological features including the ductal lesion and others are explained. Storiform fibrosis and obliterative phlebitis are diagnostic hallmarks but are sometimes equivocal. Storiform fibrosis is defined as spindle‐shaped cells, inflammatory cells and fine collagen fibers forming a flowing arrangement. Obliterative phlebitis is defined as fibrous venous obliteration with inflammatory cells. Examples of each are provided. The third part describes the differentiation of AIP from pancreatic ductal adenocarcinoma (PDAC), focusing on histological features of acinar‐ductal metaplasia in AIP, which is an important mimicker of PDAC. This guidance will help standardize pathology reports of pancreatic biopsies for diagnosing type 1 AIP.

Background and study aim: There are several types of pancreatic masses, so it is important to distinguish between them before treatment. Artificial intelligence (AI) is a mathematical technique that automates learning and recognizing data patterns. The aim of this study was to investigate the efficacy of our AI model using endoscopic ultrasonography (EUS) images of multiple types of pancreatic masses (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: CP, and autoimmune pancreatitis: AIP). Patients and 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 nonpancreatic carcinomas was developed using a deep learning architecture and the diagnostic performance of the AI model was evaluated. Results: From 933 patients, a total of 22,000 images were generated. The area under the curve, sensitivity, specificity, and accuracy (95% confidence interval: 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 (0.87-0.99), 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), CP: 0.78 (0.52-0.94), and AIP: 0.73 (0.39-0.94). Conclusions: Our developed AI model may distinguish pancreatic carcinomas from nonpancreatic carcinomas, but external validation is needed.

No abstract

Tract dilation is one of the most difficult stages of endoscopic ultrasound‐guided hepaticogastrostomy (EUS‐HGS), especially for beginners. To overcome this problem, we applied a special dedicated dilator. Herein, we retrospectively evaluate the safety and usefulness of a novel drill dilator in EUS‐HGS. This single‐center retrospective study included 20 consecutive patients who underwent EUS‐HGS with a novel drill dilator. The tip is 0.77 mm, and it becomes 7F at 3 cm from tip. The track is dilated to 7F by simple clockwise rotation. The technical success rate of both initial tract dilation and stent placement was 20/20 (100%). No cases required additional dilation such as balloon or electric cautery. In 13/20 cases (65.0%), EUS‐HGS was performed by beginner endoscopists. Median time required for dilation was 62.5 s (range, 30–144 s). Median procedure time was 13 min (range, 7–25 min). Early adverse events were two cases of mild fever. There was no bile leakage or bleeding. The novel drill dilator appears to be safe and useful for EUS‐HGS. As it is not necessary to press the device strongly, there is no pushback during dilation and the scope position is stable. These characteristics facilitate EUS‐HGS even for beginners. This device may enable the further development and increased dissemination of EUS intervention.