Raymond Shing Yan Tang

Endoscopic ultrasound (EUS)-guided elastography is an advanced imaging technique designed to improve assessment of lesion characteristics and disease diagnosis. It allows real-time assessment of tissue stiffness and is currently available in the form of strain elastography (SE) and shear wave elastography (SWE). While EUS-guided SE has high sensitivity for diagnosing malignant solid pancreatic lesions, its specificity remains modest. SWE is a novel technology currently available on the EUS platform. Promising data have been reported on the utility of EUS-guided SWE in various diseases of the pancreas and liver. This review aims to discuss the applications of EUS-guided SE and SWE in pancreatic and liver diseases.

Background and Objectives: Live courses are important sources of endoscopy education. While diagnostic and therapeutic EUS procedures have been increasingly performed in live courses recently, data on outcomes of EUS in live courses remain scarce. This study aims to compare outcomes of EUS procedures in live courses versus routine clinical service. Methods: All diagnostic and therapeutic EUS cases performed in workshops at Prince of Wales Hospital at The Chinese University of Hong Kong from 2015 to 2021 were considered for inclusion. Therapeutic EUS cases were divided into 5 subtypes: rendezvous, access (biliary, pancreatic, and enteric), endohepatology, lesion ablation or injection, and drainage (cystogastrostomy and gallbladder drainage). Propensity score matching of procedure subtype, procedure date, and age-adjusted Charlson Comorbidity Index was performed to match live course and routine service cases on a 1:1 basis for comparison. Results: After propensity score matching, 108 live courses and 108 routine service cases were included in the analysis. Access procedures were the most common therapeutic EUS subtype performed, followed by lesion injection/ablation and drainage procedures. Rates of benign and malignant indications for procedure were comparable in both cohorts. Technical success was 100% in diagnostic EUS in both groups. There was no significant difference in technical success in therapeutic EUS (96.7% vs. 100%, P = 0.496). Intraprocedure and postprocedure adverse events were also comparable in both groups. There were no 30-day procedure-related mortalities. Conclusion: In this study, diagnostic and therapeutic EUS performed during live courses yield similar technical success and safety outcomes compared with cases performed routinely.

Recent studies have demonstrated the potential of artificial intelligence (AI) in diagnostic and therapeutic endoscopy for managing gastrointestinal diseases. However, there is limited knowledge of the perspective of endoscopists towards AI technology, particularly in the Asian community. This study aims to bridge this knowledge gap to guide policymakers, healthcare providers, and technology developers through an Asia AI Task Force. An online survey of 45 questions exploring (a) the perceived benefits of AI in endoscopy, (b) the barriers to adopting AI in endoscopy, (c) the priority areas and barriers to research in AI endoscopy, as well as (d) priorities for an Asia AI Task Force were distributed between November 2022 and May 2023 to endoscopists from sixteen medical institutes across ten Asian regions. A total of 293 participants completed the survey. Two-fifths (41.98%, n = 123) report no prior exposure to AI endoscopy. The majority (73.2%, n = 90/123) of those without prior AI exposure express concerns about the accountability of AI and its impact on working practices. Almost all participants agree that AI enhances quality improvement (90.8%, n = 266) and leads to better diagnosis (90.4%, n = 265). 69% (n = 202) identify "staying up to date with AI advances" as the top challenge towards clinical adoption of AI. Notably, those without prior AI exposure express high concern regarding accountability for the wrong diagnoses (73.2% vs. 60.6%, p = 0.03) and lack of clinical trials (76.4% vs. 57.1%, p = 0.001). Most respondents prioritise developing a reference paper guide for clinicians interested in AI (81.2%) and supporting funding applications for AI research (81.5%) as key areas that an Asia AI Endoscopy task force should address. The survey results from Asian endoscopists emphasise the pressing need for collaborative frameworks and educational initiatives, including establishing an Asia AI Task Force, to facilitate the successful integration of AI in endoscopy practice and research across the region.

Ultrasound (US)-guided needle insertion is widely employed in percutaneous interventions. However, providing feedback on the needle tip position via US imaging presents challenges due to noise, artifacts, and the thin imaging plane of US, which degrades needle features and leads to intermittent tip visibility. In this letter, a Mamba-based US needle tracker MambaXCTrack utilizing structured state space models cross-correlation (SSMX-Corr) and implicit motion prompt is proposed, which is the first application of Mamba in US needle tracking. The SSMX-Corr enhances cross-correlation by long-range modeling and global searching of distant semantic features between template and search maps, benefiting the tracking under noise and artifacts by implicitly learning potential distant semantic cues. By combining with cross-map interleaved scan (CIS), local pixel-wise interaction with positional inductive bias can also be introduced to SSMX-Corr. The implicit low-level motion descriptor is proposed as a non-visual prompt to enhance tracking robustness, addressing the intermittent tip visibility problem. Extensive experiments on a dataset with motorized needle insertion in both phantom and tissue samples demonstrate that the proposed tracker outperforms other state-of-the-art trackers while ablation studies further highlight the effectiveness of each proposed tracking module.

Cholangioscopy is now widely performed in patients with pancreaticobiliary disorders, including difficult common bile duct (CBD) stones and indeterminate biliary strictures. Furthermore, an increasing number of rare pancreaticobiliary disorders have been identified by cholangioscopy when fluoroscopy fails to provide a definitive diagnosis [1] [2] [3] [4]. A 46-year-old woman was admitted for the treatment of a distal CBD stone, which cannot be identified under percutaneous cholangioscopy through the T-tube after laparoscopy cholecystectomy and CBD exploration. Fluoroscopy suggested an irregular stone in the distal CBD and choledochal cyst. Due to the unavailability of laser or electrohydraulic lithotripsy devices, the stone could not be captured with the retrieval basket under cholangioscopic guidance. Finally, following unsuccessful attempts with foreign body forceps, the CBD stone was successfully extracted using a standard retrieval basket under fluoroscopic guidance ([Fig. 1] a–c). While CBD stone clearance was confirmed on cholangioscopy, an intraductal protruding lesion with intensely hyperemic and irregular surface was observed near the biliary orifice. Additionally, multiple openings were noted near the biliary orifice, which were subsequently shown to be pancreatic duct orifices upon fluoroscopic-guided guidewire cannulation ([Fig. 2] a–d). Cholangioscopy-guided biopsy of the lesion revealed nonspecific inflammation on histology ([Video 1] and [Fig. 3]). Follow-up cholangioscopy after 9 months documented the complete resolution of the previously identified lesion near the biliary orifice, with no abnormal findings within the choledochal cyst ([Fig. 4]). In this patient, the anomalous junction of pancreaticobiliary ducts with concomitant pancreatic duct anomaly and choledochal cyst can be directly observed on cholangioscopy. These pathological changes resulted in choledocholithiasis and an intraductal inflammatory mass that regressed spontaneously after CBD stone removal. Given the malignant transformation potential of choledochal cysts [5], surgical resection was advised, but the patient declined the procedure. Endoscopy_UCTN_Code_TTT_1AR_2AB Article published online: 08 December 2025 © 2025. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/). Georg Thieme Verlag KG Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany