Background/Aims Radiation exposure during fluoroscopic procedures poses risks to both patients and medical staff. Although various protocols exist to mitigate these risks, the optimal pulse rate settings for radiation reduction remain unclear. This study aimed to evaluate the effectiveness of super low-rate pulsed fluoroscopy in reducing radiation dose during endoscopic retrograde cholangiopancreatography (ERCP) for common bile duct stone removal. Methods We retrospectively analyzed consecutive patients with common bile duct stones who underwent ERCP. Patient selection was based on two distinct time eras: procedures performed with pulsed fluoroscopy at 7.5 pulses per second (pps, standard-rate group) and 1.0 pps (super low-rate group) at a single center. The primary outcome was air kerma at the patient entrance reference point (Ka,r;mGy), and treatment-related indicators were analyzed. Results A total of 173 cases were analyzed (91 in the standard-rate group and 82 cases in the super low-rate group). The median value of Ka,r per procedure was significantly lower in the super low-rate group than in the standard-rate group (2.13 mGy vs 7.80 mGy). No significant differences were observed between groups in fluoroscopy time, procedure time, procedure success rate or adverse events. Multivariable regression analysis revealed that the super low pulse rate was associated with an 11.9 mGy dose reduction. Conclusions Using super low-rate pulsed fluoroscopy at 1.0 pps during ERCP was associated with significantly lower radiation exposure, with no observed deterioration in short-term procedural outcomes.
Bariatric surgery is an effective treatment for obesity; however, it remains among the more invasive therapeutic options and is associated with both short- and long-term complications. Given the increased risks associated with repeat surgical interventions, minimally invasive approaches are generally preferred for the management of post-bariatric complications. Consequently, endoscopy has emerged as a valuable tool for the diagnosis and treatment of a broad spectrum of post-bariatric gastrointestinal complications, including ulceration, stenosis, gallstone disease, leaks, fistulas, and recurrent weight gain. This article reviews the current role of endoscopy in the management of complications following bariatric surgery.
Artificial intelligence (AI)-assisted diagnosis of early neoplasia in Barrett’s esophagus (BE) now operates in real time during endoscopy, a step from the offline, patch-based image analysis that dominated earlier work. Three problems still limit its use in routine practice. The most physically detailed imaging methods, such as volumetric laser endomicroscopy, remain too slow and expensive for everyday use, while lightweight white-light systems that are easy to deploy generate frequent false-positive alerts. Most existing models depend on pixel-level annotation, an approach that is difficult to scale; weakly supervised attention methods have reduced this burden in histopathology but have not been tested on endoscopic video or on flat, poorly defined lesions. And little is known about how interface design, operator experience, and diagnostic uncertainty jointly shape real-time decisions between clinicians and AI systems. This review reconstructs how AI-assisted BE diagnosis evolved and examines the three gaps in turn. It closes with three directions: a performance–accessibility index applicable across imaging modalities, self-supervised and weakly supervised learning adapted to endoscopic video, and validation frameworks that bring human factors research alongside diagnostic accuracy.
