Sawas, T

AbstractBackground and study aims Endoscopic submucosal dissection (ESD) is technically challenging, difficult to learn, and carries a substantial risk of perforation, all of which remain significant barriers to its adoptability. We aimed to determine whether use of a novel scissor-type knife improved efficacy and safety among novice performers of ESD.Materials and methods Following a brief didactic session on ESD, participants performed ESD of two lesions (2 cm diameter) in an ex vivo porcine gastric model. One resection was performed with a conventional knife and the other with the scissor knife (order of knife randomized). We recorded procedure time, successful en bloc resection, and adverse events (including full-thickness perforation and muscle injury) for each dissection. Participants completed a post-study survey.Results 10 endoscopists (8 trainees, 2 staff) considered novices in ESD participated. Compared with the conventional knife, use of the scissor knife was associated with a significantly shorter time to completion of submucosal dissection (mean 6.2 [SD 5.6] vs. 15.6 [SD 15.6] minutes; P = 0.04) and total procedure time was not significantly different (22.1 [SD 13.3] vs. 24.9 [SD 26.5] minutes; P = 0.65). Scissor knife use was also associated with a significantly lower proportion of perforation and/or muscle injury (10.0 % vs. 70.0 %; P < 0.01) and proportion of muscle injury alone (10.0 % vs. 60.0 %; P = 0.02).Conclusions Among novices performing ESD on an ex vivo animal model, use of a scissor knife was associated with a significantly lower proportion of adverse events without prolonging procedure time. Scissor-type knives may improve ESD safety, at least among novices.

Objective The diagnosis of autoimmune pancreatitis (AIP) is challenging. Sonographic and cross-sectional imaging findings of AIP closely mimic pancreatic ductal adenocarcinoma (PDAC) and techniques for tissue sampling of AIP are suboptimal. These limitations often result in delayed or failed diagnosis, which negatively impact patient management and outcomes. This study aimed to create an endoscopic ultrasound (EUS)-based convolutional neural network (CNN) model trained to differentiate AIP from PDAC, chronic pancreatitis (CP) and normal pancreas (NP), with sufficient performance to analyse EUS video in real time. Design A database of still image and video data obtained from EUS examinations of cases of AIP, PDAC, CP and NP was used to develop a CNN. Occlusion heatmap analysis was used to identify sonographic features the CNN valued when differentiating AIP from PDAC. Results From 583 patients (146 AIP, 292 PDAC, 72 CP and 73 NP), a total of 1 174 461 unique EUS images were extracted. For video data, the CNN processed 955 EUS frames per second and was: 99% sensitive, 98% specific for distinguishing AIP from NP; 94% sensitive, 71% specific for distinguishing AIP from CP; 90% sensitive, 93% specific for distinguishing AIP from PDAC; and 90% sensitive, 85% specific for distinguishing AIP from all studied conditions (ie, PDAC, CP and NP). Conclusion The developed EUS-CNN model accurately differentiated AIP from PDAC and benign pancreatic conditions, thereby offering the capability of earlier and more accurate diagnosis. Use of this model offers the potential for more timely and appropriate patient care and improved outcome.

SummaryBackgroundCurrent management of refractory benign oesophageal strictures with endoscopic dilations and stenting leads to resolution of dysphagia in only 30% of patients. Oesophageal self‐dilation may be an alternative.AimTo evaluate the efficacy and safety of oesophageal self‐dilation at a tertiary referral centre.MethodsWe conducted a retrospective review of patients with refractory benign oesophageal strictures who participated in oesophageal self‐dilation at Mayo Clinic (Rochester, MN, USA) between 2003 and 2017. Clinical data including stricture characteristics, Dakkak and Bennett Dysphagia Score, number and dates of endoscopies, and complications were collected. A two‐tailed paired Student's t test was used to compare the measures of efficacy, with differences considered significant at a 5% probability level.ResultsWe identified 52 patients with refractory strictures treated with self‐dilation. The median number of endoscopic interventions was reduced from 9.5 (range 5‐30) to 0 (range 0‐3) within 12 months before and after self‐dilation, respectively (P < 0.0001). A median intervention‐free interval of 417 days (IQR 256‐756 days) was observed. The mean dysphagia score at baseline was 2.5 (95% CI 2.2‐2.8) and 0.33 (95% CI 0.11‐0.53) after self‐dilation. 23 of 27 (85%) patients who received enteral nutrition prior to self‐dilation had their feeding tubes removed.ConclusionsOesophageal self‐dilation is an effective way of maintaining oesophageal patency in refractory benign oesophageal strictures, with safety comparable to current standard of care. Prospective studies are needed to further validate the role of self‐dilation in treatment of refractory benign oesophageal strictures.