Can endoscopic ultrasound-guided needle-based confocal laser endomicroscopy replace fine-needle aspiration for pancreatic and mediastinal diseases?

Gastrointestinal Tract Polyp Anomaly Segmentation on Colonoscopy Images Using Graft-U-Net

Computer-aided polyp segmentation is a crucial task that supports gastroenterologists in examining and resecting anomalous tissue in the gastrointestinal tract. The disease polyps grow mainly in the colorectal area of the gastrointestinal tract and in the mucous membrane, which has protrusions of micro-abnormal tissue that increase the risk of incurable diseases such as cancer. So, the early examination of polyps can decrease the chance of the polyps growing into cancer, such as adenomas, which can change into cancer. Deep learning-based diagnostic systems play a vital role in diagnosing diseases in the early stages. A deep learning method, Graft-U-Net, is proposed to segment polyps using colonoscopy frames. Graft-U-Net is a modified version of UNet, which comprises three stages, including the preprocessing, encoder, and decoder stages. The preprocessing technique is used to improve the contrast of the colonoscopy frames. Graft-U-Net comprises encoder and decoder blocks where the encoder analyzes features, while the decoder performs the features’ synthesizing processes. The Graft-U-Net model offers better segmentation results than existing deep learning models. The experiments were conducted using two open-access datasets, Kvasir-SEG and CVC-ClinicDB. The datasets were prepared from the large bowel of the gastrointestinal tract by performing a colonoscopy procedure. The anticipated model outperforms in terms of its mean Dice of 96.61% and mean Intersection over Union (mIoU) of 82.45% with the Kvasir-SEG dataset. Similarly, with the CVC-ClinicDB dataset, the method achieved a mean Dice of 89.95% and an mIoU of 81.38%.

Single-step endoscopic ultrasound-guided multiple gateway drainage of complex walled-off necrosis with lumen apposing metal stents

In this study we analyzed the feasibility and safety of single-step multiple transluminal gateway drainage (MTGD) for complex walled-off necrosis (WON) using lumen-apposing metal stents (LAMSs). Six patients underwent endoscopic ultrasound (EUS)-guided MTGD using two LAMSs. Technical success was 100%. The mean procedure time was 29 min. The mean number of direct endoscopic necrosectomy sessions per patient was 2. Two of six patients developed adverse events, which was bleeding in both cases and treated endoscopically and surgically, respectively. The mean hospital stay was 52.5 days. No patients had residual necrosis or WON recurrence. Although the limited number of patients, the single-step MTGD using electrocautery-LAMSs can be considered a feasible and well-tolerated treatment option for patients with complex WON. Nevertheless, larger randomized controlled studies are needed in order to confirm our data and better define the advantages of this technique.

Needle-based confocal laser endomicroscopy in pancreatic cysts: a meta-analysis

There is currently limited evidence supporting the use of needle-based confocal laser endomicroscopy in pancreatic cystic lesions. Aim of this study was to provide a pooled estimate of the diagnostic performance and safety profile of this technique in patients with pancreatic cysts. Computerized bibliographic search on the main databases was performed through November 2019. Pooled effects were calculated using a random-effects model by means of DerSimonian and Laird test. Primary endpoint was diagnostic accuracy. Secondary outcomes were pooled sensitivity, specificity, and mean procedural time. Ten studies enrolling 536 patients were included. Eight articles, of which five prospective series, compared confocal laser endomicroscopy to cytology/cystic fluid analysis. Most patients were female and body/tail was the most frequent location of pancreatic cysts. Mucinous cysts were prevalent in most of the included studies. Diagnostic accuracy with confocal laser endomicroscopy was 88.6% (83.7-93.4%) and sensitivity analysis according to study quality, design, and treatment arms confirmed the above reported result. Pooled sensitivity and specificity were 82.4% (74.7-90.1%) and 96.6% (94.3-99%), respectively. Both accuracy and sensitivity resulted higher in patients with mucinous cysts (91.4 and 94.9%, respectively). Confocal laser endomicroscopy clearly outperformed fine-needle aspiration in terms of diagnostic accuracy (odds ratio 3.94, 1.58-9.82; P = 0.003). A mean of 6.094 minutes (4.91-7.26) was needed to complete the procedure and no significant adverse event was registered. Our meta-analysis speaks in favor of the use of needle-based confocal laser endomicroscopy as a safe and effective tool in the diagnostic algorithm of pancreatic cysts.

Long-term assessment of over-the-scope clip (OTSC) behavior after gastric application

Background: The aim of this study was to assess the long-term behavior of the over-the-scope clip (OTSC) after gastric application.Material and methods: A database of all patients who had OTSC placement with regular follow-up at a tertiary hospital between November 2013 and September 2016 was retrospectively analyzed. The incidence, time, and related adverse events of clip attachment and detachment were recorded. The relationship between the position of the clip and detachment was assessed by Fisher's exact test.Results: Seventy-two patients who had gastric OTSC placement due to iatrogenic perforations by endoscopic interventions were included in the study. The overall incidence of clip detachment was 27.8% (20/72). Fisher's exact test confirmed a significant association between clip detachment rate and clip position (p = .005): cardia 50% (3/6); gastric fundus 13.2% (5/38); gastric body 75% (9/16); and gastric antrum 25% (3/12). Except for one patient (5%; 1/20) who experienced minor gastric hemorrhage, there were no complications related to spontaneous clip detachment. There was no delayed bleeding, perforation, or obstruction due to clips staying in place in the long-term.Conclusions: Long-term gastric clip attachment appears to be safe even if spontaneous detachment occurs.

A quarter century of EUS-FNA: Progress, milestones, and future directions

Tissue acquisition using EUS has considerably evolved since the first EUS-FNA was reported 25 years ago. Its introduction was an important breakthrough in the endoscopic field. EUS-FNA has now become a part of the diagnostic and staging algorithm for the evaluation of benign and malignant diseases of the gastrointestinal tract and of the organs in its proximity, including lung diseases. This review aims to present the history of EUS-FNA development and to provide a perspective on the recent developments in procedural techniques and needle technologies that have significantly extended the role of EUS and its clinical applications. There is a bright future ahead for EUS-FNA in the years to come as extensive research is conducted in this field and various technologies are continuously implemented into clinical practice.