Introduction

EUS-guided gastroenterostomy (EUS-GE) is a novel and effective procedure for the management of malignant gastric outlet obstruction (GOO) with more durable results when compared to enteral stenting (ES). However, data comparing EUS-GE to ES in patients already treated with EUS-guided choledocoduodenostomy (EUS-CDS) for distal malignant biliary obstruction (DMBO) are lacking. We aimed to compare outcomes of EUS-GE and ES for the palliation of GOO in this specific population of patients.

Aims & Methods

A multicentre retrospective analysis of patients with DMBO treated by EUS-CDS and concomitant or subsequent GOO treated by EUS-GE or ES from 2016 to 2021 was conducted. Primary outcomes were overall AEs rate and dysfunction of the EUS-CDS after GOO treatment. Secondary outcomes included clinical success, technical success, procedure duration, length of hospital stay and relapse of GOO symptoms.

Results

77 consecutive patients were included in the study: 25 patients underwent EUS-GE and 52 underwent ES. AEs rate and patency outcomes of the EUS-CDS after GOO treatment were comparable between the two groups (12,5% vs 17,3 %; p=0,74). No recurrence of GOO symptoms was registered in the EUS-GE group while 11,5 % of ES patients had symptoms recurrence after a mean follow-up period of 93,5 days.

Conclusion

EUS-GE and ES are both effective and safe for the palliation of GOO in patients already treated by EUS-CDS for DMBO with no difference in the biliary stent dysfunction rate and overall AEs. EUS-GE is associated with less recurrence of GOO symptoms.

Introduction

There is a paucity of information on the efficacy and safety of endoscopic resection (ER) of gastric submucosal tumors (SMT) in Japan where ER for early gastric cancer is extremely popular.

Aims & Methods

A multicenter retrospective study was conducted to elucidate the current situation of ER for gastric SMT in Japanese endoscopic practice. Clinicopathological data of consecutive patients with gastric SMT who underwent ER in 12 Japanese hospitals were collected from the first case until August 2020.

Results

A total of 117 patients with 118 lesions were enrolled. The number of patients with gastric SMT who underwent ER increased over the years. The mean (SD) endoscopic tumor size was 20 (7.2) mm. The growth type was primarily intraluminal (90%). 87 (74%) of the procedures were performed in an operating room under general anesthesia. The tunneling method was used in 5 (4%) cases. The mean (SD) resection and wound closure times were 58 (38) min and 31 (41) min, respectively. Complete ER was achieved for 117 (99%) lesions. Full-thickness resection rate was 44%; however, only 12 (10%) patients required abdominal paracentesis for pneumoperitoneum. Endoscopic treatments were completed in 115 (97%) lesions, while three lesions required conversions to laparoscopic surgery due to luminal collapse, uncontrolled bleeding, and difficulty in defect closure. Two cases of delayed bleeding were managed by endoscopic hemostasis, one of which required a blood transfusion. Gastrointestinal stromal tumors were the most common pathology (74%). The R0 resection rate was 76%. Survival and recurrence on August 31, 2021, were confirmed in 112 patients (96%) with a mean (SD) follow-up period of 4.3 (2.9) years. 109 (94%) were confirmed alive, the vital status of five patients was unknown, and three patients had died of other diseases. No recurrence was observed. The 5-year overall survival rate was 98.9% (95% confidence interval, 97.8−100%).

Conclusion

The performance of ER for gastric SMT is increasing in Japan. The technique seems feasible in Japanese endoscopic practice, warranting further validation in a prospective study.

Introduction

Malignant gastric outlet obstruction (GOO) can arise from a spectrum of malignancies, including gastroduodenal, pancreaticobiliary, colorectal, breast, and lung cancers. Typically, GOO heralds a grim prognosis and manifests with symptoms such as nausea, bloating, vomiting, and abdominal pain. Presently, laparoscopic gastroenterostomy (L-GE) stands as the preferred therapeutic modality; however, endoscopic ultrasound-guided gastroenterostomy (EUS-GE) employing lumen apposing metal stents has emerged as a promising minimally invasive alternative. Comparative studies directly assessing the efficacy of EUS-GE versus L-GE remain scarce.

Aims & Methods

We aimed to compare EUS-GE with L-GE for the treatment of GOO using a propensity score-matched analysis.
In a retrospective, multicenter analysis, consecutive patients were enrolled between April 2019 and April 2024 from two academic centers and one primary care facility. To mitigate selection bias, propensity score matching was employed, taking into account factors such as underlying malignancy, tumor stage, and clinical performance status. Clinical success, defined as a reduction of gastric outlet obstruction (GOO) symptom scores by ≥1, served as the primary outcome measure. Secondary endpoints included technical success, time to oral intake, occurrence of adverse events (AEs), length of hospital stay, and 30-day mortality.

Results

A total of 94 patients underwent EUS-GE, while 78 patients underwent L-GE, as per initial screening. Propensity score matching resulted in 72 patients allocated to each group in a 1:1 ratio. The mean age of the study cohort was 68.2±12.3 years, with 59.7% being female. Clinical success rates were 90.2% for EUS-GE and 82.2% for L-GE (p=0.25). Technical success rates were 95.2% for EUS-GE and 100% for L-GE (p=0.06). The mean duration of hospital stay was significantly shorter for EUS-GE compared to L-GE (10.1±13.4 days vs. 15.5±10.5 days; p<0.001). Less AE were observed in the EUS-GE group compared to the L-GE group, both in total (4.8% vs. 22%; p=0.01) and in serious AE (1.6% vs. 6.7%; p=0.3). The 30-day mortality rate was 11.3% in the EUS-GE group and 17.8% in the L-GE group.

Conclusion

In patients presenting with malignant GOO, EUS-GE showed a tendency towards enhanced clinical success, although not statistically significant, while maintaining comparable technical success rates to L-GE. Notably, clinical recovery post-intervention and hospital stay duration were notably shorter in the EUS-GE cohort, accompanied by a significantly lower incidence of adverse events. Consequently, EUS-GE stands poised to emerge as a preferred therapeutic option for GOO. Nevertheless, further prospective, randomized trials are imperative to validate these retrospective findings.

Disclosure

ME, CG, TB, HN received consultation fees and study support from Boston Scientific, USA. The other authors have nothing to declare.

Introduction

Gastric ulcers can be categorized into malignant (ulcerative gastric cancer) and benign types. Although endoscopy with biopsy remains the gold standard for diagnosis and differentiation, it has limitations. Studies report a sensitivity of 92% and specificity of 84% for detecting malignant ulcers via endoscopy, yet approximately 5% of endoscopically diagnosed malignant ulcers are histologically confirmed as benign. Furthermore, biopsy rates among endoscopists vary widely (22.4%–52.9%), and increased biopsies often yield unnecessary negative results, burdening both patients and clinicians. While artificial intelligence (AI) has shown promise in assisting diagnosis, existing studies primarily focus on single-center, static image classification (normal mucosa, benign/malignant ulcers), which diverges from real-world clinical practice requiring dynamic, holistic lesion analysis.

Aims & Methods

We aimed to develop a deep learning-based model using multicenter data to enable real-time detection and classification of gastric ulcers during endoscopy, thereby improving diagnostic accuracy and guiding biopsy decisions. A total of 21,592 endoscopic images were retrospectively collected from three tertiary hospitals in China, including 1,424 images from 263 histologically confirmed malignant ulcers, 7,767 images from 1,470 benign ulcers, 1,490 normal mucosa images, and 10,911 frames extracted from 11 endoscopy videos. These were split into training, validation, and test sets (8:1:1 ratio). A real-time instance segmentation model was developed using the YOLOv8 architecture, with performance evaluated on the test set.

Results

For benign ulcers, the model achieved a precision, sensitivity, and specificity of 99.25% (95% CI: 98.70%–99.61%), 99.25% (95% CI: 98.70%–99.61%), and 94.07% (95% CI: 89.20%–97.27%), respectively. For malignant ulcers, precision, sensitivity, and specificity were 94.07% (95% CI: 89.20%–97.27%), 94.07% (95% CI: 89.20%–97.27%), and 99.25% (95% CI: 98.70%–99.61%), respectively. The overall precision for differentiating benign and malignant ulcers was 96.66% (95% CI: 97.91%–99.21%).

Conclusion

This multicenter study successfully developed an AI model based on an enhanced YOLOv8 architecture for real-time differentiation of benign and malignant gastric ulcers. The model demonstrates high diagnostic accuracy, offering potential to optimize endoscopic evaluations and biopsy protocols in clinical practice.

References

1.Dooley CP, Larson AW, Stace NH, et al. Double-contrast barium meal and upper gastrointestinal endoscopy. A comparative study. Ann Intern Med. 1984;101(4):538-545. doi:10.7326/0003-4819-101-4-538
2.Lv SX, Gan JH, Ma XG, et al. Biopsy from the base and edge of gastric ulcer healing or complete healing may lead to detection of gastric cancer earlier: an 8 years endoscopic follow-up study. Hepatogastroenterology. 2012;59(115):947-950. doi:10.5754/hge10692
3.Graham DY, Schwartz JT, Cain GD, Gyorkey F. Prospective evaluation of biopsy number in the diagnosis of esophageal and gastric carcinoma. Gastroenterology. 1982;82(2):228-231.
4.Januszewicz W, Wieszczy P, Bialek A, et al. Endoscopist biopsy rate as a quality indicator for outpatient gastroscopy: a multicenter cohort study with validation. Gastrointest Endosc. 2019;89(6):1141-1149. doi:10.1016/j.gie.2019.01.008
5.Namikawa K, Hirasawa T, Nakano K, et al. Artificial intelligence-based diagnostic system classifying gastric cancers and ulcers: comparison between the original and newly developed systems. Endoscopy. 2020;52(12):1077-1083. doi:10.1055/a-1194-8771
6.Liu Y, Zhang L, Hao Z, et al. An xception model based on residual attention mechanism for the classification of benign and malignant gastric ulcers. Sci Rep. 2022;12(1):15365. Published 2022 Sep 13. doi:10.1038/s41598-022-19639-x

Clinical Case Summary

A 56-year-old male presented with postprandial vomiting and weight loss beginning three weeks after laparoscopic ulcerorraphy of a perforated pyloric ulcer. An abdominal CT showed marked gastric distension and upper GI endoscopy revealed gastric stasis and a fibrotic stenosis in the duodenal bulb in close relation with a suture stitch, only transposable with an ultra-slim gastroscope. Two sessions of balloon dilation (BD) until 20mm were performed one month apart with poor clinical/endoscopic improvement. Endoscopic ultrasound-guided gastroenterostomy (EUS-GE) was proposed to avoid surgical reintervention.
Using a standard gastroscope a 0.035´´guidewire was passed into the proximal jejunum allowing insertion of a 7-french nasobiliary drain. Jejunal distension was achieved through saline, iodate contrast and methylene blue infusion. The linear echoendoscope was used to identify a distended loop adjacent to the gastric wall and EUS-guided puncture with a 19G needle was accomplished. A 20x10mm lumen-apposing metal stent (LAMS) was deployed in distal gastric body. The flow of blue mixture to the lumen confirmed successful gastroenterostomy creation. The patient was hospitalized overnight and resumed oral feeding the day after the procedure. No symptom recurrence was observed and the gastroenterostomy remained patent during the 6 months of follow-up.
Gastric outlet obstruction (GOO) may result from several malignant and benign causes. Surgical gastroenterostomy, self-expandable metal stents (SEMS) and BD are standard therapeutic options. EUS-GE is emerging as an effective and minimally invasive alternative. EUS-GE presents high technical and clinical success with lower rates of adverse events and reduced need of reintervention when compared to surgery and other endoscopic therapies. In benign GOO, SEMS seems less adequate and BD often results in suboptimal outcomes. The authors exemplify the effectiveness of EUS-GE in a case of GOO associated with a benign condition.

References

Illustrative material:
- Endoscopic and fluoroscopic images of guidewire and nasobiliary drain passed into the proximal jejunum
- EUS image of jejunal distension previous to LAMS placement
- EUS image of LAMS placement
- Endoscopic and fluoroscopic images of LAMS in situ
- Endoscopic image of 6 months follow-up