Background and aim: Optical diagnosis (OD) of colonic polyps is poorly reproducible outside high-volume referral centres. Present study aimed to assess whether real-time AI-assisted OD is accurate enough to implement the leave-in-situ strategy for diminutive (5mm) rectosigmoid (DRSPs) polyps. Methods: Consecutive colonoscopy outpatients with 5mm) rectosigmoid (DRSPs) polyps. Methods: Consecutive colonoscopy outpatients with >1 DRSP were included. DRSPs were categorized as adenomas or non-adenomas by the endoscopist, with different expertise in OD, with the assistance of real-time AI system (CADEYE, Fujifilm Co., Tokyo-Japan). Primary study endpoint was >90% negative predictive value (NPV) for adenomatous histology in high-confidence AI-assisted OD of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations (PIVI-1) threshold), with histopathology as reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (>90%, PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines. Results: Overall 596 DRSPs were retrieved for histology in 389 patients; AI-assisted high-confidence OD was made in 92.3%. The NPV of AI-assisted OD for DRSPs (PIVI-1) was 91.0% (95%CI [87.1-93.9]%). PIVI-2 threshold was met in 97.4% (95%CI [95.7-98.9]%) and 92.6% (95%CI [90.0-95.2]%) of patients according to ESGE and USMSTF, respectively. The AI-assisted OD accuracy was significantly lower for non-experts (82.3%; 95% CI [76.4-87.3]%) than for experts (91.9%; 95%CI [88.5-94.5]%), however non-experts in OD quickly approached experts’ performances over time. Conclusion: AI-assisted OD matches the required PIVI thresholds. However, this does not offset the need for a high-level confidence and expertise by the endoscopist. The AI system seems to be useful especially for non-experts.

No abstract

Background and aim: Computer-Aided Detection (CADe) increases adenoma detection in primary screening colonoscopy. The potential benefit of CADe in a fecal immunochemical test (FIT)-based colorectal cancer (CRC) screening programs is lacking. This study assesses whether the use of CADe increases the Adenoma Detection Rate (ADR) in FIT-based CRC screening program. Patients and methods: In a multicenter, randomized trial, 50-74 years old FIT-positive subjects undergoing colonoscopy, were randomized (1:1) to receive high-definition white light (HDWL) colonoscopy, with or without a real-time deep-learning CADe (CADEYE Fujifilm Co., Tokyo, Japan) by endoscopists with baseline ADR>25%. Main outcomes were ADR (primary outcome), mean number (SD) of adenomas per colonoscopy (APC) and advanced adenoma detection rate (Advanced-ADR). Subgroup analysis according to baseline endoscopists’ ADR (group 1: <40%, group 2: 41-45%, group 3 >46%) was also performed. Results: Eight hundred subjects (median age: 61.0 years, IQR: 55-67; 409 men) were included: 405 underwent CADe-assisted and 395 HDWL colonoscopy, respectively. ADR and APC were significantly higher in the CADe than in the HDWL arm: ADR: 53.6%; 95%CI: [48.6-58.5%] vs. 45.3%; 95%CI [40.3-50.45] (RR: 1.180; 95%CI: [1.026-1.361]); APC: 1.13 (1.54) vs. 0.90 (1.32), p=0.028. No significant difference in advanced-ADR (18.5%; 95%CI [14.8-22.6%] vs. 15.9%; 95%CI [12.5-19.9%]) was found. An increase in ADR was observed in all endoscopists' groups regardless of baseline ADR. Conclusions: Incorporating CADe significantly increases ADR and APC in the framework of a FIT-based CRC screening program. The impact of CADe appears to be consistent regardless of the endoscopist baseline ADR.

Gastric outlet obstruction (GOO) is a clinical syndrome characterized by postprandial vomiting, abdominal pain, bloating and, in advanced cases, by weight loss secondary to inadequate oral intake. This clinical entity may be caused by mechanical obstruction, either benign or malignant, or by motility disorders. In this review we will focus on malignant GOO and on its endoscopic ultrasound (EUS)-guided palliative treatment. The most frequent malignant causes of this syndrome are gastric and locally advanced pancreatic carcinomas; other causes include duodenal or ampullary neoplasms, gastric lymphomas, retroperitoneal lymphadenopathies and, more infrequently, gallbladder and bile duct cancers. Surgery represents the treatment of choice when radical and curative resection is potentially feasible; if the malignant cause is not likely to be completely resected, palliative treatments should be proposed. Palliative treatments for malignant GOO are primarily based on surgical gastro-jejunostomy and endoscopic placement of an enteral self-expanding metal stent. Both treatments are effective; however, endoscopic stent placement is less invasive and it is associated with good short-term results, while surgery provides longer-lasting effects with a lower frequency of reintervention. In the last few years, EUS-guided gastroenterostomy (GE) has been proposed as palliative treatment for malignant GOO. This novel technique consists of the creation of an anastomosis between the gastric lumen and a small bowel loop distal to the malignant obstruction, through the deployment of a lumen-apposing metal stent under EUS-view. EUS-GE has the advantage of being as minimally invasive as enteral stent placement, and of guaranteeing long-term results similar to those of surgery.

The differential diagnosis between benign and malignant lymph nodes (LNs) has a fundamental role in the characterization and staging of malignant conditions, as well as in subsequent patients’ management. All imaging modalities ( i.e. computed tomography and magnetic resonance imaging) rely mainly on size; endoscopic ultrasound (EUS) criteria based on B-mode evaluation and Doppler features fail to adequately characterize with high specificity LNs nature. The introduction of EUS-elastography and contrast-enhanced harmonic EUS are useful techniques to increase the diagnostic yield in identifying metastatic LNs, to identify which suspicious LN should require pathological characterization and, finally, to target tissue acquisition. EUS-guided tissue acquisition (EUS-TA) is increasingly being used for diagnosing lymphadenopathy whenever the characterization modifies patients’ subsequent management and when no superficial LN is accessible. Since target therapy are currently available ( i.e. lung cancer, breast cancer), EUS-TA of malignant LNs could be required to identify tumor biology. In this field, both fine needle aspiration and biopsy needles are able to guarantee accurate results with almost perfect specificity and sub-optimal sensitivity. We finally propose a diagnostic algorithm based on most recent, high-level evidence for the diagnostic approach to suspected LNs assessment.