Background: Endoscopic Ultrasound (EUS) is widely used for the diagnosis of bilio-pancreatic and gastrointestinal (GI) tract diseases, for the evaluation of subepithelial lesions, and for sampling of lymph nodes and solid masses located next to the GI tract. The role of Artificial Intelligence in healthcare in growing. This review aimed to provide an overview of the current state of AI in EUS from imaging to pathological diagnosis and training. Methods: AI algorithms can assist in lesion detection and characterization in EUS by analyzing EUS images and identifying suspicious areas that may require further clinical evaluation or biopsy sampling. Deep learning techniques, such as convolutional neural networks (CNNs), have shown great potential for tumor identification and subepithelial lesion (SEL) evaluation by extracting important features from EUS images and using them to classify or segment the images. Results: AI models with new features can increase the accuracy of diagnoses, provide faster diagnoses, identify subtle differences in disease presentation that may be missed by human eyes, and provide more information and insights into disease pathology. Conclusions: The integration of AI in EUS images and biopsies has the potential to improve the diagnostic accuracy, leading to better patient outcomes and to a reduction in repeated procedures in case of non-diagnostic biopsies.

The advent of immunotherapy, specifically of immune checkpoint inhibitors (ICIs), for the treatment of solid tumors has deeply transformed therapeutic algorithms in medical oncology. Approximately one-third of patients treated with ICIs may de velop immune-related adverse events, and the gastrointestinal tract is often affected by different grades of mucosal inflammation. Checkpoint inhibitors colitis (CIC) presents with watery or bloody diarrhea and, in the case of severe symptoms, requires ICIs discontinuation. The pathogenesis of CIC is multifactorial and still partially unknown: anti-tumor activity that collaterally effects the colonic tissue and the upregulation of specific systemic inflammatory pathways (i.e., CD8+ cytotoxic and CD4+ T lymphocytes) are mainly involved. Many questions remain regarding treatment timing and options, and biological treatment, especially with anti-TNF alpha, can be offered to these patients with the aim of rapidly resuming oncological therapies. CIC shares similar pathogenesis and aspects with inflammatory bowel disease (IBD) and the use of ICI in IBD patients is under evaluation. This review aims to summarize the pathogenetic mechanism underlying CIC and to discuss the current evidenced-based management options, including the role of biological therapy, emphasizing the relevant clinical impact on CIC and the need for prompt recognition and treatment.

The identification of advanced fibrosis by applying noninvasive tests is still a key component of the diagnostic algorithm of NAFLD. The aim of this study is to assess the concordance between the FIB-4 and liver stiffness measurement (LSM) in patients referred to two liver centers for the ultrasound-based diagnosis of NAFLD. Fibrosis 4 Index for Liver Fibrosis (FIB-4) and LSM were assessed in 1338 patients. A total of 428 (32%) had an LSM ≥ 8 kPa, whereas 699 (52%) and 113 (9%) patients had an FIB-4 < 1.3 and >3.25, respectively. Among 699 patients with an FIB-4 < 1.3, 118 (17%) had an LSM ≥ 8 kPa (false-negative FIB-4). This proportion was higher in patients ≥60 years, with diabetes mellitus (DM), arterial hypertension or a body mass index (BMI) ≥ 27 kg/m². In multiple adjusted models, age ≥ 60 years (odds ratio (OR) = 1.96, 95% confidence interval (CI) 1.19–3.23)), DM (OR = 2.59, 95% CI 1.63–4.13), body mass index (BMI) ≥ 27 kg/m² (OR = 2.17, 95% CI 1.33–3.56) and gamma-glutamyltransferase ≥ 25 UI/L (OR = 2.68, 95% CI 1.49–4.84) were associated with false-negative FIB-4. The proportion of false-negative FIB-4 was 6% in patients with none or one of these risk factors and increased to 16, 31 and 46% among those with two, three and four concomitant risk factors, respectively. FIB-4 is suboptimal to identify patients to refer to liver centers, because about one-fifth may be false negative at FIB-4, having instead an LSM ≥ 8 KPa.

Gastrojejunostomy is the principal method of palliation for unresectable malignant gastric outlet obstructions (GOO). Gastrojejunostomy was traditionally performed as a surgical procedure with an open approach butrecently, notable progress in the development of minimally invasive procedures such as laparoscopic gastrojejunostomies have emerged. Additionally, advancements in endoscopic techniques, including endoscopic stenting (ES) and endoscopic ultrasound-guided gastroenterostomy (EUS-GE), are becoming more prominent. ES involves the placement of self-expandable metal stents (SEMS) to restore luminal patency. ES is commonly the first choice for patients deemed unfit for surgery or at high surgical risk. However, although ES leads to rapid improvement of symptoms, it carries limitations like higher stent dysfunction rates and the need for frequent re-interventions. Recently, EUS-GE has emerged as a potential alternative, combining the minimally invasive nature of the endoscopic approach with the long-lasting effects of a gastrojejunostomy. Having reviewed the advantages and disadvantages of these different techniques, this article aims to provide a comprehensive review regarding the management of unresectable malignant GOO.

Many tumors may secondarily involve the pancreas; however, only retrospective autopic and surgical series are available. We retrospectively collected data from all consecutive patients with histologically confirmed secondary tumors of the pancreas referred to five Italian centers between 2010 and 2021. We described clinical and pathological features, therapeutic approach and treatment outcomes. EUS characteristics of the lesions and the tissue acquisition procedures (needle, passages, histology) were recorded. A total of 116 patients (males/females 69/47; mean age 66.7) with 236 histologically confirmed pancreatic metastases were included; kidney was the most common primary site. EUS was performed to confirm the diagnosis in 205 lesions which presented as predominantly solitary (59), hypoechoic (95) and hypervascular (60), with a heterogeneous (n = 54) pattern and well-defined borders (n = 52). EUS-guided tissue acquisition was performed in 94 patients with an overall accuracy of 97.9%. Histological evaluation was possible in 88.3% of patients, obtaining final diagnosis in all cases. When cytology alone was performed, the final diagnosis was obtained in 83.3% of cases. A total of 67 patients underwent chemo/radiation therapy, and surgery was attempted in 45 (38.8%) patients. Pancreatic metastases are a possible event in the natural history of solid tumors, even long after the diagnosis of the primary site. EUS-guided fine needle biopsy may be suggested to implement the differential diagnosis.

Background: Endoscopic Ultrasound (EUS) is widely used for the diagnosis of bilio-pancreatic and gastrointestinal (GI) tract diseases, for the evaluation of subepithelial lesions, and for sampling of lymph nodes and solid masses lo-cated next to the GI tract. The role of Artificial Intelligence in healthcare in growing. This review aimed to provide an overview of the current state of AI in EUS from imaging to pathological diagnosis and training. Methods: AI algorithms can assist in lesion detection and characterization in EUS by analysing EUS images and identifying suspicious areas that may require further clinical evaluation or biopsy sampling. Deep learning tech-niques, such as convolutional neural networks (CNNs), have shown great potential for tumour identification and subepithelial lesion (SEL) evaluation by extracting important features from EUS images and using them to classify or segment the images. Results: AI models with new features can increase the accuracy of diagnoses, provide faster diagnoses, identify subtle differences in disease presentation that may be missed by human eyes, and provide more information and in-sights into disease pathology. Conclusions: The integration of AI in EUS images and biopsies has the potential to improve the diagnostic accura-cy, leading to better patient outcomes and to a reduction of repeated procedures in case of non-diagnostic biopsies.