Faculty Bibliography

BACKGROUND:EUS-guided gastroenterostomy (EUS-GE) is a minimally invasive therapy for the management of gastric outlet obstruction (GOO). EUS-GE has demonstrated excellent short-term efficacy without the risks of surgical bypass. However, there is limited data on follow-up outcomes. In this study, we collected 6-month follow-up data on patients who underwent EUS-GE for benign and malignant etiologies, to aim to show the shift in paradigm in their management algorithm. METHODS:This was a retrospective multicenter study across 7 international centers of consecutive patients undergoing EUS-GE over a 4-year period who were entered in a dedicated registry. Demographic characteristics, procedure-related information, and follow-up data were collected. Primary outcome was the 6-month data on clinical resolution of GOO. RESULTS:Ninety-one patients were included (71 malignant and 20 benign cases). Technical success was 99% due to high expertise and volume. Clinical success at 48 hours was 97% (88/90) with an average procedure time of 47 minutes and length of stay of 5.86 days. At 3 months, 87 (95.6%) patients had achieved clinical resolution. At 6 months, 48 (53%) subjects were alive, 40 (44%) were deceased, 3 were lost to follow-up (3.3%) and 1 (1%) had a recurrence of GOO. Clinical success at 6 months follow-up was 98% (47/48). CONCLUSIONS:The majority of patients with GOO who undergo EUS-GE showed clinical resolution at 6-month follow-up. Patients with malignant etiology are appropriately palliated during their life span. Further prospective studies are necessary to obtain long-term data regarding EUS-GE for benign etiologies.

Diagnosing and characterizing biliary strictures (BS) remains challenging. Artificial intelligence (AI) applied to digital single-operator cholangioscopy (D-SOC) holds promise for improving diagnostic accuracy in indeterminate BS. This multicenter study aimed to validate a convolutional neural network (CNN) model using a large dataset of D-SOC images to automatically detect and characterize malignant BS. D-SOC exams from three centers-Centro Hospitalar Universitário de São João, Porto, Portugal (n = 123), Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Spain (n = 18), and New York University Langone Hospital, New York, USA (n = 23)-were included. Frames were categorized based on histopathology. The CNN's performance in detecting tumor vessels, papillary projections, nodules, and masses was assessed. The dataset was split into 90% training and 10% validation sets. Performance metrics included AUC, sensitivity, specificity, PPV, and NPV. Analysis of 96,020 images from 164 D-SOC exams (50,427 malignant strictures and 45,593 benign findings) showed the CNN achieved 92.9% accuracy, 91.7% sensitivity, 94.4% specificity, 95.1% PPV, 93.1% NPV, and an AUROC of 0.95. Accuracy rates for morphological features were 90.8% (papillary projections), 93.6% (nodules), 93.2% (masses), and 78.1% (tumor vessels). AI-driven CNN models hold promise for enhancing diagnostic accuracy in suspected biliary malignancies. This multicenter study contributes diverse datasets to ongoing research, supporting further AI applications in this patient population.

Gastric outlet obstruction (GOO) occurs due to anatomic blockage of the stomach or duodenum. GOO typically manifests with symptoms such as early satiety, nausea, vomiting, and weight loss, due to either underlying benign or malignant causes. Historically, the gold standard for managing GOO has been surgical gastrojejunostomy. However, this approach comes with considerable drawbacks including prolonged recovery times and the necessity for suitable surgical candidates. Endoscopically placed self-expanding metal stents emerged as a notable advancement in palliating symptoms associated with GOO. However, their long-term efficacy is hindered by the frequent occurrence of stent occlusion, necessitating the need for further intervention. Most recently, endoscopic ultrasound guided gastroenterostomy (EUS-GE) using lumen-apposing metal stents has been described with promising technical and clinical success rates. The advent of EUS-GE heralds a significant stride forward in the management of GOO, offering a less invasive yet effective alternative to conventional surgical approaches. EUS-GE has been associated with lower adverse events as compared with surgical gastrojejunostomy and lower recurrence and reintervention rates compared with enteral stenting. The advent of EUS-GE heralds a significant stride forward in the management of GOO, offering a less invasive yet effective alternative to conventional surgical approaches. EUS-GE is a promising evolving technique for treating GOO, and ongoing studies are necessary to validate its use in both benign and malignant GOO.

INTRODUCTION/BACKGROUND:Endoscopic ultrasound (EUS) allows for characterization and biopsy of pancreatic lesions. Pancreatic cystic neoplasms (PCN) include mucinous (M-PCN) and nonmucinous lesions (NM-PCN). Pancreatic ductal adenocarcinoma (P-DAC) is the commonest pancreatic solid lesion (PSL), followed by pancreatic neuroendocrine tumor (P-NET). Although EUS is preferred for pancreatic lesion evaluation, its diagnostic accuracy is suboptimal. This multicentric study aims to develop a convolutional neural network (CNN) for detecting and distinguishing PCN (namely M-PCN and NM-PCN) and PSL (particularly P-DAC and P-NET). METHODS:A CNN was developed with 378 EUS examinations from 4 international reference centers (Centro Hospitalar Universitário São João, Hospital Universitario Puerta de Hierro Majadahonda, New York University Hospitals, Hospital das Clínicas Faculdade de Medicina da Universidade de São Paulo). About 126.000 images were obtained-19.528 M-PCN, 8.175 NM-PCN, 64.286 P-DAC, 29.153 P-NET, and 4.858 normal pancreas images. A trinary CNN differentiated normal pancreas tissue from M-PCN and NM-PCN. A binary CNN distinguished P-DAC from P-NET. The total data set was divided into a training and testing data set (used for model's evaluation) in a 90/10% ratio. The model was evaluated through its sensitivity, specificity, positive and negative predictive values, and accuracy. RESULTS:The CNN had 99.1% accuracy for identifying normal pancreatic tissue, 99.0% and 99.8% for M-PCN and NM-PCN, respectively. P-DAC and P-NET were distinguished with 94.0% accuracy. DISCUSSION/CONCLUSIONS:Our group developed the first worldwide CNN capable of detecting and differentiating the commonest PCN and PSL in EUS images, using examinations from 4 centers in 2 continents, minimizing the impact of the demographic bias. Larger multicentric studies are needed for technology implementation.

BACKGROUND/UNASSIGNED:Neoadjuvant therapy (NAT) is increasingly being used for pancreatic ductal adenocarcinoma (PDAC) treatment. However, its specific effects on carcinoma cells and the tumor microenvironment (TME) are not fully understood. This study aims to investigate how NAT differentially impacts PDAC's carcinoma cells and TME. METHODS/UNASSIGNED:Spatial transcriptomics was used to compare gene expression profiles in carcinoma cells and the TME between 23 NAT-treated and 13 NAT-naïve PDAC patients, correlating with their clinicopathologic features. Analysis of an online single-nucleus RNA sequencing (snRNA-seq) dataset was performed for validation of the specific cell types responsible for NAT-induced gene expression alterations. RESULTS/UNASSIGNED:T cells, monocytes, and mast cells; and reduced immune exhaustion gene expression. snRNA-seq analysis demonstrates C3 complement was specifically upregulated in CAFs but not in other stroma cell types. CONCLUSIONS/UNASSIGNED:NAT can enhance complement production and signaling within the TME, which is associated with reduced immunosuppression in PDAC. These findings suggest that local complement dynamics could serve as a novel biomarker for prognosis, evaluating treatment response and resistance, and guiding therapeutic strategies in NAT-treated PDAC patients.

BACKGROUND AND AIMS/OBJECTIVE:Digital single-operator cholangioscopy (DSOC) allows direct visualization of the biliary tree for evaluation of biliary strictures. Our objective was to assess the interobserver agreement (IOA) of DSOC interpretation for indeterminate biliary strictures using newly refined criteria. METHODS:Fourteen endoscopists were asked to review an atlas of reference clips and images of 5 criteria derived from expert consensus. They then proceeded to score 50 deidentified DSOC video clips based on the visualization of tortuous and dilated vessels, irregular nodulations, raised intraductal lesions, irregular surface with or without ulcerations, and friability. The endoscopists then diagnosed the clips as neoplastic or non-neoplastic. Intraclass correlation (ICC) analysis was done to evaluate inter-rater agreement for both criteria sets and final diagnosis. RESULTS:Clips of 41 malignant lesions and 9 benign lesions were scored. Three of 5 revised criteria had almost perfect agreement. ICC was almost perfect for presence of tortuous and dilated vessels (.86), raised intraductal lesions (.90), and presence of friability (.83); substantial agreement for presence of irregular nodulations (.71); and moderate agreement for presence of irregular surface with or without ulcerations (.44). The diagnostic ICC was almost perfect for neoplastic (.90) and non-neoplastic (.90) diagnoses. The overall diagnostic accuracy using the revised criteria was 77%, ranging from 64% to 88%. CONCLUSIONS:The IOA and accuracy rate of DSOC using the new Mendoza criteria shows a significant increase of 16% and 20% compared with previous criteria. The reference atlas helps with formal training and may improve diagnostic accuracy. (Clinical trial registration number: NCT02166099.).

Pancreatic fluid collections (PFCs) are frequent complications in severe acute pancreatitis that are the result of damage to the pancreas to include but not limited to trauma, surgery, autoimmune diseases, alcohol abuse, infections, medications, gallstones, metabolic disorders, and premalignant or malignant conditions. The majority of these collections resolve spontaneously; however, if the collection is infected or causes symptoms to include abdominal pain, nausea, vomiting, diarrhea, fevers, and tachycardia, drainage is indicated. Drainage of PFCs can be accomplished surgically, percutaneously, or endoscopically and should be approached in a multidisciplinary fashion for best overall patient care and outcomes. Before the introduction of endoscopic procedures, surgical and percutaneous drainage was the preferred modality. Today a minimally-invasive "step-up" approach is generally accepted depending upon the specific characteristics of the PFC and clinical presentation. Endoscopic ultrasound-guided PFC drainage is favored due to high success rates, shorter hospital stays, and lower cost. Direct debridement of walled-off pancreatitis can now be performed endoscopically with higher success rates with larger caliber fully covered metal stents. At large, the field of endoscopic techniques has evolved, and more specifically, the management of PFCs continues to evolve with increasing experience and with the advent of new stents and accessories, leading to increased efficacy with less adverse events.