Endoscopic ultrasound (EUS) morphology can aid in the discrimination between mucinous and non-mucinous pancreatic cystic lesions (PCLs) but has several limitations that can be overcome by artificial intelligence. We developed a convolutional neural network (CNN) algorithm for the automatic diagnosis of mucinous PCLs. Images retrieved from videos of EUS examinations for PCL characterization were used for the development, training, and validation of a CNN for mucinous cyst diagnosis. The performance of the CNN was measured calculating the area under the receiving operator characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values. A total of 5505 images from 28 pancreatic cysts were used (3725 from mucinous lesions and 1780 from non-mucinous cysts). The model had an overall accuracy of 98.5%, sensitivity of 98.3%, specificity of 98.9% and AUC of 1. The image processing speed of the CNN was 7.2 ms per frame. We developed a deep learning algorithm that differentiated mucinous and non-mucinous cysts with high accuracy. The present CNN may constitute an important tool to help risk stratify PCLs.

The treatment goal of Crohn’s disease (CD) has moved towards achieving mucosal healing, resolution of transmural inflammation, and normalization of biomarkers. The purpose of this study was to evaluate how well computed tomography enterography (CTE) and fecal calprotectin (FC) correlated with endoscopic activity in newly diagnosed patients with CD and after 1 year of therapy. Consecutive patients with newly diagnosed CD were evaluated by endoscopy, CTE, and FC at diagnosis and 12 months after beginning immunosuppression. Endoscopic severity was assessed using the Simplified Endoscopic Score for Crohn’s Disease (SES-CD). Biomarkers, clinical indexes, and FC were recorded on the day of ileocolonoscopy at diagnosis and 1 year after diagnosis. We adapted a CTE score for disease activity based on radiological signs of inflammation (i.e. mural thickness, mural hyperenhancement, mesenteric fat proliferation, mesenteric fat densification, comb sign, presence of strictures, fistulas, abscesses, ascites, and lymphadenopathy). Correlations between endoscopy, CTE, and FC were assessed using Spearman’s rank correlation. A total of 29 patients (48% women; median age 30 (24.5–35.5) years) were included in this prospective cohort. CTE findings significantly correlated with endoscopic findings. Endoscopic remission (ER) at 1-year follow up significantly correlated with improvement in mural hyperenhancement (p = 0.004), mesenteric fat densification (p = 0.001), comb sign (p = 0.004), and strictures (p = 0.008) in CTE. None of the CTE findings improved in patients without ER. FC correlated with SES-CD (rs = 0.696, p < 0.001) and with CTE features of inflammation (rs = 0.596, p < 0.001). A cut-off of 100 µg/g predicted ER with 92% sensitivity, 65% specificity, and 83% accuracy (area under curve 0.878, p < 0.001). CTE findings and FC levels correlated with endoscopic activity in CD both at diagnosis and at 1-year follow up. These two noninvasive markers of disease activity may be used as an alternative to endoscopy to monitor disease response to therapy.

INTRODUCTION: 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: 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 and Aims: Endoscopic ultrasound (EUS)-guided fine-needle aspiration (FNA) is essential for the classification of pancreatic cystic lesions (PCLs). Recently, intracystic glucose has been suggested as an alternative to carcinoembryonic antigen (CEA) level as a predictor of mucinous cystic lesions (M-PCLs). This study aims to evaluate the diagnostic performance of intra-cystic glucose in distinguishing between M-PCLs and non M-PCLs (NM-PCLs) and to analyze the possibility of on-site glucose measurement with a standard glucometer. Methods: Patients with PCLs submitted to EUS-FNA with simultaneous intracystic glucose measurement between 2017 and 2022 were included. The diagnostic performance of glucose versus CEA for the differentiation between M-PCLs and NM-PCLs was compared to a final diagnosis based on the analysis of surgical specimen, intracystic biopsy or, if this data was unavailable, multidisciplinary evaluation. A cut-off of <50 mg/dL was used for the diagnosis of MCLs. Additionally, the agreement between on-site glucose determination with a standard glucometer and laboratory glucose measurement was assessed. Results: Mucinous lesions accounted for 56% of all PCLs. The median values of glucose and CEA for M-PCLs were 18 mg/dL and 286 ng/mL, respectively. Intracystic glucose had a sensitivity and specificity of 93.2% and 76.5%, respectively, for the diagnosis of MCLs (versus 55.6% and 87.5%, respectively, for CEA). The area under the curve was 0.870 for on-site glucose (versus 0.806 for CEA). An excellent correlation was observed between on-site and laboratory glucose measurement (ρ=0.919). Conclusions: The measurement of intracystic glucose showed superior performance compared with CEA in distinguishing between M-PCLs and NM-PCLs, with excellent correlation between on-site and conventional lab glucose measurement. Thus, on-site intracystic glucose appears to be an excellent biomarker for the characterization of PCLs due to its low cost, high availability, and the need for a minimal cyst fluid volume for its determination.

Artificial intelligence (AI) has emerged as a transformative tool across several specialties, namely gastroenterology, where it has the potential to optimize both diagnosis and treatment as well as enhance patient care. Coloproctology, due to its highly prevalent pathologies and tremendous potential to cause significant mortality and morbidity, has drawn a lot of attention regarding AI applications. In fact, its application has yielded impressive outcomes in various domains, colonoscopy being one prominent example, where it aids in the detection of polyps and early signs of colorectal cancer with high accuracy and efficiency. With a less explored path but equivalent promise, AI-powered capsule endoscopy ensures accurate and time-efficient video readings, already detecting a wide spectrum of anomalies. High-resolution anoscopy is an area that has been growing in interest in recent years, with efforts being made to integrate AI. There are other areas, such as functional studies, that are currently in the early stages, but evidence is expected to emerge soon. According to the current state of research, AI is anticipated to empower gastroenterologists in the decision-making process, paving the way for a more precise approach to diagnosing and treating patients. This review aims to provide the state-of-the-art use of AI in coloproctology while also reflecting on future directions and perspectives.

Background/Objectives: Endoscopic ultrasound (EUS) is crucial for lymph node (LN) characterization, playing a key role in oncological staging and treatment guidance. EUS criteria for predicting malignancy are imprecise, and histologic diagnosis may have limitations. This multicenter study aimed to evaluate the effectiveness of a novel artificial intelligence (AI)–based system in predicting LN malignancy from EUS images. Methods: This multicenter study included EUS images from nine centers. Lesions were labeled (“malignant” or “benign”) and delimited with bounding boxes. Definitive diagnoses were based on cytology/biopsy or surgical specimens and, if negative, a minimum six-month clinical follow-up. A convolutional neural network (CNN) was developed using the YOLO (You Only Look Once) architecture, incorporating both detection and classification modules. Results: A total of 59,992 images from 82 EUS procedures were analyzed. The CNN distinguished malignant from benign lymph nodes with a sensitivity of 98.8% (95% CI: 98.5–99.2%), specificity of 99.0% (95% CI: 98.3–99.7%), and precision of 99.0% (95% CI: 98.4–99.7%). The negative and positive predictive values for malignancy were 98.8% and 99.0%, respectively. Overall diagnostic accuracy was 98.3% (95% CI: 97.6–99.1%). Conclusions: This is the first study evaluating the performance of deep learning systems for LN assessment using EUS imaging. Our AI-powered imaging model shows excellent detection and classification capabilities, emphasizing its potential to provide a valuable tool to refine LN evaluation with EUS, ultimately supporting more tailored, efficient patient care.