Deep Learning for Automatic Diagnosis and Morphologic Characterization of Malignant Biliary Strictures Using Digital Cholangioscopy: A Multicentric Study.

Digital single-operator cholangioscopy (D-SOC) has enhanced the ability to diagnose indeterminate biliary strictures (BSs). Pilot studies using artificial intelligence (AI) models in D-SOC demonstrated promising results. Our group aimed to develop a convolutional neural network (CNN) for the identification and morphological characterization of malignant BSs in D-SOC. A total of 84,994 images from 129 D-SOC exams in two centers (Portugal and Spain) were used for developing the CNN. Each image was categorized as either a normal/benign finding or as malignant lesion (the latter dependent on histopathological results). Additionally, the CNN was evaluated for the detection of morphologic features, including tumor vessels and papillary projections. The complete dataset was divided into training and validation datasets. The model was evaluated through its sensitivity, specificity, positive and negative predictive values, accuracy and area under the receiver-operating characteristic and precision-recall curves (AUROC and AUPRC, respectively). The model achieved a 82.9% overall accuracy, 83.5% sensitivity and 82.4% specificity, with an AUROC and AUPRC of 0.92 and 0.93, respectively. The developed CNN successfully distinguished benign findings from malignant BSs. The development and application of AI tools to D-SOC has the potential to significantly augment the diagnostic yield of this exam for identifying malignant strictures.

Distal Intestinal Obstruction Syndrome resolved by dissolution with Coca-Cola® via colonoscopy in a cystic fibrosis patient.

We report the case of a 37 years old woman who presented to emergency department because of a 3 days history of abdominal disconfort and distension. After physical examination and a CT scan of the abdomen she was diagnosed of Distal Intestinal Obstruction Syndrome (DIOS) in the context of her underlying cystic fibrosis. Conservative management was attempted with no improvement. A colonoscopy was performed and thick solid feces were seen filling the cecum and right colon. An attempt to dissolve the impacted stool was made by instilling one liter of Diet Coca-Cola® through the working channel of the colonoscope. After that, the condition of the resolved in the following 24 h with no more interventions.

Guía clínica para la resección mucosa endoscópica de lesiones colorrectales no pediculadas / Clinical guidelines for endoscopic mucosal resection of non-pedunculated colorectal lesions

Este documento resume el contenido de la Guía de resección mucosa endoscópica elaborada por el grupo de trabajo de la Sociedad Española de Endoscopia Digestiva (GSEED de Resección Endoscópica) y expone las recomendaciones sobre el manejo endoscópico de las lesiones neoplásicas colorrectales superficiales (AU)

This document summarizes the contents of the Clinical Guidelines for the Endoscopic Mucosal Resection of Non-Pedunculated Colorectal Lesions that was developed by the working group of the Spanish Society of Digestive Endoscopy (GSEED of Endoscopic Resection). This document presents recommendations for the endoscopic management of superficial colorectal neoplastic lesions (AU)

Guía clínica para la resección mucosa endoscópica de lesiones colorrectales no pediculadas / Clinical guidelines for endoscopic mucosal resection of non-pedunculated colorectal lesions

Este documento resume el contenido de la Guía de resección mucosa endoscópica elaborada por el grupo de trabajo de la Sociedad Española de Endoscopia Digestiva (GSEED de Resección Endoscópica) y expone las recomendaciones sobre el manejo endoscópico de las lesiones neoplásicas colorrectales superficiales (AU)

This document summarizes the contents of the Clinical Guidelines for the Endoscopic Mucosal Resection of Non-Pedunculated Colorectal Lesions that was developed by the working group of the Spanish Society of Digestive Endoscopy (GSEED of Endoscopic Resection). This document presents recommendations for the endoscopic management of superficial colorectal neoplastic lesions (AU)

Clinical guidelines for endoscopic mucosal resection of non-pedunculated colorectal lesions.

This document summarizes the contents of the Clinical Guidelines for the Endoscopic Mucosal Resection of Non-Pedunculated Colorectal Lesions that was developed by the working group of the Spanish Society of Digestive Endoscopy (GSEED of Endoscopic Resection). This document presents recommendations for the endoscopic management of superficial colorectal neoplastic lesions.

Clinical guidelines for endoscopic mucosal resection of non-pedunculated colorectal lesions. / Guía clínica para la resección mucosa endoscópica de lesiones colorrectales no pediculadas.

This document summarizes the contents of the Clinical Guidelines for the Endoscopic Mucosal Resection of Non-Pedunculated Colorectal Lesions that was developed by the working group of the Spanish Society of Digestive Endoscopy (GSEED of Endoscopic Resection). This document presents recommendations for the endoscopic management of superficial colorectal neoplastic lesions.

A Scoring System to Determine Risk of Delayed Bleeding After Endoscopic Mucosal Resection of Large Colorectal Lesions.

BACKGROUND & AIMS: After endoscopic mucosal resection (EMR) of colorectal lesions, delayed bleeding is the most common serious complication, but there are no guidelines for its prevention. We aimed to identify risk factors associated with delayed bleeding that required medical attention after discharge until day 15 and develop a scoring system to identify patients at risk. METHODS: We performed a prospective study of 1214 consecutive patients with nonpedunculated colorectal lesions 20 mm or larger treated by EMR (n = 1255) at 23 hospitals in Spain, from February 2013 through February 2015. Patients were examined 15 days after the procedure, and medical data were collected. We used the data to create a delayed bleeding scoring system, and assigned a weight to each risk factor based on the ß parameter from multivariate logistic regression analysis. Patients were classified as being at low, average, or high risk for delayed bleeding. RESULTS: Delayed bleeding occurred in 46 cases (3.7%, 95% confidence interval, 2.7%-4.9%). In multivariate analysis, factors associated with delayed bleeding included age ≥75 years (odds ratio [OR], 2.36; P < .01), American Society of Anesthesiologist classification scores of III or IV (OR, 1.90; P ≤ .05), aspirin use during EMR (OR, 3.16; P < .05), right-sided lesions (OR, 4.86; P < .01), lesion size ≥40 mm (OR, 1.91; P ≤ .05), and a mucosal gap not closed by hemoclips (OR, 3.63; P ≤ .01). We developed a risk scoring system based on these 6 variables that assigned patients to the low-risk (score, 0-3), average-risk (score, 4-7), or high-risk (score, 8-10) categories with a receiver operating characteristic curve of 0.77 (95% confidence interval, 0.70-0.83). In these groups, the probabilities of delayed bleeding were 0.6%, 5.5%, and 40%, respectively. CONCLUSIONS: The risk of delayed bleeding after EMR of large colorectal lesions is 3.7%. We developed a risk scoring system based on 6 factors that determined the risk for delayed bleeding (receiver operating characteristic curve, 0.77). The factors most strongly associated with delayed bleeding were right-sided lesions, aspirin use, and mucosal defects not closed by hemoclips. Patients considered to be high risk (score, 8-10) had a 40% probability of delayed bleeding.

Red flag imaging in Barrett's esophagus: does it help to find the needle in the haystack?

Esophageal Adenocarcinoma (EAC) has suffered a sharp increase on its incidence for the last decades, and it is associated with a poor prognosis. Barrett's Esophagus (BE) is the most important identifiable risk factor for the progression to esophageal adenocarcinoma. The key to prevent and provide a curative treatment of esophageal adenocarcinoma is the detection and eradication of early neoplasia in patients with esophagus. Endoscopic surveillance is evolving from a blind or random four quadrant biopsies protocol (Seattle protocol) to a more targeted approach. A detailed white light examination with high-resolution endoscopy is the cornerstone for recognition of early neoplastic lesions in BE. Additional imaging modalities may enhance targeting of lesions or provide more information at a focused level. There are emerging data that some of these new modalities can increase the yield of detecting dysplasia, although its routine use has yet to be validated.