Development of convolutional neural network models that recognize normal anatomic structures during real-time radial-array and linear-array EUS (with videos).

BACKGROUND AND AIMS: EUS is a high-skill technique that requires numerous procedures to achieve competence. However, training facilities are limited worldwide. Convolutional neural network (CNN) models have been previously implemented for object detection. We developed 2 EUS-based CNN models for normal anatomic structure recognition during real-time linear- and radial-array EUS evaluations. METHODS: The study was performed from February 2020 to June 2022. Consecutive patient videos of linear- and radial-array EUS videos were recorded. Expert endosonographers identified and labeled 20 normal anatomic structures within the videos for training and validation of the CNN models. Initial CNN models (CNNv1) were developed from 45 videos and the improved models (CNNv2) from an additional 102 videos. CNN model performance was compared with that of 2 expert endosonographers. RESULTS: CNNv1 used 45,034 linear-array EUS frames and 21,063 radial-array EUS frames. CNNv2 used 148,980 linear-array EUS frames and 128,871 radial-array EUS frames. Linear-array CNNv1 and radial-array CNNv1 achieved a 75.65% and 71.36% mean average precision (mAP) with a total loss of .19 and .18, respectively. Linear-array CNNv2 obtained an 88.7% mAP with a .06 total loss, whereas radial-array CNNv2 achieved an 83.5% mAP with a .07 total loss. CNNv2 accurately detected all studied normal anatomic structures with a >98% observed agreement during clinical validation. CONCLUSIONS: The proposed CNN models accurately recognize the normal anatomic structures in prerecorded videos and real-time EUS. Prospective trials are needed to evaluate the impact of these models on the learning curves of EUS trainees.

Assessing EUS-guided radiofrequency ablation in unresectable pancreatic ductal adenocarcinoma: a single-center historic cohort study.

BACKGROUND AND AIMS: EUS-guided radiofrequency ablation (EUS-RFA) has emerged as an alternative for the local treatment of unresectable pancreatic ductal adenocarcinoma (PDAC). We assessed the feasibility and safety of EUS-RFA in patients with unresectable PDAC. METHODS: This study followed an historic cohort compounded by locally advanced (LA-) and metastatic (m)PDAC-naïve patients who underwent EUS-RFA between October 2019 and March 2022. EUS-RFA was performed with a 19-gauge needle electrode with a 10-mm active tip for energy delivery. Study primary endpoints were feasibility, safety, and clinical follow-up, whereas secondary endpoints were performance status (PS), local control, and overall survival (OS). RESULTS: Twenty-six patients were selected: 15 with locally advanced pancreatic duct adenocarcinoma (LA-PDAC) and 11 with metastatic pancreatic duct adenocarcinoma (mPDAC). Technical success was achieved in all patients with no major adverse events. Six months after EUS-RFA, OS was seen in 11 of 26 patients (42.3%), with significant PS improvement (P = .03). Local control was achieved, with tumor reduction from 39.5 mm to 26 mm (P = .04). A post-treatment hypodense necrotic area was observed at the 6-month follow-up in 11 of 11 patients who were still alive. Metastatic disease was a significant factor for worsening OS (hazard ratio, 5.021; 95% confidence interval, 1.589-15.87; P = .004). CONCLUSIONS: EUS-RFA for the treatment of pancreatic adenocarcinoma is a minimally invasive and safe technique that may have an important role as targeted therapy for local treatment of unresectable cases and as an alternative for poor surgical candidates. Also, RFA may play a role in downstaging cancer with a potential increase in OS in nonmetastatic cases. Large prospective cohorts are required to evaluate this technique in clinical practice.

Prophylactic EUS-guided gallbladder drainage prevents acute cholecystitis in patients with malignant biliary obstruction and cystic duct orifice involvement: a randomized trial (with video).

BACKGROUND AND AIMS: Patients with distal malignant biliary obstruction (MBO) and cystic duct orifice tumoral involvement have an increased risk for the development of acute cholecystitis after self-expandable metallic stent (SEMS) placement. We aimed to determine whether primary EUS-guided gallbladder drainage prevents acute cholecystitis in these patients. METHODS: This was a single-center, randomized control trial in patients with distal MBO enrolled from July 2018 to July 2020. Patients were randomized into 2 groups: an interventional group treated with conventional ERCP biliary drainage with SEMS placement and subsequent primary EUS-guided gallbladder drainage (EUS-GBD) and a control group treated with conventional biliary drainage alone. The primary outcome of the study was the occurrence of post-treatment acute cholecystitis, assessed for ≤12 months or until death. The secondary outcomes were hospitalization length and median survival time. RESULTS: Forty-four patients were included in the study: 22 in each group. Five patients in the control group (22.7%) and none in the intervention group experienced acute cholecystitis. The median hospitalization time was significantly lower in the interventional group than in the control group (2 days vs 1 day, P = .017). There was no difference in the observed median survival rates in the primary EUS-GBD group (2.9 months) and the control group (2.8 months) (P = .580). CONCLUSION: In this single-center study of patients with unresectable MBO and occlusion of the cystic duct orifice, prophylactic EUS-GBD demonstrated a reduced incidence of acute cholecystitis.

Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model.

BACKGROUND: We aimed to develop a convolutional neural network (CNN) model for detecting neoplastic lesions during real-time digital single-operator cholangioscopy (DSOC) and to clinically validate the model through comparisons with DSOC expert and nonexpert endoscopists. METHODS: In this two-stage study, we first developed and validated CNN1. Then, we performed a multicenter diagnostic trial to compare four DSOC experts and nonexperts against an improved model (CNN2). Lesions were classified into neoplastic and non-neoplastic in accordance with Carlos Robles-Medranda (CRM) and Mendoza disaggregated criteria. The final diagnosis of neoplasia was based on histopathology and 12-month follow-up outcomes. RESULTS: In stage I, CNN2 achieved a mean average precision of 0.88, an intersection over the union value of 83.24 %, and a total loss of 0.0975. For clinical validation, a total of 170 videos from newly included patients were analyzed with the CNN2. Half of cases (50 %) had neoplastic lesions. This model achieved significant accuracy values for neoplastic diagnosis, with a 90.5 % sensitivity, 68.2 % specificity, and 74.0 % and 87.8 % positive and negative predictive values, respectively. The CNN2 model outperformed nonexpert #2 (area under the receiver operating characteristic curve [AUC]-CRM 0.657 vs. AUC-CNN2 0.794, P < 0.05; AUC-Mendoza 0.582 vs. AUC-CNN2 0.794, P < 0.05), nonexpert #4 (AUC-CRM 0.683 vs. AUC-CNN2 0.791, P < 0.05), and expert #4 (AUC-CRM 0.755 vs. AUC-CNN2 0.848, P < 0.05; AUC-Mendoza 0.753 vs. AUC-CNN2 0.848, P < 0.05). CONCLUSIONS: The proposed CNN model distinguished neoplastic bile duct lesions with good accuracy and outperformed two nonexpert and one expert endoscopist.

Vascularity can distinguish neoplastic from non-neoplastic bile duct lesions during digital single-operator cholangioscopy.

BACKGROUND AND AIMS: Various macroscopic features are proposed for the diagnosis of biliary lesions during digital single-operator cholangioscopy (DSOC); however, neovasculature may be one of the most reliable features of neoplasia. We aimed to evaluate the detection of neovasculature during DSOC to distinguish neoplastic from non-neoplastic bile duct lesions. METHODS: A retrospective, single-center, cohort study was used. Neovasculature was defined as the presence of irregular or "spider" vascularity on bile duct lesions. The accuracy of detection of neovasculature for the identification of neoplastic lesions was estimated using the histologic results, surgical specimens, and/or 6-month follow-up as the criterion standard. Interobserver agreement analysis (kappa value) was performed between 2 expert endoscopists and 3 nonexpert physicians. RESULTS: Ninety-five patients were included; the median age was 65.6 years (range, 20-93 years), and 51 (53.7%) patients were female. Signs of neovasculature were observed in 65 of 95 (68.4%) patients. Histology confirmed neoplasia in 48 of 95 (50.5%) patients, and 6-month follow-up survival confirmed neoplasia in 52 of 95 (54.7%) patients. The use of vascularity for identifying neoplastic lesions achieved an accuracy of 80%, sensitivity of 94%, specificity of 63%, positive predictive value of 75%, negative predictive value of 90%, positive likelihood ratio of 2.53 (95% confidence interval, 1.71-3.76), and negative likelihood ratio of 0.09 (95% confidence interval, 0.03-0.28). The interobserver and intraobserver agreement were excellent (κ > 80%; P < .001) between expert endoscopists and nonexpert physicians. CONCLUSION: Detection of irregular or spider vascularity on bile duct lesions during DSOC evaluations accurately identifies biliary neoplastic lesions. Prospective multicenter trials are required to evaluate neovasculature as a single factor for predicting neoplasia.

Over-The-Scope Clip system as a first-line therapy for high-risk bleeding peptic ulcers: a retrospective study.

BACKGROUND: Effective hemostasis is essential to prevent rebleeding. We evaluated the efficacy and feasibility of the Over-The-Scope Clip (OTSC) system compared to combined therapy (through-the-scope clips with epinephrine injection) as a first-line endoscopic treatment for high-risk bleeding peptic ulcers. METHODS: We retrospectively analyzed data of 95 patients from a single, tertiary center and underwent either OTSC (n = 46) or combined therapy (n = 49). The primary outcome of the present study was the efficacy of the OTSC system as a first-line therapy in patients with high-risk bleeding peptic ulcers compared to combined therapy with TTS clips and epinephrine injection. The secondary outcomes included the rebleeding rate, perforation rate, mean procedure time, reintervention rate, mean procedure cost and days of hospitalization in the two study groups within 30 days of the index procedure. RESULTS: All patients achieved hemostasis within the procedure; two patients in the OTSC group and four patients in the combined therapy group developed rebleeding (p = 0.444). No patients experienced gastrointestinal perforation. OTSC had a shorter median procedure time than combined therapy (11 min versus 20 min; p < 0.001). The procedure cost was superior for OTSC compared to combined therapy ($102,000 versus $101,000; p < 0.001). We found no significant difference in the rebleeding prevention rate (95.6% versus 91.8%, p = 0.678), hospitalization days (3 days versus 4 days; p = 0.215), and hospitalization costs ($108,000 versus $240,000, p = 0.215) of the OTSC group compared to the combined therapy group. CONCLUSION: OTSC treatment is an effective and feasible first-line therapy for high-risk bleeding peptic ulcers. OTSC confers comparable costs and patient outcomes as combined treatments, with a shorter procedure time.

Endoscopic ultrasonography-guided deployment of embolization coils and cyanoacrylate injection in gastric varices versus coiling alone: a randomized trial.

BACKGROUND: Gastric variceal bleeding is a life-threating condition with challenging management. We aimed to compare the efficacy and safety of endoscopic ultrasonography (EUS)-guided coil embolization and cyanoacrylate injection versus EUS-guided coil embolization alone in the management of gastric varices. METHODS: A single-center, parallel-randomized controlled trial involving 60 participants with gastric varices (GOV II and IGV I) who were randomly allocated to EUS-guided coil embolization and cyanoacrylate injection (n = 30) or EUS-guided coil embolization alone (n = 30). The primary end points were the technical and clinical success rates of both procedures. The secondary end points were the reappearance of gastric varices during follow-up, along with rebleeding, the need for reintervention, and complication and survival rates. RESULTS: The technical success rate was 100 % in both groups. Immediate disappearance of varices was observed in 86.7 % of patients treated with coils and cyanoacrylate, versus 13.3 % of patients treated with coils alone (P < 0.001). Median survival time was 16.4 months with coils and cyanoacrylate versus 14.2 months with coils alone (P = 0.90). Rebleeding occurred in 3.3 % of patients treated with combined treatment and 20 % of those treated with coils alone (P = 0.04). With combined treatment, 83.3 % of patients were free from reintervention versus 60 % with coils alone (hazard ratio 0.27; 95 % confidence interval 0.095 - 0.797; P = 0.01). CONCLUSIONS: EUS-guided coil embolization with cyanoacrylate injection achieved excellent clinical success, with lower rates of rebleeding and reintervention than coil treatment alone. Multicenter studies are required to define the most appropriate technique for gastric variceal obliteration.

Safety, Feasibility, and Efficacy of Pancolonic Retroflexed Viewing Using a Short-turn Radius Colonoscope.

GOALS: The goal of this study was to evaluate the safety and feasibility of routine segmental retroflexed withdrawal viewing (RV) of the colon with the RetroView colonoscope. MATERIALS AND METHODS: This was a prospective, single-center, 2-stage diagnostic trial. After cecal intubation, mucosal evaluation by forward viewing (FV) and RV was performed by segment (right, transverse, left, and sigmoid colon, and rectum). Lesions detected during FV were removed and/or marked before retroflexion. Safety and feasibility were measured through adverse event and technical success rates. All lesions detected and removed endoscopically were recorded. RESULTS: Two hundred twenty-five patients underwent colonoscopy with the RetroView colonoscope. Retroflexion by segment was successful in the right, transverse, left, and sigmoid colon, and rectum in 98.9%, 100%, 100%, 82.6%, and 100% of cases, respectively. The mean total procedure time was 16.6 minutes. Ninety-four lesions were detected through retroflexion evaluation, for an increase in the lesions' detection rate of 30.7%. The per-adenoma miss rate of standard colonoscopy (FV) was 35.71%. The adenoma detection rate (ADR) for FV was 16%, whereas, when performing FV and RV, the ADR increased to 24.9%. Adverse events were recorded in 0.4% of cases. Therapeutic procedures were performed successfully through the retroflexed position in 81/225 patients. CONCLUSIONS: Routine retroflexion evaluation of the colonic mucosa by segment using the RetroView colonoscope is safe and feasible. Retroflexion evaluation increases the detection rate of colonic lesions behind folds, including the number of adenomas per colonoscopy and ADR, offering a complete screening colonoscopy. All therapeutic procedures are feasible through retroflexion.

Endoscopic-ultrasound-guided coil and cyanoacrylate embolization for gastric varices and the roles of endoscopic Doppler and endosonographic varicealography in vascular targeting.

OBJECTIVE: To report the results of endoscopic ultrasound-guided injection of coils with cyanoacrylate (CYA) using a less-expensive coil with an emphasis on the roles of Doppler and endosonographic varicealography (EV) in identifying the feeder vessel in gastric varix treatment. METHODS: An observational, descriptive study with prospectively collected data. Patients with gastric varices (GV) were included and were treated by endoscopic ultrasound-guided injection of CYA and a less-expensive coil. Technical success, complete and immediate variceal obliteration, rebleeding, complication and survival rates were evaluated. RESULTS: Thirty patients with GV with a mean age of 62 years (range: 44-76 years) were treated. Median number of coils used was 2 (range: 1-3), and median volume of CYA was 1.8 mL (1.2-2.4 mL). Technical success rate was 100%. EV technical success was observed in 26/30 patients. Complete variceal obliteration was observed in 96.6% of patients, and immediate disappearance of the varix was observed in 24 (80%) patients. The complication rate was 6.7%. CONCLUSIONS: Endoscopic-ultrasound guidance for gastric varix treatment with the addition of EV and the use of a less-expensive coil is a safe and effective technique that results in the immediate disappearance of GV after targeting the feeding vessel.

Reliability and accuracy of a novel classification system using peroral cholangioscopy for the diagnosis of bile duct lesions.

BACKGROUND: The aim of this study was to propose a novel, comprehensive, macroscopic classification for bile duct lesions. METHODS: A two-stage protocol was designed. In Stage I, a retrospective study (September 2013 to September 2015) of patients with bile duct lesions detected by peroral cholangioscopy (POCS) was performed. A total of 315 images with at least 6 months of follow-up were recorded, analyzed, and correlated to histology, and were classified as non-neoplastic (one of three types, 1 - 3) or neoplastic (one of four types, 1 - 4) based on morphological and vascular patterns. In Stage II, a prospective, nonrandomized, double-blind study was performed from December 2015 to December 2016 to validate the proposed classification. Sensitivity, specificity, positive and negative predictive values (PPV and NPV, respectively), and positive and negative likelihood ratios (LR + and LR - , respectively) were calculated (gold standard: 6-month follow-up). Inter- and intraobserver agreement (kappa value, κ) among experts and non-experts were calculated. RESULTS: 171 patients were included (65 retrospective; 106 prospective). In Stage I, 28/65 cases were neoplastic and 37 /65 were non-neoplastic, according to the final diagnosis. In Stage II, 56/106 were neoplastic with a sensitivity, specificity, PPV, NPV, LR + , and LR - for neoplastic diagnosis of 96.3 %, 92.3 %, 92.9 %, 96 %, 12.52, and 0.04, respectively. The proposed classification presented high reproducibility among observers, for both neoplastic and subtypes categories. However, it was better for experts (κ > 80 %) than non-experts (κ 64.7 % - 81.9 %). CONCLUSION: The novel classification system could help physicians to distinguish non-neoplastic from neoplastic bile duct lesions.

Latin American consensus on diagnosis of gastroesophageal reflux disease.

BACKGROUND: Diagnosing gastroesophageal reflux disease (GERD) can be challenging given varying symptom presentations, and complex multifactorial pathophysiology. The gold standard for GERD diagnosis is esophageal acid exposure time (AET) measured by pH-metry. A variety of additional diagnostic tools are available. The goal of this consensus was to assess the individual merits of GERD diagnostic tools based on current evidence, and provide consensus recommendations following discussion and voting by experts. METHODS: This consensus was developed by 15 experts from nine countries, based on a systematic search of the literature, using GRADE (grading of recommendations, assessment, development and evaluation) methodology to assess the quality and strength of the evidence, and provide recommendations regarding the diagnostic utility of different GERD diagnosis tools, using AET as the reference standard. KEY RESULTS: A proton pump inhibitor (PPI) trial is appropriate for patients with heartburn and no alarm symptoms, but nor for patients with regurgitation, chest pain, or extraesophageal presentations. Severe erosive esophagitis and abnormal reflux monitoring off PPI are clearly indicative of GERD. Esophagram, esophageal biopsies, laryngoscopy, and pharyngeal pH monitoring are not recommended to diagnose GERD. Patients with PPI-refractory symptoms and normal endoscopy require reflux monitoring by pH or pH-impedance to confirm or exclude GERD, and identify treatment failure mechanisms. GERD confounders need to be considered in some patients, pH-impedance can identify supragrastric belching, impedance-manometry can diagnose rumination. CONCLUSIONS: Erosive esophagitis on endoscopy and abnormal pH or pH-impedance monitoring are the most appropriate methods to establish a diagnosis of GERD. Other tools may add useful complementary information.

Accurate and safe diagnosis and treatment of neoplastic biliary lesions using a novel 9F and 11F digital single-operator cholangioscope.

Background and study aims Digital single-operator cholangioscopy (DSOC) allows the diagnosis of biliary duct disorders and treatment for complicated stones. However, these technologies have limitations such as the size of the probe and working channel, excessive cost, and low image resolution. Recently, a novel DSOC system (eyeMAX, Micro-Tech, Nanjing, China) was developed to address these limitations. We aimed to evaluate the usefulness and safety of a novel 9F and 11F DSOC system in terms of neoplastic diagnostic accuracy based on visual examination, ability to evaluate tumor extension and to achieve complete biliary stone clearance, and procedure-related adverse events (AEs). Patients and methods Data from ≥ 18-year-old patients who underwent DSOC from July 2021 to April 2022 were retrospectively recovered and divided into a diagnostic and a therapeutic cohort. Results A total of 80 patients were included. In the diagnostic cohort (n = 49/80), neovascularity was identified in 26 of 49 patients (46.9%). Biopsy was performed in 65.3% patients with adequate tissue sample obtained in 96.8% of cases. Biopsy confirmed neoplasia in 23 of 32 cases. DSOC visual impression achieved 91.6% sensitivity and 87.5% specificity in diagnosing neoplasms. In the therapeutic cohort (n = 43/80), 26 of 43 patients required lithotripsy alone. Total stone removal was achieved in 71% patients in the first session. Neither early nor late AEs were documented in either the diagnostic or therapeutic cohort. Conclusions The novel DSOC device has excellent diagnostic accuracy in distinguishing neoplastic biliary lesions as well as therapeutic benefits in the context of total stone removal, with no documented AEs.

Water-jet dissector for endoscopic submucosal dissection in an animal study: outcomes of the continuous and pulsed modes.

BACKGROUND: Endoscopic submucosal dissection (ESD) allows en bloc resection of early neoplastic lesions of gastrointestinal tract. Lesions are lifted by submucosal fluid injection before circumferential incision and dissection. High-pressure fluid injection using water jet (WJ) technology is already used for lifting and dissection in surgery. The study was designed to assess WJ for ESD submucosal lifting and dissection. METHODS: An experimental, randomized comparative, "in vivo" nonsurvival animal study on 12 pigs was designed. Stomach mucosal areas were delineated and resected using three ESD techniques: technique A-syringe injection and IT knife dissection; technique B-WJ continuous injection and IT knife dissection; technique C-WJ injection and WJ pulsed dissection. Injection and dissection speeds and complications rates were assessed. RESULTS: Water jet continuous injection is faster than syringe injection (B faster than A, p = 0.001 and B nonsignificantly faster than C, p = 0.06). IT knife dissection is significantly faster after WJ continuous injection (B faster than A, p = 0.003). WJ pulsed dissection is significantly slower than IT knife dissection (C slower than A and B, both p < 0.001). The overall procedure speed was significantly higher and the immediate bleedings rate was significantly lower for technique B than A and C (overall procedure speed p = 0.001, immediate bleedings p = 0.032 and 0.038 respectively). There were no perforations with any technique. CONCLUSIONS: Water jet fluid continuous injection speeds up ESD, whereas pulsed WJ dissection does not.

Spanish translation and validation of a hybrid, health-related quality of life questionnaire for chronic esophageal conditions: NEQOL-S.

BACKGROUND: Chronic esophageal conditions (CEC) are associated with significant disease-related burden, disability, and costs. Health-related quality of life (HRQOL) constructs are intended to capture the physical, mental, social, and emotional aspects of a patient's life and how health status impacts these domains. The Northwestern Esophageal Quality of Life (NEQOL) can be used among esophageal diseases while maintaining sensitivity to specific conditions. We aimed to translate, cross-cultural adapt, and validate the NEQOL into Spanish. METHODS: After language and cross-cultural adaptation, the NEQOL was applied to an outpatient clinic-based population in a single tertiary center. We analyzed the internal consistency, construct, criterion validity, and test-retest reliability of the questionnaire. The criterion validity was tested against the SF-12 questionnaire. KEY RESULTS: After completing the translation process, no item was considered problematic. A total of 385 patients were included in the validation study. The internal consistency (Cronbach's alpha) for the total NEQOL-S score was 0.89. The NEQOL-S questionnaire showed moderate test-retest reliability (ICC = 0.828; 95% CI 0.755-0.881; p < 0.001). Criterion validity showed good coherence when correlated with the SF-12 survey (R2  = 0.538; 95% CI 0.491-0.585, p < 0.001). CONCLUSIONS AND INFERENCES: The translated and cross-culturally adapted NEQOL-S showed good psychometric properties that allow its use in Spanish-speaking patients suffering from CEC.