Effect of AI on performance of endoscopists to detect Barrett neoplasia: A Randomized Tandem Trial.

Background and study aims To evaluate the effect of an AI-based clinical decision support system (AI) on the performance and diagnostic confidence of endoscopists during the assessment of Barrett's esophagus (BE). Patients and Methods Ninety-six standardized endoscopy videos were assessed by 22 endoscopists from 12 different centers with varying degrees of BE experience. The assessment was randomized into two video sets: Group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level. Results AI had a standalone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.6%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1 and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.7% (95% CI, 65.2% - 74.2%) to 78.0% (95% CI, 74.0% - 82.0%); specificity 67.3% (95% CI, 62.5% - 72.2%) to 72.7% (95 CI, 68.2% - 77.3%). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI. Conclusion BE nonexperts benefitted significantly from the additional AI. BE experts and nonexperts remained below the standalone performance of AI, suggesting that there may be other factors influencing endoscopists to follow or discard AI advice.

Implementación de la disección endoscópica submucosa esofágica en España: resultados del registro nacional / Implementation of esophageal endoscopic submucosal dissection in Spain: Results from the nationwide registry

Introducción y objetivos Los resultados de la disección submucosa endoscópica (DSE) en el esófago no han sido evaluados en nuestro país. Nuestro objetivo principal fue analizar la efectividad y la seguridad de la técnica. Material y métodos Análisis del registro nacional prospectivo de DSE. Se incluyeron todas las lesiones superficiales esofágicas extirpadas mediante DSE en 17 hospitales (20 endoscopistas) entre enero de 2016 y diciembre de 2021. Se excluyeron las lesiones subepiteliales. La variable principal fue el porcentaje de resección curativa. Se realizó un análisis de regresión logística para conocer los predictores de resección no curativa y un análisis de supervivencia. Resultados Se realizaron un total de 102 DSE en 96 pacientes. El éxito técnico fue del 100% y el porcentaje de resección en bloque, del 98%. El porcentaje de resección R0 y curativa fue del 77,5% (n = 79; IC 95%: 68%-84%) y del 63,7% (n = 65; IC 95%: 54%-72%), respectivamente. La histología más frecuente fue la neoplasia sobre esófago de Barrett (n = 55 [53,9%]). El principal motivo de resección no curativa fue la invasión submucosa profunda (n = 25). Los centros con menor volumen de casos obtuvieron cifras inferiores de resección curativa. El porcentaje de perforación, sangrado diferido y estenosis posprocedimiento fue del 5%, del 5% y del 15,7%, respectivamente. Ningún paciente falleció ni requirió cirugía por un efecto adverso. Tras una mediana de seguimiento de 14 meses, 20 pacientes (20,8%) recibieron cirugía y/o quimio-radioterapia, y 9 fallecieron (mortalidad del 9,4%). Conclusiones En nuestro medio, la DSE esofágica es curativa en aproximadamente dos de cada tres pacientes, con un riesgo aceptable de efectos adversos (AU)

Introduction and aims The outcomes of endoscopic submucosal dissection (ESD) in the esophagus have not been assessed in our country. Our primary aim was to analyze the effectiveness and safety of the technique. Material and methods Analysis of the prospectively maintained national registry of ESD. We included all superficial esophageal lesions removed by ESD in 17 hospitals (20 endoscopists) between January 2016 and December 2021. Subepithelial lesions were excluded. The primary outcome was curative resection. We conducted a survival analysis and used logistic regression analysis to assess predictors of non-curative resection. Results A total of 102 ESD were performed on 96 patients. The technical success rate was 100% and the percentage of en-bloc resection was 98%. The percentage of R0 and curative resection was 77.5% (n = 79; 95% CI: 68%-84%) and 63.7% (n = 65; 95% CI: 54%-72%), respectively. The most frequent histology was Barrett-related neoplasia (n = 55 [53.9%]). The main reason for non-curative resection was deep submucosal invasion (n = 25). The centers with a lower volume of ESD obtained worse results in terms of curative resection. The rate of perforation, delayed bleeding and post-procedural stenosis were 5%, 5% and 15.7%, respectively. No patient died or required surgery due to an adverse effect. After a median follow-up of 14 months, 20 patients (20.8%) underwent surgery and/or chemoradiotherapy, and 9 patients died (mortality 9.4%). Conclusions In Spain, esophageal ESD is curative in approximately two out of three patients, with an acceptable risk of adverse events (AU)

Implementation of esophageal endoscopic submucosal dissection in Spain: Results from the nationwide registry. / Implementación de la disección endoscópica submucosa esofágica en España: resultados del registro nacional.

INTRODUCTION AND AIMS: The outcomes of endoscopic submucosal dissection (ESD) in the esophagus have not been assessed in our country. Our primary aim was to analyze the effectiveness and safety of the technique. MATERIAL AND METHODS: Analysis of the prospectively maintained national registry of ESD. We included all superficial esophageal lesions removed by ESD in 17 hospitals (20 endoscopists) between January 2016 and December 2021. Subepithelial lesions were excluded. The primary outcome was curative resection. We conducted a survival analysis and used logistic regression analysis to assess predictors of non-curative resection. RESULTS: A total of 102 ESD were performed on 96 patients. The technical success rate was 100% and the percentage of en-bloc resection was 98%. The percentage of R0 and curative resection was 77.5% (n=79; 95%CI: 68%-84%) and 63.7% (n=65; 95%CI: 54%-72%), respectively. The most frequent histology was Barrett-related neoplasia (n=55 [53.9%]). The main reason for non-curative resection was deep submucosal invasion (n=25). The centers with a lower volume of ESD obtained worse results in terms of curative resection. The rate of perforation, delayed bleeding and post-procedural stenosis were 5%, 5% and 15.7%, respectively. No patient died or required surgery due to an adverse effect. After a median follow-up of 14months, 20patients (20.8%) underwent surgery and/or chemoradiotherapy, and 9 patients died (mortality 9.4%). CONCLUSIONS: In Spain, esophageal ESD is curative in approximately two out of three patients, with an acceptable risk of adverse events.

Applicability of the Barcelona scale to assess the quality of cleanliness of mucosa at esophagogastroduodenoscopy.

BACKGROUND AND OBJECTIVES: There are few scales with prospective validation for the assessment of the upper gastrointestinal mucosal cleanliness during an esophagogastroduodenoscopy (EGD). The aim of this study was to develop a valid and reproducible cleanliness scale for use during an EGD. METHODS: We developed a cleanliness scale (Barcelona scale) with a score (0-2 points) of five segments of the upper gastrointestinal tract with thorough cleaning techniques (esophagus, fundus, body, antrum, and duodenum). First, 125 photos (25 of each area) were assessed, and a score was assigned to each image by consensus among 7 experts endoscopists. Subsequently, 100 of the 125 images were selected and the inter- and intra-observer variability of 15 previously trained endoscopists was evaluated using the same images at two different times. RESULTS: In total, 1500 assessments were performed. In 1336/1500 observations (89%) there was agreement with the consensus score, with a mean kappa value of 0.83 (0.45-0.96). In the second evaluation, in 1330/1500 observations (89%) there was agreement with the consensus score, with a mean kappa value of 0.82 (0.45-0.93). The intra-observer variability was 0.89 (0.76-0.99). CONCLUSIONS: The Barcelona cleanliness scale is a valid measure and reproducible with minimal training. Its application in clinical practice is a significant step to standardize the quality of the EGD.

Diagnosis and management of Barrett esophagus: European Society of Gastrointestinal Endoscopy (ESGE) Guideline.

MR1 : ESGE recommends the following standards for Barrett esophagus (BE) surveillance:- a minimum of 1-minute inspection time per cm of BE length during a surveillance endoscopy- photodocumentation of landmarks, the BE segment including one picture per cm of BE length, and the esophagogastric junction in retroflexed position, and any visible lesions- use of the Prague and (for visible lesions) Paris classification- collection of biopsies from all visible abnormalities (if present), followed by random four-quadrant biopsies for every 2-cm BE length.Strong recommendation, weak quality of evidence. MR2: ESGE suggests varying surveillance intervals for different BE lengths. For BE with a maximum extent of ≥ 1 cm and < 3 cm, BE surveillance should be repeated every 5 years. For BE with a maximum extent of ≥ 3 cm and < 10 cm, the interval for endoscopic surveillance should be 3 years. Patients with BE with a maximum extent of ≥ 10 cm should be referred to a BE expert center for surveillance endoscopies. For patients with an irregular Z-line/columnar-lined esophagus of < 1 cm, no routine biopsies or endoscopic surveillance are advised.Weak recommendation, low quality of evidence. MR3: ESGE suggests that, if a patient has reached 75 years of age at the time of the last surveillance endoscopy and/or the patient's life expectancy is less than 5 years, the discontinuation of further surveillance endoscopies can be considered. Weak recommendation, very low quality of evidence. MR4: ESGE recommends offering endoscopic eradication therapy using ablation to patients with BE and low grade dysplasia (LGD) on at least two separate endoscopies, both confirmed by a second experienced pathologist.Strong recommendation, high level of evidence. MR5: ESGE recommends endoscopic ablation treatment for BE with confirmed high grade dysplasia (HGD) without visible lesions, to prevent progression to invasive cancer.Strong recommendation, high level of evidence. MR6: ESGE recommends offering complete eradication of all remaining Barrett epithelium by ablation after endoscopic resection of visible abnormalities containing any degree of dysplasia or esophageal adenocarcinoma (EAC).Strong recommendation, moderate quality of evidence. MR7: ESGE recommends endoscopic resection as curative treatment for T1a Barrett's cancer with well/moderate differentiation and no signs of lymphovascular invasion.Strong recommendation, high level of evidence. MR8: ESGE suggests that low risk submucosal (T1b) EAC (i. e. submucosal invasion depth ≤ 500 µm AND no [lympho]vascular invasion AND no poor tumor differentiation) can be treated by endoscopic resection, provided that adequate follow-up with gastroscopy, endoscopic ultrasound (EUS), and computed tomography (CT)/positrion emission tomography-computed tomography (PET-CT) is performed in expert centers.Weak recommendation, low quality of evidence. MR9: ESGE suggests that submucosal (T1b) esophageal adenocarcinoma with deep submucosal invasion (tumor invasion > 500 µm into the submucosa), and/or (lympho)vascular invasion, and/or a poor tumor differentiation should be considered high risk. Complete staging and consideration of additional treatments (chemotherapy and/or radiotherapy and/or surgery) or strict endoscopic follow-up should be undertaken on an individual basis in a multidisciplinary discussion.Strong recommendation, low quality of evidence. MR10 A: ESGE recommends that the first endoscopic follow-up after successful endoscopic eradication therapy (EET) of BE is performed in an expert center.Strong recommendation, very low quality of evidence. B: ESGE recommends careful inspection of the neo-squamocolumnar junction and neo-squamous epithelium with high definition white-light endoscopy and virtual chromoendoscopy during post-EET surveillance, to detect recurrent dysplasia.Strong recommendation, very low level of evidence. C: ESGE recommends against routine four-quadrant biopsies of neo-squamous epithelium after successful EET of BE.Strong recommendation, low level of evidence. D: ESGE suggests, after successful EET, obtaining four-quadrant random biopsies just distal to a normal-appearing neo-squamocolumnar junction to detect dysplasia in the absence of visible lesions.Weak recommendation, low level of evidence. E: ESGE recommends targeted biopsies are obtained where there is a suspicion of recurrent BE in the tubular esophagus, or where there are visible lesions suspicious for dysplasia.Strong recommendation, very low level of evidence. MR11: After successful EET, ESGE recommends the following surveillance intervals:- For patients with a baseline diagnosis of HGD or EAC:at 1, 2, 3, 4, 5, 7, and 10 years after last treatment, after which surveillance may be stopped.- For patients with a baseline diagnosis of LGD:at 1, 3, and 5 years after last treatment, after which surveillance may be stopped.Strong recommendation, low quality of evidence.

Diagnosis and management of barrett esophagus: european society of gastrointestinal endoscopy (ESGE) guideline

This Guideline is an official statement of the European Society of Gastrointestinal Endoscopy (ESGE). It is an update of the previous (2017) Position Statement on the endoscopic management of Barrett esophagus.

Diagnostic accuracy of artificial intelligence-aided capsule endoscopy (TOP100) in overt small bowel bleeding.

BACKGROUND: Capsule endoscopy (CE) is the first-choice exploration in case of overt small bowel bleeding (SBB). An early CE is known to increase diagnostic yield, but long reading times may delay therapeutics. The study evaluates the diagnostic performance of the artificial intelligence tool TOP100 in patients with overt SBB undergoing early CE with Pillcam SB3. METHODS: Patients who underwent early CE (up to 14 days from the bleeding episode) for suspected overt SBB were included. One experienced endoscopist prospectively performed standard reading (SR) and a second blind experienced endoscopist performed a TOP100-based reading (TR). The primary endpoint was TR diagnostic accuracy for lesions with high bleeding potential (P2). RESULTS: A total of 111 patients were analyzed. The most common clinical presentation was melena (64%). CE showed angiodysplasias in 40.5% of patients (45/111). In per-patient analysis, TR showed a sensitivity of 90.48% (95% CI 82.09-95.80), specificity of 100% (95% CI 87.23-100) with a PPV of 100% (95% CI 94.01-100), NPV of 77.14% (95% CI 63.58-86.71) and diagnostic accuracy of 92.79 (86.29-96.84). At multivariate analysis, adequate intestinal cleansing was the only independent predictor of concordance between TR and SR (OR 2.909, p = 0.019). The median reading time for SR and TR was 23 min (18.0-26.8) and 1.9 min (range 1.7-2.1), respectively (p < 0.001). CONCLUSIONS: TOP100 provides a fast-reading mode for early CE in case of overt small bowel bleeding. It identifies most patients with active bleeding and angiodysplasias, aiding in the prioritization of therapeutic procedures. However, its accuracy in detecting ulcers, varices and P1 lesions seems insufficient.

Preclinical Evaluation of a Microwave-Based Accessory Device for Colonoscopy in an In Vivo Porcine Model with Colorectal Polyps.

BACKGROUND AND AIMS: Colonoscopy is currently the most effective way of detecting colorectal cancer and removing polyps, but it has some drawbacks and can miss up to 22% of polyps. Microwave imaging has the potential to provide a 360° view of the colon and addresses some of the limitations of conventional colonoscopy. This study evaluates the feasibility of a microwave-based colonoscopy in an in vivo porcine model. METHODS: A prototype device with microwave antennas attached to a conventional endoscope was tested on four healthy pigs and three gene-targeted pigs with mutations in the adenomatous polyposis coli gene. The first four animals were used to evaluate safety and maneuverability and compatibility with endoscopic tools. The ability to detect polyps was tested in a series of three gene-targeted pigs. RESULTS: the microwave-based device did not affect endoscopic vision or cause any adverse events such as deep mural injuries. The microwave system was stable during the procedures, and the detection algorithm showed a maximum detection signal for adenomas compared with healthy mucosa. CONCLUSIONS: Microwave-based colonoscopy is feasible and safe in a preclinical model, and it has the potential to improve polyp detection. Further investigations are required to assess the device's efficacy in humans.

Técnicas de imagen avanzada en la detección y caracterización de las lesiones precursoras del cáncer gástrico y del cáncer gástrico precoz / Image-enhanced endoscopy in the diagnosis of gastric premalignant conditions and gastric cancer

La detección del cáncer gástrico precoz y de sus lesiones precursoras constituye un desafío para gran parte de los endoscopistas occidentales. Los cambios morfológicos que se producen en la mucosa gástrica generalmente son sutiles y, por tanto, difíciles de visualizar. En esta revisión se analiza la utilidad de la cromoendoscopia convencional, así como de sus modalidades digitales, y de la endoscopia con magnificación para reconocer y caracterizar estas lesiones.(AU)

Diagnosis of early gastric cancer and its precancerous lesions remains a challenge for great part of western endoscopists. Changes seen in the mucosal pattern are generally subtle and hence difficult to identify. In this article, we will review the usefulness of conventional and virtual chromoendoscopy and magnification endoscopy in the recognition and classification of these lesions.(AU)

Pancreatic Cancer Surveillance in Carriers of a Germline Pathogenic Variant in CDKN2A.

Three percent of patients with pancreatic ductal adenocarcinoma (PDAC) present a germline pathogenic variant (GPV) associated with an increased risk of this tumor, CDKN2A being one of the genes associated with the highest risk. There is no clear consensus on the recommendations for surveillance in CDKN2A GPV carriers, although the latest guidelines from the International Cancer of the Pancreas Screening Consortium recommend annual endoscopic ultrasound (EUS) or magnetic resonance imaging (MRI) regardless of family history. Our aim is to describe the findings of the PDAC surveillance program in a cohort of healthy CDKN2A GPV heterozygotes. This is an observational analysis of prospectively collected data from all CDKN2A carriers who underwent screening for PDAC at the high-risk digestive cancer clinic of the "Hospital Clínic de Barcelona" between 2013 and 2021. A total of 78 subjects were included. EUS or MRI was performed annually with a median follow-up of 66 months. Up to 17 pancreatic findings were described in 16 (20.5%) individuals under surveillance, although most of them were benign. No significant precursor lesions were identified, but an early PDAC was detected and treated. While better preventive strategies are developed, we believe that annual surveillance with EUS and/or MRI in CDKN2A GPV heterozygotes may be beneficial.

Motorized Spiral Enteroscopy Is Effective in Patients with Prior Abdominal Surgery.

BACKGROUND: Motorized Spiral Enteroscopy (MSE) reduces procedure time and increases insertion depth into the small bowel; however, there is scarce evidence on factors affecting MSE efficacy. AIMS: To evaluate diagnostic yield and adverse events of MSE including patients with prior major abdominal surgery. METHODS: A prospective observational study was conducted on patients undergoing MSE from June 2019 to December 2021. Demographic characteristics, procedure time, depth of maximum insertion (DMI), technical success, diagnostic yield, and adverse events were collected. RESULTS: Seventy-four anterograde (54.4%) and 62 retrograde (45.6%) enteroscopies were performed in 117 patients (64 males, median age 67 years). Fifty patients (42.7%) had prior major abdominal surgery. Technical success was 91.9% for anterograde and 90.3% for retrograde route. Diagnostic yield was 71.6% and 61.3%, respectively. The median DMI was 415 cm (264-585) for anterograde and 120 cm (37-225) for retrograde enteroscopy. In patients with prior major abdominal surgery, MSE showed significantly longer small bowel insertion time (38 vs 29 min, p = 0.004), with similar diagnostic yield (61 vs 71.4%, p = 0.201) and DMI (315 vs 204 cm, p = 0.226). The overall adverse event rate was 10.3% (SAE 1.5%), with no differences related to prior abdominal surgery (p = 0.598). Patients with prior surgeries directly involving the gastrointestinal tract showed lower DMI (189 vs 374 cm, p = 0.019) with equal exploration time (37.5 vs 38 min, p = 0.642) compared to those with other abdominal surgeries. CONCLUSIONS: MSE is effective and safe in patients with major abdominal surgery, although longer procedure times were observed. A lower depth of insertion was detected in patients with gastrointestinal surgery.

Wet-suction versus slow-pull technique for endoscopic ultrasound-guided fine-needle biopsy: a multicenter, randomized, crossover trial.

BACKGROUND : It is unknown whether there is an advantage to using the wet-suction or slow-pull technique during endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) with new-generation needles. We aimed to compare the performance of each technique in EUS-FNB. METHODS: This was a multicenter, randomized, single-blind, crossover trial including patients with solid lesions of ≥ 1 cm. Four needle passes with 22 G fork-tip or Franseen-type needles were performed, alternating the wet-suction and slow-pull techniques in a randomized order. The primary outcome was the histological yield (samples containing an intact piece of tissue of at least 550 µm). Secondary end points were sample quality (tissue integrity and blood contamination), diagnostic accuracy, and adequate tumor fraction. RESULTS: Overall, 210 patients with 146 pancreatic and 64 nonpancreatic lesions were analyzed. A tissue core was retrieved in 150 (71.4 %) and 129 (61.4 %) cases using the wet-suction and the slow-pull techniques, respectively (P = 0.03). The mean tissue integrity score was higher using wet suction (P = 0.02), as was the blood contamination of samples (P < 0.001). In the two subgroups of pancreatic and nonpancreatic lesions, tissue core rate and tissue integrity score were not statistically different using the two techniques, but blood contamination was higher with wet suction. Diagnostic accuracy and tumor fraction did not differ between the two techniques. CONCLUSION: Overall, the wet-suction technique in EUS-FNB resulted in a higher tissue core procurement rate compared with the slow-pull method. Diagnostic accuracy and the rate of samples with adequate tumor fraction were similar between the two techniques.

Image-enhanced endoscopy in the diagnosis of gastric premalignant conditions and gastric cancer. / Técnicas de imagen avanzada en la detección y caracterización de las lesiones precursoras del cáncer gástrico y del cáncer gástrico precoz.

Diagnosis of early gastric cancer and its precancerous lesions remains a challenge for great part of western endoscopists. Changes seen in the mucosal pattern are generally subtle and hence difficult to identify. In this article, we will review the usefulness of conventional and virtual chromoendoscopy and magnification endoscopy in the recognition and classification of these lesions.

Endoscopic diagnosis of H. pylori infection. / Diagnóstico endoscópico de la infección por H. pylori.

Helicobacter pylori (H. pylori) infection is highly prevalent in our environment and is associated with highly relevant gastric disease, both benign and malignant. The gold standard for diagnosis is histological confirmation by biopsy. However, there is increasing evidence that optical endoscopic diagnosis could have a fundamental role in avoiding unnecessary biopsies in certain cases. Specifically, the regular distribution of the collecting venules (RAC pattern) seems to have a high negative predictive value (NPV) to rule out infection. This review describes the most outstanding endoscopic findings with the best diagnostic potential for H. pylori infection after an exhaustive search comparing the most relevant studies that have been carried out in Europe and the East.

Serological levels of IGF-1 and IGFBP-3 in patients with Barrett's esophagus and esophageal adenocarcinoma: Longitudinal study. / Niveles séricos de IGF-1 e IGFBP-3 en pacientes con esófago de Barrett y adenocarcinoma de esófago. Estudio longitudinal.

BACKGROUND: Barrett's esophagus (BE) is an entity with a known histological progression to malignancy. The insulin-like growth factor (IGF) system is involved in the carcinogenesis through obesity-related mechanisms that include IGF and it has been associated with several types of cancer. OBJECTIVES: To evaluate the serological levels of IGF-1 and IGFBP-3 in patients with BE and esophageal adenocarcinoma. PATIENTS AND METHODS: Prospective study of patients with BE and esophageal adenocarcinoma who underwent upper endoscopy between September 2012 and December 2015. A baseline determination of IGF-1 and IGFBP-3 was performed. We included a control group of patients without BE. RESULTS: One hundred sixteen patients were included: 36 controls, 62 with BE (42 without dysplasia and 20 with dysplasia) and 18 with adenocarcinoma. IGF-1 and IGF-1/IGFBP-3 molar ratio showed a progression to high levels in BE and adenocarcinoma than in controls (IGF-1: 135.55±66.07ng/ml, 148.33±81.5ng/ml, 108.19±46.69ng/ml, respectively; P=.049) (molar ratio: 0.23±0.91, 0.29±0.11, 0.19±0.06, respectively; P=.001), without differences between the histological types of BE. Fifty-four out of the 65 patients with BE were followed up (median of 58.50 months, range 12-113) and 11 of them (20.4%) presented progression to low-grade dysplasia (n=8) or high-grade dysplasia/adenocarcinoma (n=3), without differences in the IGF system compared with patients without progression. CONCLUSIONS: Patients with BE and esophageal adenocarcinoma have changes in the IGF system although the serological levels of IGF-1 and IGFBP-3 do not correlate with histological progression of BE.

Wide-area transepithelial sampling with computer-assisted analysis to detect high grade dysplasia and cancer in Barrett's esophagus: a multicenter randomized study.

BACKGROUND: Current surveillance for Barrett's esophagus (BE), consisting of four-quadrant random forceps biopsies (FBs), has an inherent risk of sampling error. Wide-area transepithelial sampling (WATS) may increase detection of high grade dysplasia (HGD) and esophageal adenocarcinoma (EAC). In this multicenter randomized trial, we aimed to evaluate WATS as a substitute for FB. METHODS: Patients with known BE and a recent history of dysplasia, without visible lesions, at 17 hospitals were randomized to receive either WATS followed by FB or vice versa. All WATS samples were examined, with computer assistance, by at least two experienced pathologists at the CDx Diagnostics laboratory. Similarly, all FBs were examined by two expert pathologists. The primary end point was concordance/discordance for detection of HGD/EAC between the two techniques. RESULTS: 172 patients were included, of whom 21 had HGD/EAC detected by both modalities, 18 had HGD/EAC detected by WATS but missed by FB, and 12 were detected by FB but missed by WATS. The detection rate of HGD/EAC did not differ between WATS and FB (P = 0.36). Using WATS as an adjunct to FB significantly increased the detection of HGD/EAC vs. FB alone (absolute increase 10 % [95 %CI 6 % to 16 %]). Mean procedural times in minutes for FB alone, WATS alone, and the combination were 6.6 (95 %CI 5.9 to 7.1), 4.9 (95 %CI 4.1 to 5.4), and 11.2 (95 %CI 10.5 to 14.0), respectively. CONCLUSIONS: Although the combination of WATS and FB increases dysplasia detection in a population of BE patients enriched for dysplasia, we did not find a statistically significant difference between WATS and FB for the detection of HGD/EAC as single modality.

Artificial intelligence in gastrointestinal endoscopy — Evolution to a new era

Artificial intelligence (AI) systems based on machine learning have evolved in the last few years with increasing applicability in gastrointestinal endoscopy. Thanks to AI, animage (input) can be transformed into a clinical decision(output). Although AI systems have been studied mainly toimprove detection (CADe) and characterization of colorectalpolyps (CADx), other indications are being currently investigated, including detection of blind spots, scope guidance,and delineation/measurement of lesions.The objective of this review is to summarize the current evidence on the applicability of AI systems in gastrointestinalendoscopy, to highlight the strengths and limitations of thetechnology involved, and to review the relevant regulatoryand ethical aspects for general implementation in gastrointestinal endoscopy. (AU)

In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy.

Background and study aims Artificial intelligence is currently able to accurately predict the histology of colorectal polyps. However, systems developed to date use complex optical technologies and have not been tested in vivo. The objective of this study was to evaluate the efficacy of a new deep learning-based optical diagnosis system, ATENEA, in a real clinical setting using only high-definition white light endoscopy (WLE) and to compare its performance with endoscopists. Methods ATENEA was prospectively tested in real life on consecutive polyps detected in colorectal cancer screening colonoscopies at Hospital Clínic. No images were discarded, and only WLE was used. The in vivo ATENEA's prediction (adenoma vs non-adenoma) was compared with the prediction of four staff endoscopists without specific training in optical diagnosis for the study purposes. Endoscopists were blind to the ATENEA output. Histology was the gold standard. Results Ninety polyps (median size: 5 mm, range: 2-25) from 31 patients were included of which 69 (76.7 %) were adenomas. ATENEA correctly predicted the histology in 63 of 69 (91.3 %, 95 % CI: 82 %-97 %) adenomas and 12 of 21 (57.1 %, 95 % CI: 34 %-78 %) non-adenomas while endoscopists made correct predictions in 52 of 69 (75.4 %, 95 % CI: 60 %-85 %) and 20 of 21 (95.2 %, 95 % CI: 76 %-100 %), respectively. The global accuracy was 83.3 % (95 % CI: 74%-90 %) and 80 % (95 % CI: 70 %-88 %) for ATENEA and endoscopists, respectively. Conclusion ATENEA can accurately be used for in vivo characterization of colorectal polyps, enabling the endoscopist to make direct decisions. ATENEA showed a global accuracy similar to that of endoscopists despite an unsatisfactory performance for non-adenomatous lesions.