An Interactive Web-Based Educational Tool Improves Detection and Delineation of Barrett's Esophagus-Related Neoplasia

Will Transformers change gastrointestinal endoscopic image analysis? A comparative analysis between CNNs and Transformers, in terms of performance, robustness and generalization

Gastrointestinal endoscopic image analysis presents significant challenges, such as considerable variations in quality due to the challenging in-body imaging environment, the often-subtle nature of abnormalities with low interobserver agreement, and the need for real-time processing. These challenges pose strong requirements on the performance, generalization, robustness and complexity of deep learning-based techniques in such safety-critical applications. While Convolutional Neural Networks (CNNs) have been the go-to architecture for endoscopic image analysis, recent successes of the Transformer architecture in computer vision raise the possibility to update this conclusion. To this end, we evaluate and compare clinically relevant performance, generalization and robustness of state-of-the-art CNNs and Transformers for neoplasia detection in Barrett's esophagus. We have trained and validated several top-performing CNNs and Transformers on a total of 10,208 images (2,079 patients), and tested on a total of 7,118 images (998 patients) across multiple test sets, including a high-quality test set, two internal and two external generalization test sets, and a robustness test set. Furthermore, to expand the scope of the study, we have conducted the performance and robustness comparisons for colonic polyp segmentation (Kvasir-SEG) and angiodysplasia detection (Giana). The results obtained for featured models across a wide range of training set sizes demonstrate that Transformers achieve comparable performance as CNNs on various applications, show comparable or slightly improved generalization capabilities and offer equally strong resilience and robustness against common image corruptions and perturbations. These findings confirm the viability of the Transformer architecture, particularly suited to the dynamic nature of endoscopic video analysis, characterized by fluctuating image quality, appearance and equipment configurations in transition from hospital to hospital. The code is made publicly available at: https://github.com/BONS-AI-VCA-AMC/Endoscopy-CNNs-vs-Transformers.

The use of a real-time computer-aided detection system for visible lesions in the Barrett's esophagus during live endoscopic procedures: a pilot study (with video)

BACKGROUND AND AIMS

This pilot study evaluated the performance of a recently developed computer-aided detection (CADe) system for Barrett's neoplasia during live endoscopic procedures.

METHODS

Fifteen patients with a visible lesion and 15 without were included in this study. A CAD-assisted workflow was used that included a slow pullback video recording of the entire Barrett's segment with live CADe assistance, followed by CADe-assisted level-based video recordings every 2 cm of the Barrett's segment. Outcomes were per-patient and per-level diagnostic accuracy of the CAD-assisted workflow, in which the primary outcome was per-patient in vivo CADe sensitivity.

RESULTS

In the per-patient analyses, the CADe system detected all visible lesions (sensitivity 100%). Per-patient CADe specificity was 53%. Per-level sensitivity and specificity of the CADe-assisted workflow were 100% and 73%, respectively.

CONCLUSIONS

In this pilot study, detection by the CADe system of all potentially neoplastic lesions in Barrett's esophagus was comparable to that of an expert endoscopist. Continued refinement of the system may improve specificity. External validation in larger multicenter studies is planned. (Clinical trial registration number: NCT05628441.).

Effect of an online educational module incorporating real-time feedback on accuracy of polyp sizing in trainees: a randomized controlled trial

BACKGROUND

Although polyp size dictates surveillance intervals, endoscopists often estimate polyp size inaccurately. We hypothesized that an intervention providing didactic instruction and real-time feedback could significantly improve polyp size classification.

METHODS

We conducted a multicenter randomized controlled trial to evaluate the impact of different components of an online educational module on polyp sizing. Participants were randomized to control (no video, no feedback), video only, feedback only, or video + feedback. The primary outcome was accuracy of polyp size classification into clinically relevant categories (diminutive [1-5mm], small [6-9mm], large [≥10mm]). Secondary outcomes included accuracy of exact polyp size (inmm), learning curves, and directionality of inaccuracy (over- vs. underestimation).

RESULTS

36 trainees from five training programs provided 1360 polyp size assessments. The feedback only (80.1%, P=0.01) and video + feedback (78.9%, P=0.02) groups had higher accuracy of polyp size classification compared with controls (71.6%). There was no significant difference in accuracy between the video only group (74.4%) and controls (P=0.42). Groups receiving feedback had higher accuracy of exact polyp size (inmm) and higher peak learning curves. Polyps were more likely to be overestimated than underestimated, and 29.3% of size inaccuracies impacted recommended surveillance intervals.

CONCLUSIONS

Our online educational module significantly improved polyp size classification. Real-time feedback appeared to be a critical component in improving accuracy. This scalable and no-cost educational module could significantly decrease under- and overutilization of colonoscopy, improving patient outcomes while increasing colonoscopy access.

Quality indicators in Barrett's endoscopy: Best is yet to come

There is growing interest in establishing quality indicators (QIs) for endoscopic screening and surveillance in Barrett's esophagus (BE). QIs are objective, measurable, and evidence-based metrics that are applicable in a health-care setting to monitor a process and identify key performance indicators (KPIs) to achieve defined goals. In the Barrett's endoscopy setting, QIs can offer a standardized approach to monitor and maintain high-quality endoscopy for BE screening and surveillance that will allow measuring performance of an endoscopist as an individual, a group, or a facility. Since BE is an endoscopically identifiable premalignant condition with histological corroboration, adherence to QIs is paramount for the early and accurate detection of dysplasia and neoplasia. It is the holy grail for BE screening and surveillance. Although several suggested QIs for Barrett's endoscopy exist, issues remain in determining the most appropriate ones. These issues include inconsistent use of terminology, unclear definitions, and a scarcity of studies linking these QIs with relevant patient outcomes, making it difficult for clinicians to understand the concept and clinical importance. Hence, there is an urgent need to determine what should constitute appropriate QIs for Barrett's endoscopy, clearly define items used in the QIs, and identify ways to measure these KPIs. Ultimately, well-defined and validated QIs will contribute to clinically effective, safe, timely, and patient-focused care. In this review, we summarize recent literature and discuss four proposed QIs: (i) neoplasia detection rate; (ii) postendoscopy Barrett's neoplasia; (iii) Barrett's inspection time; and (iv) adherence to the Seattle biopsy protocol.

Management of high risk T1 esophageal adenocarcinoma following endoscopic resection

High-risk T1 esophageal adenocarcinoma (HR-T1 EAC) is defined as T1 cancer, with one or more of the following histological criteria: submucosal invasion, poorly or undifferentiated cancer, and/or presence of lympho-vascular invasion. Esophagectomy has long been the only available treatment for these HR-T1 EACs and was considered necessary because of a presumed high risk of lymph node metastases up to 46%. However, endoscopic submucosal disscection have made it possible to radically remove HR-T1 EAC, irrespective of size, while leaving the esophageal anatomy intact. Parallel to this development, new publications demonstrated that the risk of lymph node metastases for HR-T1 EAC may be even <24%. Therefore, indications for endoscopic treatment of HR-T1 EAC are being reconsidered and current research aims at finding the optimal management strategy for this indication, where watchful waiting may proof to be an acceptable strategy in selected patients. In this review, we will discuss the latest developments in this field.

A deep learning system for detection of early Barrett's neoplasia: a model development and validation study

BACKGROUND

Computer-aided detection (CADe) systems could assist endoscopists in detecting early neoplasia in Barrett's oesophagus, which could be difficult to detect in endoscopic images. The aim of this study was to develop, test, and benchmark a CADe system for early neoplasia in Barrett's oesophagus.

METHODS

The CADe system was first pretrained with ImageNet followed by domain-specific pretraining with GastroNet. We trained the CADe system on a dataset of 14 046 images (2506 patients) of confirmed Barrett's oesophagus neoplasia and non-dysplastic Barrett's oesophagus from 15 centres. Neoplasia was delineated by 14 Barrett's oesophagus experts for all datasets. We tested the performance of the CADe system on two independent test sets. The all-comers test set comprised 327 (73 patients) non-dysplastic Barrett's oesophagus images, 82 (46 patients) neoplastic images, 180 (66 of the same patients) non-dysplastic Barrett's oesophagus videos, and 71 (45 of the same patients) neoplastic videos. The benchmarking test set comprised 100 (50 patients) neoplastic images, 300 (125 patients) non-dysplastic images, 47 (47 of the same patients) neoplastic videos, and 141 (82 of the same patients) non-dysplastic videos, and was enriched with subtle neoplasia cases. The benchmarking test set was evaluated by 112 endoscopists from six countries (first without CADe and, after 6 weeks, with CADe) and by 28 external international Barrett's oesophagus experts. The primary outcome was the sensitivity of Barrett's neoplasia detection by general endoscopists without CADe assistance versus with CADe assistance on the benchmarking test set. We compared sensitivity using a mixed-effects logistic regression model with conditional odds ratios (ORs; likelihood profile 95% CIs).

FINDINGS

Sensitivity for neoplasia detection among endoscopists increased from 74% to 88% with CADe assistance (OR 2·04; 95% CI 1·73-2·42; p<0·0001 for images and from 67% to 79% [2·35; 1·90-2·94; p<0·0001] for video) without compromising specificity (from 89% to 90% [1·07; 0·96-1·19; p=0·20] for images and from 96% to 94% [0·94; 0·79-1·11; ] for video; p=0·46). In the all-comers test set, CADe detected neoplastic lesions in 95% (88-98) of images and 97% (90-99) of videos. In the benchmarking test set, the CADe system was superior to endoscopists in detecting neoplasia (90% vs 74% [OR 3·75; 95% CI 1·93-8·05; p=0·0002] for images and 91% vs 67% [11·68; 3·85-47·53; p<0·0001] for video) and non-inferior to Barrett's oesophagus experts (90% vs 87% [OR 1·74; 95% CI 0·83-3·65] for images and 91% vs 86% [2·94; 0·99-11·40] for video).

INTERPRETATION

CADe outperformed endoscopists in detecting Barrett's oesophagus neoplasia and, when used as an assistive tool, it improved their detection rate. CADe detected virtually all neoplasia in a test set of consecutive cases.

FUNDING

Olympus.

Deep learning based identification of pituitary adenoma on surgical endoscopic images: a pilot study

Accurate tumor identification during surgical excision is necessary for neurosurgeons to determine the extent of resection without damaging the surrounding tissues. No conventional technologies have achieved reliable performance for pituitary adenomas. This study proposes a deep learning approach using intraoperative endoscopic images to discriminate pituitary adenomas from non-tumorous tissue inside the sella turcica. Static images were extracted from 50 intraoperative videos of patients with pituitary adenomas. All patients underwent endoscopic transsphenoidal surgery with a 4 K ultrahigh-definition endoscope. The tumor and non-tumorous tissue within the sella turcica were delineated on static images. Using intraoperative images, we developed and validated deep learning models to identify tumorous tissue. Model performance was evaluated using a fivefold per-patient methodology. As a proof-of-concept, the model's predictions were pathologically cross-referenced with a medical professional's diagnosis using the intraoperative images of a prospectively enrolled patient. In total, 605 static images were obtained. Among the cropped 117,223 patches, 58,088 were labeled as tumors, while the remaining 59,135 were labeled as non-tumorous tissues. The evaluation of the image dataset revealed that the wide-ResNet model had the highest accuracy of 0.768, with an F1 score of 0.766. A preliminary evaluation on one patient indicated alignment between the ground truth set by neurosurgeons, the model's predictions, and histopathological findings. Our deep learning algorithm has a positive tumor discrimination performance in intraoperative 4-K endoscopic images in patients with pituitary adenomas.

Magnitude and Time-Trends of Post-Endoscopy Esophageal Adenocarcinoma and Post-Endoscopy Esophageal Neoplasia in a Population-Based Cohort Study: The Nordic Barrett's Esophagus Study

BACKGROUND & AIMS

Post-endoscopy esophageal adenocarcinoma (PEEC) and post-endoscopy esophageal neoplasia (PEEN) undermine early cancer detection in Barrett's esophagus (BE). We aimed to assess the magnitude and conduct time-trend analysis of PEEC and PEEN among patients with newly diagnosed BE.

METHODS

This population-based cohort study was conducted in Denmark, Finland, and Sweden between 2006 and 2020 and included 20,588 patients with newly diagnosed BE. PEEC and PEEN were defined as esophageal adenocarcinoma (EAC) or high-grade dysplasia (HGD)/EAC, respectively, diagnosed 30-365 days from BE diagnosis (index endoscopy). HGD/EAC diagnosed from 0-29 days and HGD/EAC diagnosed >365 days from BE diagnosis (incident HGD/EAC) were assessed. Patients were followed up until HGD/EAC, death, or end of study period. Incidence rates (IR) per 100,000 person-years with 95% confidence interval (95% CI) were calculated using Poisson regression.

RESULTS

Among 293 patients diagnosed with EAC, 69 (23.5%) were categorized as PEEC, 43 (14.7%) as index EAC, and 181 (61.8%) as incident EAC. The IRs/100,000 person-years for PEEC and incident EAC were 392 (95% CI, 309-496), and 208 (95% CI, 180-241), respectively. Among 279 patients diagnosed with HGD/EAC (Sweden only), 17.2% were categorized as PEEN, 14.6% as index HGD/EAC, and 68.1% as incident HGD/EAC. IRs/100,000 person-years for PEEN, and incident HGD/EAC were 421 (95% CI, 317-558), and 285 (95% CI, 247-328), respectively. Sensitivity analyses that varied time interval for occurrence of PEEC/PEEN demonstrated similar results. A time-trend analysis for IRs demonstrated rising incidence rates of PEEC/PEEN.

CONCLUSIONS

Almost a quarter of all EACs are detected within a year after an ostensibly negative upper endoscopy in patients with newly diagnosed BE. Interventions to improve detection may reduce PEEC/PEEN rates.

High Proportions of Newly Detected Visible Lesions and Pathology Grade Change Among Patients with Barrett's Esophagus Referred to Expert Centers

BACKGROUND AND AIMS

Endoscopic eradication therapy for Barrett's esophagus (BE)-related neoplasia is increasingly being performed at tertiary and community centers. While it has been suggested that these patients should be evaluated at expert centers, the impact of this practice has not been evaluated. We aimed to assess the impact of referral of BE-related neoplasia patients to expert centers by assessing the proportion of patients with change in pathological diagnosis and visible lesions detected.

METHODS

Multiple databases were searched until December 2021 for studies of patients with BE referred from the community to expert center. The proportions of pathology grade change and newly detected visible lesions at expert centers were pooled using a random-effects model. Subgroup analyses were performed based on baseline histology and other relevant factors.

RESULTS

Twelve studies were included (1630 patients). The pooled proportion of pathology grade change after expert pathologist review was 47% (95% CI 34-59%) overall and 46% (95% CI 31-62%) among patients with baseline low-grade dysplasia. When upper endoscopy was repeated at an expert center, the pooled proportion of pathology grade change was still high 47% (95% 26-69%) overall and 40% (95% CI 34-45%) among patients with baseline LGD. The pooled proportion of newly detected visible lesions was 45% (95% CI 28-63%) and among patients referred with LGD was 27% (95% CI 22-32%).

CONCLUSION

An alarmingly high proportion of newly detected visible lesions and pathology grade change were found when patients were referred to expert centers supporting the need for centralized care for BE-related neoplasia patients.

Learning Outcomes and Educational Effectiveness of E-Learning as a Continuing Professional Development Intervention for Practicing Surgeons and Proceduralists: A Systematic Review

BACKGROUND

Electronic learning (e-Learning) has become a prevalent mode of delivering medical education. We aimed to determine the learning outcomes and educational effectiveness of e-Learning as a continuing professional development (CPD) intervention for practicing surgeons and proceduralists.

METHODS

We searched MEDLINE databases and included studies reporting learning outcomes of e-learning CPD interventions for practicing surgeons and physicians performing technical procedures. We excluded articles only studying surgical trainees and those not reporting learning outcomes. Two reviewers independently screened, extracted data, and assessed study quality using the Critical Appraisal Skills Programme (CASP) tools. Learning outcomes and educational effectiveness were categorized using Moore's Outcomes Framework (PROSPERO: CRD42022333523).

RESULTS

Of 1307 identified articles, 12 were included- 9 cohort studies, one randomized controlled trial and 2 qualitative studies, with a total of 2158 participants. Eight studies were rated as moderate, five as strong, and 2 as weak in study quality. E-Learning CPD interventions included web-based modules, image recognition, videos, a repository of videos and schematics, and an online journal club. Seven studies reported participants' satisfaction with the e-Learning interventions (Moore's Level 2), 4 reported improvements in participants' declarative knowledge (Level 3a), 1 reported improvements in procedural knowledge (Level 3b) and five reported improvements in participants' procedural competence in an educational setting (Level 4). No studies demonstrated improvements in participants' workplace-based performance, the health of patients, or community health (Levels 5-7).

CONCLUSIONS

E-Learning as a CPD educational intervention is associated with high satisfaction and improvements in knowledge and procedural competencies of practicing surgeons and proceduralists in an educational setting. Future research is required to investigate whether e-Learning is associated with higher-level learning outcomes.

Towards a robust and compact deep learning system for primary detection of early Barrett's neoplasia: Initial image-based results of training on a multi-center retrospectively collected data set

INTRODUCTION

Endoscopic detection of early neoplasia in Barrett's esophagus is difficult. Computer Aided Detection (CADe) systems may assist in neoplasia detection. The aim of this study was to report the first steps in the development of a CADe system for Barrett's neoplasia and to evaluate its performance when compared with endoscopists.

METHODS

This CADe system was developed by a consortium, consisting of the Amsterdam University Medical Center, Eindhoven University of Technology, and 15 international hospitals. After pretraining, the system was trained and validated using 1.713 neoplastic (564 patients) and 2.707 non-dysplastic Barrett's esophagus (NDBE; 665 patients) images. Neoplastic lesions were delineated by 14 experts. The performance of the CADe system was tested on three independent test sets. Test set 1 (50 neoplastic and 150 NDBE images) contained subtle neoplastic lesions representing challenging cases and was benchmarked by 52 general endoscopists. Test set 2 (50 neoplastic and 50 NDBE images) contained a heterogeneous case-mix of neoplastic lesions, representing distribution in clinical practice. Test set 3 (50 neoplastic and 150 NDBE images) contained prospectively collected imagery. The main outcome was correct classification of the images in terms of sensitivity.

RESULTS

The sensitivity of the CADe system on test set 1 was 84%. For general endoscopists, sensitivity was 63%, corresponding to a neoplasia miss-rate of one-third of neoplastic lesions and a potential relative increase in neoplasia detection of 33% for CADe-assisted detection. The sensitivity of the CADe system on test sets 2 and 3 was 100% and 88%, respectively. The specificity of the CADe system varied for the three test sets between 64% and 66%.

CONCLUSION

This study describes the first steps towards the establishment of an unprecedented data infrastructure for using machine learning to improve the endoscopic detection of Barrett's neoplasia. The CADe system detected neoplasia reliably and outperformed a large group of endoscopists in terms of sensitivity.

Surveillance in Barrett's Esophagus: Challenges, Progress, and Possibilities

Endoscopic surveillance of Barrett's esophagus, aiming to detect prevalent dysplasia and adenocarcinoma, followed by effective endoscopic treatment, is an integral part of the esophageal adenocarcinoma prevention paradigm. However, several limitations, such as the subtle appearance of dysplasia, sampling error (inherent in current surveillance protocols), and noncompliance with surveillance recommendations, lead to missed dysplasia and neoplasia, reducing the effectiveness of surveillance as currently practiced. Careful endoscopic assessment with high-resolution white-light endoscopy, dye-based or electronic chromoendoscopy, and comprehensive sampling of the BE mucosa, remains the cornerstone of endoscopic surveillance. Emerging innovations in this area span the gamut of more efficient sampling methods, advanced imaging tools, artificial intelligence, and molecular marker-powered approaches as adjuncts, to identify prevalent and predict incident dysplasia or adenocarcinoma. Development and implementation of validated quality indicators will allow additional advancement of this critical field. These approaches will hopefully enable efficient and effective cancer prevention and treatment.

Interactive training versus self-driven training in the prediction of colorectal polyp histology by trainees using the NICE classification

BACKGROUND

The COVID-19 pandemic has impacted endoscopic training of the Narrow Band Imaging International Colorectal Endoscopic (NICE) classification, which could accurately predict pathology of colorectal polyps. This study aimed to evaluate the diagnostic performance by trainees of self-driven training vs. interactive training in the prediction of colorectal polyp histology.

METHODS

This was a prospective randomized controlled study at five academic centers from January 1, 2021 to May 31, 2021. Trainees with no previous formal training of narrow band imaging or blue light imaging for prediction of colorectal polyp histology were randomly allocated to the self-driven training group or interactive training group. Before and after the training, all trainees were given 20 selected cases of colorectal polyp for testing. Their diagnostic performance was analyzed.

RESULTS

Overall, the two training groups showed similar accuracy of NICE classification (79.3% vs. 78.1%; P = 0.637), vessel analysis (77.8% vs. 77.6%, P = 0.939), and surface pattern analysis (78.1% vs. 76.9%, P = 0.616). The accuracy of color analysis in the interactive training group was better (74.4% vs. 80.0%, P = 0.027). For high-confidence predictions, the self-driven training group showed higher accuracy of NICE classification (84.8% vs. 78.7%, P < 0.001) but no difference for analysis of color (79.6% vs. 81.0%), vessel pattern (83.0% vs. 78.5%), and surface pattern (81.8% vs. 78.5%).

CONCLUSIONS

Overall, self-driven training showed comparable accuracy of NICE classification, vessel pattern, and surface pattern to interactive training, but lower accuracy of color analysis. This method showed comparable effectiveness and is more applicable than interactive training. It is worth spreading during the COVID-19 pandemic. Trial registration Name of the registry: Chinese Clinical Trial Registry, Trial registration number: ChiCTR2000031659, Date of registration: 06/04/2020, URL of trial registry record: http://www.chictr.org.cn/showproj.aspx?proj=51994.

Green endoscopy: British Society of Gastroenterology (BSG), Joint Accreditation Group (JAG) and Centre for Sustainable Health (CSH) joint consensus on practical measures for environmental sustainability in endoscopy

GI endoscopy is highly resource-intensive with a significant contribution to greenhouse gas (GHG) emissions and waste generation. Sustainable endoscopy in the context of climate change is now the focus of mainstream discussions between endoscopy providers, units and professional societies. In addition to broader global challenges, there are some specific measures relevant to endoscopy units and their practices, which could significantly reduce environmental impact. Awareness of these issues and guidance on practical interventions to mitigate the carbon footprint of GI endoscopy are lacking. In this consensus, we discuss practical measures to reduce the impact of endoscopy on the environment applicable to endoscopy units and practitioners. Adoption of these measures will facilitate and promote new practices and the evolution of a more sustainable specialty.

Wide Variability in Dysplasia Detection Rate and Adherence to Seattle Protocol and Surveillance Recommendations in Barrett' Esophagus: A Population-Based Analysis using the GIQuIC National Quality Benchmarking Registry

INTRODUCTION

Variability in adherence rates to the Seattle protocol and to surveillance interval recommendations, established quality indicators (QIs) in Barrett's esophagus (BE), are unknown.

METHODS

We evaluated endoscopist and site-based adherence rates to these QIs from 1/2018-5/2021 using the GI Quality Improvement Consortium (GIQuIC) national registry with matched endoscopy and pathology data.

RESULTS

Across 153 practices with 572 endoscopists performing 20,155 endoscopies, adherence to Seattle protocol varied by endoscopists (median 93.8%, IQR 18.9%) and by site (median 90.0%, IQR 20.1%). Adherence to appropriate surveillance intervals for nondysplastic BE also varied by endoscopist (median 82.4%, IQR 36.3%) and site (median 77.2%, IQR 29.8%). Overall dysplasia detection rate was 3.1% and varied among endoscopists and sites.

CONCLUSION

These US population-based results can serve as a benchmark for quality initiatives and intervention trials aimed at improving outcomes for BE patients.

Interventions to improve the performance of upper GI endoscopy quality indicators

The promotion of quality and best practices in gastroenterology and endoscopy is an ongoing effort. For upper GI endoscopy, quality indicators derived from clinical studies and expert consensus have been long established but remain variably obtained. To date, data on interventions aimed to improve these indicators are scarce. We systematically reviewed the literature to identify interventions and measures demonstrated to improve the performance of previously established upper endoscopy quality indicators. We also identified evidence gaps and opportunities for improvement in this area.

Management of nondysplastic Barrett’s esophagus: When to survey? When to ablate?

Barrett’s esophagus (BE), a precursor for esophageal adenocarcinoma (EAC), is defined as salmon-colored mucosa extending more than 1 cm proximal to the gastroesophageal junction with histological evidence of intestinal metaplasia. The actual risk of EAC in nondysplastic Barrett’s esophagus (NDBE) is low with an annual incidence of 0.3%. The mainstay in the management of NDBE is control of gastroesophageal reflux disease (GERD) along with enrollment in surveillance programs. The current recommendation for surveillance is four-quadrant biopsies every 2 cm (or 1 cm in known or suspected dysplasia) followed by biopsy of mucosal irregularity (nodules, ulcers, or other visible lesions) performed at 3- to 5-year intervals. Challenges to surveillance include missed cancers, suboptimal adherence to surveillance guidelines, and lack of strong evidence for efficacy. There is minimal role for endoscopic eradication therapy in NDBE. The role for enhanced imaging techniques, artificial intelligence, and risk prediction models using clinical data and molecular markers is evolving.

Artificial Intelligence and Deep Learning for Upper Gastrointestinal Neoplasia

Upper gastrointestinal (GI) neoplasia account for 35% of GI cancers and 1.5 million cancer-related deaths every year. Despite its efficacy in preventing cancer mortality, diagnostic upper GI endoscopy is affected by a substantial miss rate of neoplastic lesions due to failure to recognize a visible lesion or imperfect navigation. This may be offset by the real-time application of artificial intelligence (AI) for detection (computer-aided detection [CADe]) and characterization (computer-aided diagnosis [CADx]) of upper GI neoplasia. Stand-alone performance of CADe for esophageal squamous cell neoplasia, Barrett's esophagus-related neoplasia, and gastric cancer showed promising accuracy, sensitivity ranging between 83% and 93%. However, incorporation of CADe/CADx in clinical practice depends on several factors, such as possible bias in the training or validation phases of these algorithms, its interaction with human endoscopists, and clinical implications of false-positive results. The aim of this review is to guide the clinician across the multiple steps of AI development in clinical practice.

Impact of expert center endoscopic assessment of confirmed low grade dysplasia in Barrett's esophagus diagnosed in community hospitals

BACKGROUND : The optimal management for patients with low grade dysplasia (LGD) in Barrett's esophagus (BE) is unclear. According to the Dutch national guideline, all patients with LGD with histological confirmation of the diagnosis by an expert pathologist (i. e. "confirmed LGD"), are referred for a dedicated re-staging endoscopy at an expert center. We aimed to assess the diagnostic value of re-staging endoscopy by an expert endoscopist for patients with confirmed LGD. METHODS : This retrospective cohort study included all patients with flat BE diagnosed in a community hospital who had confirmed LGD and were referred to one of the nine Barrett Expert Centers (BECs) in the Netherlands. The primary outcome was the proportion of patients with prevalent high grade dysplasia (HGD) or cancer during re-staging in a BEC. RESULTS : Of the 248 patients with confirmed LGD, re-staging in the BEC revealed HGD or cancer in 23 % (57/248). In 79 % (45/57), HGD or cancer in a newly detected visible lesion was diagnosed. Of the remaining patients, re-staging in the BEC showed a second diagnosis of confirmed LGD in 68 % (168/248), while the remaining 9 % (23/248) had nondysplastic BE. CONCLUSION : One quarter of patients with apparent flat BE with confirmed LGD diagnosed in a community hospital had prevalent HGD or cancer after re-staging at an expert center. This endorses the advice to refer patients with confirmed LGD, including in the absence of visible lesions, to an expert center for re-staging endoscopy.

Long-term outcomes after endoscopic treatment for Barrett's neoplasia with radiofrequency ablation ± endoscopic resection: results from the national Dutch database in a 10-year period

OBJECTIVE

Radiofrequency ablation (RFA)±endoscopic resection (ER) is the preferred treatment for early neoplasia in Barrett's oesophagus (BE). We aimed to report short-term and long-term outcomes for all 1384 patients treated in the Netherlands (NL) from 2008 to 2018, with uniform treatment and follow-up (FU) in a centralised setting.

DESIGN

Endoscopic therapy for early BE neoplasia in NL is centralised in nine expert centres with specifically trained endoscopists and pathologists that adhere to a joint protocol. Prospectively collected data are registered in a uniform database. Patients with low/high-grade dysplasia or low-risk cancer, were treated by ER of visible lesions followed by trimonthly RFA sessions of any residual BE until complete eradication of BE (CE-BE). Patients with ER alone were not included.

RESULTS

After ER (62% of cases; 43% low-risk cancers) and median 1 circumferential and 2 focal RFA (p25-p75 0-1; 1-2) per patient, CE-BE was achieved in 94% (1270/1348). Adverse events occurred in 21% (268/1386), most commonly oesophageal stenosis (15%), all were managed endoscopically. A total of 1154 patients with CE-BE were analysed for long-term outcomes. During median 43 months (22-69) and 4 endoscopies (1-5), 38 patients developed dysplastic recurrence (3%, annual recurrence risk 1%), all were detected as endoscopically visible abnormalities. Random biopsies from a normal appearing cardia showed intestinal metaplasia (IM) in 14% and neoplasia in 0%. A finding of IM in the cardia was reproduced during further FU in only 33%, none progressed to neoplasia. Frequent FU visits in the first year of FU were not associated with recurrence risk.

CONCLUSION

In a setting of centralised care, RFA±ER is effective for eradication of Barrett's related neoplasia and has remarkably low rates of dysplastic recurrence. Our data support more lenient FU intervals, with emphasis on careful endoscopic inspection. Random biopsies from neosquamous epithelium and cardia are of questionable value.

NETHERLANDS TRIAL REGISTER NUMBER

NL7039.

Magnitude and Time-Trend Analysis of Postendoscopy Esophageal Adenocarcinoma: A Systematic Review and Meta-analysis

BACKGROUND & AIMS

Identification of postendoscopy esophageal adenocarcinoma (PEEC) among Barrett's esophagus (BE) patients presents an opportunity to improve survival of esophageal adenocarcinoma (EAC). We aimed to estimate the proportion of PEEC within the first year after BE diagnosis.

METHODS

Multiple databases (Medline, Embase, Scopus, and Cochrane databases) were searched until September 2020 for original studies with at least 1-year follow-up evaluation that reported EAC and/or high-grade dysplasia (HGD) in the first year after index endoscopy in nondysplastic BE, low-grade dysplasia, or indefinite dysplasia. The proportions of PEEC defined using EAC alone and EAC+HGD were calculated by dividing EAC or EAC+HGD in the first year over the total number of EAC or EAC+HGD, respectively.

RESULTS

We included 52 studies with 145,726 patients and a median follow-up period of 4.8 years. The proportion of PEEC (EAC) was 21% (95% CI, 13-31) and PEEC (EAC+HGD) was 26% (95% CI, 19-34). Among studies with nondysplastic BE only, the PEEC (EAC) proportion was 17% (95% CI, 11-23) and PEEC (EAC+HGD) was 14% (95% CI, 8-19). Among studies with 5 or more years of follow-up evaluation, the PEEC (EAC) proportion was 10% and PEEC (EAC+HGD) was 19%. Meta-regression analysis showed a strong inverse relationship between PEEC and incident EAC (P < .001). The PEEC (EAC) proportion increased from 5% in studies published before 2000 to 30% after 2015. Substantial heterogeneity was observed for most analyses.

CONCLUSIONS

PEEC accounts for a high proportion of HGD/EACs and is proportional to reduction in incident EAC. Using best endoscopic techniques now and performing future research on improving neoplasia detection through implementation of quality measures and educational tools is needed to reduce PEEC.

JAG consensus statements for training and certification in oesophagogastroduodenoscopy

INTRODUCTION

Training and quality assurance in oesophagogastroduodenoscopy (OGD) is important to ensure competent practice. A national evidence-based review was undertaken to update and develop standards and recommendations for OGD training and certification.

METHODS

Under the oversight of the Joint Advisory Group (JAG), a modified Delphi process was conducted with stakeholder representation from British Society of Gastroenterology, Association of Upper Gastrointestinal Surgeons, trainees and trainers. Recommendations on OGD training and certification were formulated following literature review and appraised using Grading of Recommendations Assessment, Development and Evaluation. These were subjected to electronic voting to achieve consensus. Accepted statements were incorporated into the updated certification pathway.

RESULTS

In total, 32 recommendation statements were generated for the following domains: definition of competence (4 statements), acquisition of competence (12 statements), assessment of competence (10 statements) and post-certification support (6 statements). The consensus process led to following certification criteria: (1) performing ≥250 hands-on procedures; (2) attending a JAG-accredited basic skills course; (3) attainment of relevant minimal performance standards defined by British Society of Gastroenterology/Association of Upper Gastrointestinal Surgeons of Great Britain and Ireland, (4) achieving physically unassisted D2 intubation and J-manoeuvre in ≥95% of recent procedures, (5) satisfactory performance in formative and summative direct observation of procedural skills assessments.

CONCLUSION

The JAG standards for diagnostic OGD have been updated following evidence-based consensus. These standards are intended to support training, improve competency assessment to uphold standards of practice and provide support to the newly-independent practitioner.

Dysplasia in Random Biopsies from Barrett's Surveillance Is an Important Marker for More Severe Pathology

BACKGROUND AND AIM

Although endoscopic recognition of dysplasia in Barrett's esophagus is difficult, experience in recognition of early neoplastic lesions is supposed to increase the detection of early neoplastic lesions. The aim of this study was to assess the significance of dysplasia in random biopsies in Barrett's esophagus, in the absence of reported visible lesions as well as the difference in final outcome of pathology.

METHODS

We retrospectively identified all patients with Barrett's esophagus with suspicion of dysplasia or early adenocarcinoma who were referred to our center between February 2008 and April 2016. We analyzed all endoscopy reports, pathology reports, and referral letters from 19 different hospitals. Patients were divided into two groups, based on the presence or absence of visible lesions reported upon referral.

RESULTS

In total, 170 patients diagnosed with dysplasia or adenocarcinoma were referred to our tertiary center. Ninety-one of these referred patients were referred with dysplasia or adenocarcinoma in random biopsies, without a reported lesion during endoscopy in the referral center. During endoscopic work-up at our center, a visible lesion was detected in 44 of these 91 patients (48.4%). After endoscopic work-up and treatment, adenocarcinoma was found in an additional 21 patients. Two of these patients were initially referred with low-grade dysplasia, and 19 patients were initially referred with high-grade dysplasia. The final pathology was upstaged in 35.8% of the patients.

CONCLUSIONS

The presence of any grade of dysplasia in random biopsies during surveillance in referral centers is a marker for more severe final pathology. Training in recognition of early neoplastic lesions in Barrett's esophagus imaging is recommended for endoscopists performing Barrett's surveillance.

Revising the European Society of Gastrointestinal Endoscopy (ESGE) research priorities: a research progress update

BACKGROUND

One of the aims of the European Society of Gastrointestinal Endoscopy (ESGE) is to encourage high quality endoscopic research at a European level. In 2016, the ESGE research committee published a set of research priorities. As endoscopic research is flourishing, we aimed to review the literature and determine whether endoscopic research over the last 4 years had managed to address any of our previously published priorities.

METHODS

As the previously published priorities were grouped under seven different domains, a working party with at least two European experts was created for each domain to review all the priorities under that domain. A structured review form was developed to standardize the review process. The group conducted an extensive literature search relevant to each of the priorities and then graded the priorities into three categories: (1) no longer a priority (well-designed trial, incorporated in national/international guidelines or adopted in routine clinical practice); (2) remains a priority (i. e. the above criterion was not met); (3) redefine the existing priority (i. e. the priority was too vague with the research question not clearly defined).

RESULTS

The previous ESGE research priorities document published in 2016 had 26 research priorities under seven domains. Our review of these priorities has resulted in seven priorities being removed from the list, one priority being partially removed, another seven being redefined to make them more precise, with eleven priorities remaining unchanged. This is a reflection of a rapid surge in endoscopic research, resulting in 27 % of research questions having already been answered and another 27 % requiring redefinition.

CONCLUSIONS

Our extensive review process has led to the removal of seven research priorities from the previous (2016) list, leaving 19 research priorities that have been redefined to make them more precise and relevant for researchers and funding bodies to target.

Current Trends in Endoscopic Diagnosis and Treatment of Early Esophageal Cancer

Simple Summary

Early esophageal cancer is diagnosed in the context of reflux disease, surveillance of Barrett’s metaplasia, or during upper gastrointestinal endoscopy for other indications. High definition and virtual or dye chromoendoscopy are mandatory for the screening and evaluation of neoplasia. Endoscopic treatment options include endoscopic mucosal resection (EMR) or endoscopic submucosal dissection (ESD). Resection is considered curative if histopathology confirms low or absent risk of lymph node metastasis. Barrett’s high-grade dysplasia or early adenocarcinoma is treated by EMR or ESD, followed by ablation of Barrett’s epithelium to avoid metachronous cancer. ESD is the treatment of choice for squamous cell neoplasia. Excellent outcomes have been reported if the ESD of squamous cell cancer with slight submucosal infiltration and thus substantial risk for lymph node metastasis was combined with adjuvant chemo-radiotherapy. In contrast, infiltration of squamous cell cancer exceeding the lamina propria mucosae is not curative. However, despite a substantial risk of lymph node metastasis, excellent outcomes have recently been reported if endoscopic resection of tumors with up to 200 µm submucosal infiltration was combined with adjuvant chemo-radiotherapy.

Abstract

Diagnosis of esophageal adenocarcinoma mostly occurs in the context of reflux disease or surveillance of Barrett’s metaplasia. Optimal detection rates are obtained with high definition and virtual or dye chromoendoscopy. Smaller lesions can be treated with endoscopic mucosal resection. Endoscopic submucosal dissection (ESD) is an option for larger lesions. Endoscopic resection is considered curative (i.e., without significant risk of lymph node metastasis) if histopathology confirms en bloc and R0 resection of a well-differentiated (G1/2) tumor without infiltration of lymphatic or blood vessels and the maximal submucosal infiltration depth is 500µm. Ablation of remaining Barrett’s metaplasia is important, to reduce the risk of metachronous cancer. Esophageal squamous cell cancer is associated with different risk factors, and most of the detected lesions are diagnosed during upper gastrointestinal endoscopy for other indications. Virtual high definition and dye chromoendoscopy with Lugol’s solution are used for screening and evaluation. ESD is the preferred resection technique. The criteria for curative resection are similar to Barrett’s cancer, but the maximum infiltration depth must not exceed lamina propria mucosae. Although a submucosal infiltration depth of up to 200 µm carries a substantial risk of lymph node metastasis, ESD combined with adjuvant chemo-radiotherapy gives excellent results. The complication rates of endoscopic resection are low, and the functional outcomes are favorable compared to surgery.

Barrett's esophagus: current standards in advanced imaging

Esophageal adenocarcinoma (EAC) continues to be one of the fastest rising incident cancers in the Western population with the majority of patients presenting with late stage disease and associated with a dismal 5-year survival rate. Barrett's esophagus (BE) is the only identifiable precursor lesion to EAC. Strategies to screen for and survey BE are critical to detect earlier cancers and reduce morbidity and mortality related to EAC. A high-quality endoscopic examination with careful inspection of the Barrett's segment and adherence to the Seattle protocol for tissue sampling are critical. Advanced imaging modalities offer the potential to improve dysplasia detection, predict histopathology in real time and guide endoscopic eradication therapy (EET). Several technologies have been studied and although most are not yet recommended for routine clinical practice, high definition white light endoscopy (HD-WLE) as well as chromoendoscopy (including virtual chromoendoscopy) improved dysplasia detection in numerous studies supporting their use. Future studies should evaluate the role of artificial intelligence in optimizing detection of dysplasia in BE patients.

Endoscopic Resection Without Subsequent Ablation Therapy for Early Barrett's Neoplasia: Endoscopic Findings and Long-Term Mortality

INTRODUCTION

After endoscopic resection (ER) of neoplasia in Barrett's esophagus (BE), it is recommended to ablate the remaining BE to minimize the risk for metachronous disease. However, we report long-term outcomes for a nationwide cohort of all patients who did not undergo ablation of the remaining BE after ER for early BE neoplasia, due to clinical reasons or performance status.

METHODS

Endoscopic therapy for BE neoplasia in the Netherlands is centralized in 8 expert centers with specifically trained endoscopists and pathologists. Uniformity is ensured by a joint protocol and regular group meetings. We report all patients who underwent ER for a neoplastic lesion between 2008 and 2018, without further ablation therapy. Outcomes include progression during endoscopic FU and all-cause mortality.

RESULTS

Ninety-four patients were included with mean age 74 (± 10) years. ER was performed for low-grade dysplasia (LGD) (10%), high-grade dysplasia (HGD) (25%), or low-risk esophageal adenocarcinoma (EAC) (65%). No additional ablation was performed for several reasons; in 73 patients (78%), the main argument was expected limited life expectancy. Median C2M5 BE persisted after ER, and during median 21 months (IQR 11-51) with 4 endoscopies per patient, no patient progressed to advanced cancer. Seventeen patients (18%) developed HGD/EAC: all were curatively treated endoscopically. In total, 29/73 patients (40%) with expected limited life expectancy died due to unrelated causes during FU, none of EAC.

CONCLUSION

In selected patients, ER monotherapy with endoscopic surveillance of the residual BE is a valid alternative to eradication therapy with ablation.

Advanced Imaging and Sampling in Barrett's Esophagus: Artificial Intelligence to the Rescue?

Because the current Barrett's esophagus (BE) surveillance protocol suffers from sampling error of random biopsies and a high miss-rate of early neoplastic lesions, many new endoscopic imaging and sampling techniques have been developed. None of these techniques, however, have significantly increased the diagnostic yield of BE neoplasia. In fact, these techniques have led to an increase in the amount of visible information, yet endoscopists and pathologists inevitably suffer from variations in intra- and interobserver agreement. Artificial intelligence systems have the potential to overcome these endoscopist-dependent limitations.

Artificial intelligence for non-polypoid colorectal neoplasms

The miss rate of flat advanced colorectal neoplasia is still unacceptably high, especially in the Western setting, notwithstanding the widespread implementation of quality improvement programs and training. It is well known that flat morphology is associated with miss rate of colorectal neoplasia, and that this subset of lesions often shows a more aggressive biological behaviour. Artificial intelligence (AI) applied to the detection of colorectal neoplasia has been shown to increase adenoma detection rate, consistently across all lesion sizes and locations in the colon. However, there is still uncertainty whether AI can reduce the miss rate of flat advanced neoplasia, mainly because all published trials report a low number of flat colorectal lesions in their training sets, and this could reduce AI accuracy for this subset of lesions. In addition, flat lesions have different morphologies with variable prevalence and potentially different accuracy in their detection. For example, the subtle appearance and rarer frequency of a non-granular laterally spreading tumor (LST) could be much harder to identify than a granular mixed LST. In this review, we present a summary of the evidence on the role of AI in the identification of colorectal flat neoplasia, with a focus on data regarding presence of LSTs in the training/validation sets of the AI systems currently available on the market.

Extracellular miRNAs for the Management of Barrett's Esophagus and Esophageal Adenocarcinoma: A Systematic Review

Esophageal adenocarcinoma (EAC), the major histologic type of esophageal cancer (EC) in Western countries, is a disease with a poor prognosis, primarily due to usual diagnosis at an advanced stage. The prevalence of EAC has increased in recent years, both in Western countries and in Asia. Barrett's esophagus (BE) is a precursor lesion of EAC. Therefore, early detection and proper management of BE and EAC is important to improve prognosis. Here, we systematically summarize current knowledge about the potential utility of extracellular microRNAs (miRNAs), which are thought to be non-invasive biomarkers for many diseases, for these purposes. A search of the PubMed and Embase databases identified 22 papers about extracellular miRNAs that have potential utility for management of EAC. Among them, 19 were EAC-related and ten were BE-related; some of these dealt with both conditions. The articles included studies reporting diagnosis, prognosis, and treatment responses. Multiple papers report dysregulation of miR-194-5p in BE and miR-21-5p, -25-3p, and -93-5p in EAC. Although it will take time to utilize these miRNAs in clinical practice, they are likely to be useful non-invasive markers in the future.

Machine learning in GI endoscopy: practical guidance in how to interpret a novel field

There has been a vast increase in GI literature focused on the use of machine learning in endoscopy. The relative novelty of this field poses a challenge for reviewers and readers of GI journals. To appreciate scientific quality and novelty of machine learning studies, understanding of the technical basis and commonly used techniques is required. Clinicians often lack this technical background, while machine learning experts may be unfamiliar with clinical relevance and implications for daily practice. Therefore, there is an increasing need for a multidisciplinary, international evaluation on how to perform high-quality machine learning research in endoscopy. This review aims to provide guidance for readers and reviewers of peer-reviewed GI journals to allow critical appraisal of the most relevant quality requirements of machine learning studies. The paper provides an overview of common trends and their potential pitfalls and proposes comprehensive quality requirements in six overarching themes: terminology, data, algorithm description, experimental setup, interpretation of results and machine learning in clinical practice.

Standalone performance of artificial intelligence for upper GI neoplasia: a meta-analysis

OBJECTIVE

Artificial intelligence (AI) may reduce underdiagnosed or overlooked upper GI (UGI) neoplastic and preneoplastic conditions, due to subtle appearance and low disease prevalence. Only disease-specific AI performances have been reported, generating uncertainty on its clinical value.

DESIGN

We searched PubMed, Embase and Scopus until July 2020, for studies on the diagnostic performance of AI in detection and characterisation of UGI lesions. Primary outcomes were pooled diagnostic accuracy, sensitivity and specificity of AI. Secondary outcomes were pooled positive (PPV) and negative (NPV) predictive values. We calculated pooled proportion rates (%), designed summary receiving operating characteristic curves with respective area under the curves (AUCs) and performed metaregression and sensitivity analysis.

RESULTS

Overall, 19 studies on detection of oesophageal squamous cell neoplasia (ESCN) or Barrett's esophagus-related neoplasia (BERN) or gastric adenocarcinoma (GCA) were included with 218, 445, 453 patients and 7976, 2340, 13 562 images, respectively. AI-sensitivity/specificity/PPV/NPV/positive likelihood ratio/negative likelihood ratio for UGI neoplasia detection were 90% (CI 85% to 94%)/89% (CI 85% to 92%)/87% (CI 83% to 91%)/91% (CI 87% to 94%)/8.2 (CI 5.7 to 11.7)/0.111 (CI 0.071 to 0.175), respectively, with an overall AUC of 0.95 (CI 0.93 to 0.97). No difference in AI performance across ESCN, BERN and GCA was found, AUC being 0.94 (CI 0.52 to 0.99), 0.96 (CI 0.95 to 0.98), 0.93 (CI 0.83 to 0.99), respectively. Overall, study quality was low, with high risk of selection bias. No significant publication bias was found.

CONCLUSION

We found a high overall AI accuracy for the diagnosis of any neoplastic lesion of the UGI tract that was independent of the underlying condition. This may be expected to substantially reduce the miss rate of precancerous lesions and early cancer when implemented in clinical practice.

Curriculum for optical diagnosis training in Europe: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

This manuscript represents an official Position Statement of the European Society of Gastrointestinal Endoscopy (ESGE) aiming to guide general gastroenterologists to develop and maintain skills in optical diagnosis during endoscopy. In general, this requires additional training beyond the core curriculum currently provided in each country. In this context, ESGE have developed a European core curriculum for optical diagnosis practice across Europe for high quality optical diagnosis training. 1:  ESGE suggests that every endoscopist should have achieved general competence in upper and/or lower gastrointestinal (UGI/LGI) endoscopy before commencing training in optical diagnosis of the UGI/LGI tract, meaning personal experience of at least 300 UGI and/or 300 LGI endoscopies and meeting the ESGE quality measures for UGI/LGI endoscopy. ESGE suggests that every endoscopist should be able and competent to perform UGI/LGI endoscopy with high definition white light combined with virtual and/or dye-based chromoendoscopy before commencing training in optical diagnosis. 2:  ESGE suggests competency in optical diagnosis can be learned by attending a validated optical diagnosis training course based on a validated classification, and self-learning with a minimum number of lesions. If no validated training course is available, optical diagnosis can only be learned by attending a non-validated onsite training course and self-learning with a minimum number of lesions. 3:  ESGE suggests endoscopists are competent in optical diagnosis after meeting the pre-adoption and learning criteria, and meeting competence thresholds by assessing a minimum number of lesions prospectively during real-time endoscopy. ESGE suggests ongoing in vivo practice by endoscopists to maintain competence in optical diagnosis. If a competent endoscopist does not perform in vivo optical diagnosis on a regular basis, ESGE suggests repeating the learning and competence phases to maintain competence.Key areas of interest were optical diagnosis training in Barrett's esophagus, esophageal squamous cell carcinoma, early gastric cancer, diminutive colorectal lesions, early colorectal cancer, and neoplasia in inflammatory bowel disease. Condition-specific recommendations are provided in the main document.

What is the optimal surveillance strategy for non-dysplastic Barrett's esophagus?

PURPOSE OF REVIEW

There is conflicting data on the effectiveness of the currently recommended endoscopic surveillance strategy in non-dysplastic BE patients. We reviewed the literature to evaluate the (cost) effectiveness of the current surveillance strategy. We also reviewed critical strategies and new technologies which could improve dysplasia detection.

RECENT FINDINGS

Adherence to the current EGD surveillance guidelines is suboptimal with high rates of missed dysplasia/EAC. The influence of surveillance on EAC mortality appears modest. Careful cleansing, inspection and sampling of the BE mucosa using high resolution while light and (electronic) chromoendoscopy is critical. Newer sampling techniques coupled with computer aided diagnosis and emerging imaging technologies have shown promise in improving dysplasia detection. Personalized surveillance with risk stratification based on risk factors for progression may be on the horizon.

SUMMARY

Current BE surveillance strategy will likely be further refined and optimized by emerging new technologies in tissue sampling, advanced imaging and risk stratification.

The Impact of Artificial Intelligence in the Endoscopic Assessment of Premalignant and Malignant Esophageal Lesions: Present and Future

In the gastroenterology field, the impact of artificial intelligence was investigated for the purposes of diagnostics, risk stratification of patients, improvement in quality of endoscopic procedures and early detection of neoplastic diseases, implementation of the best treatment strategy, and optimization of patient prognosis. Computer-assisted diagnostic systems to evaluate upper endoscopy images have recently emerged as a supporting tool in endoscopy due to the risks of misdiagnosis related to standard endoscopy and different expertise levels of endoscopists, time-consuming procedures, lack of availability of advanced procedures, increasing workloads, and development of endoscopic mass screening programs. Recent research has tended toward computerized, automatic, and real-time detection of lesions, which are approaches that offer utility in daily practice. Despite promising results, certain studies might overexaggerate the diagnostic accuracy of artificial systems, and several limitations remain to be overcome in the future. Therefore, additional multicenter randomized trials and the development of existent database platforms are needed to certify clinical implementation. This paper presents an overview of the literature and the current knowledge of the usefulness of different types of machine learning systems in the assessment of premalignant and malignant esophageal lesions via conventional and advanced endoscopic procedures. This study makes a presentation of the artificial intelligence terminology and refers also to the most prominent recent research on computer-assisted diagnosis of neoplasia on Barrett’s esophagus and early esophageal squamous cell carcinoma, and prediction of invasion depth in esophageal neoplasms. Furthermore, this review highlights the main directions of future doctor–computer collaborations in which machines are expected to improve the quality of medical action and routine clinical workflow, thus reducing the burden on physicians.

Multicenter study on the diagnostic performance of multiframe volumetric laser endomicroscopy targets for Barrett's esophagus neoplasia with histopathology correlation

Volumetric laser endomicroscopy (VLE) has been shown to improve detection of early neoplasia in Barrett's esophagus (BE). However, diagnostic performance using histopathology-correlated VLE regions of interest (ROIs) has not been adequately studied. We evaluated the diagnostic accuracy of VLE assessors for identification of early BE neoplasia in histopathology-correlated VLE ROIs. In total, 191 ROIs (120 nondysplastic and 71 neoplastic) from 50 BE patients were evaluated in a random order using a web-based module. All ROIs contained histopathology correlations enabled by VLE laser marking. Assessors were blinded to endoscopic BE images and histology. ROIs were first scored as nondysplastic or neoplastic. Level of confidence was assigned to the predicted diagnosis. Outcome measures were: (i) diagnostic performance of VLE assessors for identification of BE neoplasia in all VLE ROIs, defined as accuracy, sensitivity, and specificity; (ii) diagnostic performance of VLE assessors for only high level of confidence predictions; and (iii) interobserver agreement. Accuracy, sensitivity, and specificity for BE neoplasia identification were 79% (confidence interval [CI], 75-83), 75% (CI, 71-79), and 81% (CI, 76-86), respectively. When neoplasia was identified with a high level of confidence, accuracy, sensitivity, and specificity were 88%, 83%, and 90%, respectively. The overall strength of interobserver agreement was fair (k = 0.29). VLE assessors can identify BE neoplasia with reasonable diagnostic accuracy in histopathology-correlated VLE ROIs, and accuracy is enhanced when BE neoplasia is identified with high level of confidence. Future work should focus on renewed VLE image reviewing criteria and real-time automatic assessment of VLE scans.

Deep learning algorithm detection of Barrett's neoplasia with high accuracy during live endoscopic procedures: a pilot study (with video)

BACKGROUND AND AIMS

We assessed the preliminary diagnostic accuracy of a recently developed computer-aided detection (CAD) system for detection of Barrett's neoplasia during live endoscopic procedures.

METHODS

The CAD system was tested during endoscopic procedures in 10 patients with nondysplastic Barrett's esophagus (NDBE) and 10 patients with confirmed Barrett's neoplasia. White-light endoscopy images were obtained at every 2-cm level of the Barrett's segment and immediately analyzed by the CAD system, providing instant feedback to the endoscopist. At every level, 3 images were evaluated by the CAD system. Outcome measures were diagnostic performance of the CAD system per level and per patient, defined as accuracy, sensitivity, and specificity (ground truth was established by expert assessment and corresponding histopathology), and concordance of 3 sequential CAD predictions per level.

RESULTS

Accuracy, sensitivity, and specificity of the CAD system in a per-level analyses were 90%, 91%, and 89%, respectively. Nine of 10 neoplastic patients were correctly diagnosed. The single lesion not detected by CAD showed NDBE in the endoscopic resection specimen. In only 1 NDBE patient, the CAD system produced false-positive predictions. In 75% of all levels, the CAD system produced 3 concordant predictions.

CONCLUSIONS

This is one of the first studies to evaluate a CAD system for Barrett's neoplasia during live endoscopic procedures. The system detected neoplasia with high accuracy, with only a small number of false-positive predictions and with a high concordance rate between separate predictions. The CAD system is thereby ready for testing in larger, multicenter trials. (Clinical trial registration number: NL7544.).

Radiofrequency Ablation of Barrett's Esophagus: Have We Gone Too Far, or Not Far Enough?

PURPOSE OF REVIEW

Barrett's esophagus (BE) is a premalignant condition of the esophagus associated with an increased risk for esophageal adenocarcinoma (EAC). Radiofrequency ablation (RFA) is a safe and effective first-line treatment for dysplastic BE and early stage EAC. This report reviews clinically relevant evidence published over the last 3 years regarding RFA for BE.

RECENT FINDINGS

Our use of this technology has simultaneously gone too far, in that many patients who may not derive a benefit from these treatments are receiving them, and not far enough, in that many patients who would be eligible for ablative therapy never undergo screening exams to assess them for dysplastic BE, or do not have endoscopic therapy considered part of the treatment of superficial invasive cancer. Research to better identify patients with BE, risk stratify those patients, improve the quality of RFA treatment, and inform surveillance practices has the potential to optimize the benefit of RFA, and minimize the harms, costs, and risks.

Blue-light imaging and linked-color imaging improve visualization of Barrett's neoplasia by nonexpert endoscopists

BACKGROUND AND AIMS

Endoscopic recognition of early Barrett's neoplasia is challenging. Blue-light imaging (BLI) and linked-color imaging (LCI) may assist endoscopists in appreciation of neoplasia. Our aim was to evaluate BLI and LCI for visualization of Barrett's neoplasia in comparison with white-light endoscopy (WLE) alone, when assessed by nonexpert endoscopists.

METHODS

In this web-based assessment, corresponding WLE, BLI, and LCI images of 30 neoplastic Barrett's lesions were delineated by 3 expert endoscopists to establish ground truth. These images were then scored and delineated by 76 nonexpert endoscopists from 3 countries and with different levels of expertise, in 4 separate assessment phases with a washout period of 2 weeks. Assessments were as follows: assessment 1, WLE only; assessment 2, WLE + BLI; assessment 3, WLE + LCI; assessment 4, WLE + BLI + LCI. The outcomes were (1) appreciation of macroscopic appearance and ability to delineate lesions (visual analog scale [VAS] scores); (2) preferred technique (ordinal scores); and (3) assessors' delineation performance in terms of overlap with expert ground truth.

RESULTS

Median VAS scores for phases 2 to 4 were significantly higher than in phase 1 (P < .001). Assessors preferred BLI and LCI over WLE for appreciation of macroscopic appearance (P < .001) and delineation (P < .001). Linear mixed-effect models showed that delineation performance increased significantly in phase 4.

CONCLUSIONS

The use of BLI and LCI has significant additional value for the visualization of Barrett's neoplasia when used by nonexpert endoscopists. Assessors appreciated the addition of BLI and LCI better than the use of WLE alone. Furthermore, this addition led to improved delineation performance, thereby allowing for better acquisition of targeted biopsy samples. (The Netherlands Trial Registry number: NL7541.).

Deep-Learning System Detects Neoplasia in Patients With Barrett's Esophagus With Higher Accuracy Than Endoscopists in a Multistep Training and Validation Study With Benchmarking

BACKGROUND & AIMS

We aimed to develop and validate a deep-learning computer-aided detection (CAD) system, suitable for use in real time in clinical practice, to improve endoscopic detection of early neoplasia in patients with Barrett's esophagus (BE).

METHODS

We developed a hybrid ResNet-UNet model CAD system using 5 independent endoscopy data sets. We performed pretraining using 494,364 labeled endoscopic images collected from all intestinal segments. Then, we used 1704 unique esophageal high-resolution images of rigorously confirmed early-stage neoplasia in BE and nondysplastic BE, derived from 669 patients. System performance was assessed by using data sets 4 and 5. Data set 5 was also scored by 53 general endoscopists with a wide range of experience from 4 countries to benchmark CAD system performance. Coupled with histopathology findings, scoring of images that contained early-stage neoplasia in data sets 2-5 were delineated in detail for neoplasm position and extent by multiple experts whose evaluations served as the ground truth for segmentation.

RESULTS

The CAD system classified images as containing neoplasms or nondysplastic BE with 89% accuracy, 90% sensitivity, and 88% specificity (data set 4, 80 patients and images). In data set 5 (80 patients and images) values for the CAD system vs those of the general endoscopists were 88% vs 73% accuracy, 93% vs 72% sensitivity, and 83% vs 74% specificity. The CAD system achieved higher accuracy than any of the individual 53 nonexpert endoscopists, with comparable delineation performance. CAD delineations of the area of neoplasm overlapped with those from the BE experts in all detected neoplasia in data sets 4 and 5. The CAD system identified the optimal site for biopsy of detected neoplasia in 97% and 92% of cases (data sets 4 and 5, respectively).

CONCLUSIONS

We developed, validated, and benchmarked a deep-learning computer-aided system for primary detection of neoplasia in patients with BE. The system detected neoplasia with high accuracy and near-perfect delineation performance. The Netherlands National Trials Registry, Number: NTR7072.