Identifying key mechanisms leading to visual recognition errors for missed colorectal polyps using eye-tracking technology.

BACKGROUND AND AIM: Lack of visual recognition of colorectal polyps may lead to interval cancers. The mechanisms contributing to perceptual variation, particularly for subtle and advanced colorectal neoplasia, have scarcely been investigated. We aimed to evaluate visual recognition errors and provide novel mechanistic insights. METHODS: Eleven participants (seven trainees and four medical students) evaluated images from the UCL polyp perception dataset, containing 25 polyps, using eye-tracking equipment. Gaze errors were defined as those where the lesion was not observed according to eye-tracking technology. Cognitive errors occurred when lesions were observed but not recognized as polyps by participants. A video study was also performed including 39 subtle polyps, where polyp recognition performance was compared with a convolutional neural network. RESULTS: Cognitive errors occurred more frequently than gaze errors overall (65.6%), with a significantly higher proportion in trainees (P = 0.0264). In the video validation, the convolutional neural network detected significantly more polyps than trainees and medical students, with per-polyp sensitivities of 79.5%, 30.0%, and 15.4%, respectively. CONCLUSIONS: Cognitive errors were the most common reason for visual recognition errors. The impact of interventions such as artificial intelligence, particularly on different types of perceptual errors, needs further investigation including potential effects on learning curves. To facilitate future research, a publicly accessible visual perception colonoscopy polyp database was created.

Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement.

This ESGE Position Statement defines the expected value of artificial intelligence (AI) for the diagnosis and management of gastrointestinal neoplasia within the framework of the performance measures already defined by ESGE. This is based on the clinical relevance of the expected task and the preliminary evidence regarding artificial intelligence in artificial or clinical settings. MAIN RECOMMENDATIONS:: (1) For acceptance of AI in assessment of completeness of upper GI endoscopy, the adequate level of mucosal inspection with AI should be comparable to that assessed by experienced endoscopists. (2) For acceptance of AI in assessment of completeness of upper GI endoscopy, automated recognition and photodocumentation of relevant anatomical landmarks should be obtained in ≥90% of the procedures. (3) For acceptance of AI in the detection of Barrett's high grade intraepithelial neoplasia or cancer, the AI-assisted detection rate for suspicious lesions for targeted biopsies should be comparable to that of experienced endoscopists with or without advanced imaging techniques. (4) For acceptance of AI in the management of Barrett's neoplasia, AI-assisted selection of lesions amenable to endoscopic resection should be comparable to that of experienced endoscopists. (5) For acceptance of AI in the diagnosis of gastric precancerous conditions, AI-assisted diagnosis of atrophy and intestinal metaplasia should be comparable to that provided by the established biopsy protocol, including the estimation of extent, and consequent allocation to the correct endoscopic surveillance interval. (6) For acceptance of artificial intelligence for automated lesion detection in small-bowel capsule endoscopy (SBCE), the performance of AI-assisted reading should be comparable to that of experienced endoscopists for lesion detection, without increasing but possibly reducing the reading time of the operator. (7) For acceptance of AI in the detection of colorectal polyps, the AI-assisted adenoma detection rate should be comparable to that of experienced endoscopists. (8) For acceptance of AI optical diagnosis (computer-aided diagnosis [CADx]) of diminutive polyps (≤5 mm), AI-assisted characterization should match performance standards for implementing resect-and-discard and diagnose-and-leave strategies. (9) For acceptance of AI in the management of polyps ≥ 6 mm, AI-assisted characterization should be comparable to that of experienced endoscopists in selecting lesions amenable to endoscopic resection.

Comparison of focal cryoballoon ablation with 10- and 8-second doses for treatment of Barrett's esophagus-related neoplasia: results from a prospective European multicenter study (with video).

BACKGROUND AND AIMS: Focal cryoballoon ablation (FCBA) is currently being investigated for the treatment of Barrett's esophagus (BE)-related neoplasia in a European multicenter study (Euro-Coldplay study). After inclusion of 28 of 107 patients, the initial dose of 10 seconds was lowered to 8 seconds. The current study aimed to compare the efficacy and safety of a single FCBA treatment session with 10 seconds versus 8 seconds. METHODS: Treatments were performed at 7 European BE referral centers. All 28 patients treated with 10 seconds were compared with 28 consecutive patients treated with 8 seconds. The gastroesophageal junction was ablated circumferentially followed by all visible BE. To assess efficacy and safety, 3 expert adjudicators, blinded to physician and dose, compared pre- and post-treatment images. Primary outcomes were median BE surface regression and stricture rate after single-session FCBA. RESULTS: We included 56 patients (10-second cohort, n = 28; 8-second cohort, n = 28) with a median BE length of C0M2 (Prague classification). Baseline characteristics did not significantly differ between the cohorts. The median BE surface regression after a single FCBA session was comparable for 10 seconds and 8 seconds (80% [95% confidence interval {CI}, 75-90] and 80% [95% CI, 66-90], respectively; P = .65). Strictures requiring dilation were seen in 19% (95% CI, 4-33) and 15% (95% CI, 4-30) of the 10-second and 8-second groups, respectively (P = 1.00). Two patients in the 10-second group developed a severe stricture requiring >3 dilations. CONCLUSIONS: In patients with limited BE, single-session FCBA with 8 seconds showed similar BE surface regression as compared with 10 seconds and may theoretically result in fewer and less severe strictures. Therefore, we suggest using 8 seconds as the standard dose for FCBA. (Clinical trial registration number: NL7253.).

Durable metabolic improvements 2 years after duodenal mucosal resurfacing (DMR) in patients with type 2 diabetes (REVITA-1 Study).

AIMS: Duodenal mucosal resurfacing (DMR) is an endoscopic procedure developed to improve metabolic parameters and restore insulin sensitivity in patients with diabetes. Here we report long-term DMR safety and efficacy from the REVITA-1 study. MATERIALS AND METHODS: REVITA-1 was a prospective, single-arm, open-label, multicenter study of DMR feasibility, safety, and efficacy in patients with type 2 diabetes (hemoglobin A1c [HbA1c] of 7.5-10.0% (58-86 mmol/mol)) on oral medication. Safety and glycemic (HbA1c), hepatic (alanine aminotransferase [ALT]), and cardiovascular (HDL, triglyceride [TG]/HDL ratio) efficacy parameters were assessed (P values presented for LS mean change). RESULTS: Mean ± SD HbA1c levels reduced from 8.5 ± 0.7% (69.1 ± 7.1 mmol/mol) at baseline (N = 34) to 7.5 ± 0.8% (58.9 ± 8.8 mmol/mol) at 6 months (P < 0.001); and this reduction was sustained through 24 months post-DMR (7.5 ± 1.1% [59.0 ± 12.3 mmol/mol], P < 0.001) while in greater than 50% of patients, glucose-lowering therapy was reduced or unchanged. ALT decreased from 38.1 ± 21.1 U/L at baseline to 32.5 ± 22.1 U/L at 24 months (P = 0.048). HDL and TG/HDL improved during 24-months of follow-up. No device- or procedure-related serious adverse events, unanticipated device effects, or hypoglycemic events were noted between 12 and 24 months post-DMR. CONCLUSIONS: DMR is associated with durable improvements in insulin sensitivity and multiple downstream metabolic parameters through 24 months post-treatment in type 2 diabetes. Clinical trial reg. no. NCT02413567, clinicaltrials.gov.

Performance of artificial intelligence for detection of subtle and advanced colorectal neoplasia.

OBJECTIVES: There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated lesions (SSLs), due to low prevalence in testing datasets and prospective trials. This has been highlighted as a top research priority for the field. METHODS: An AI algorithm was evaluated on four video test datasets containing 173 polyps (35,114 polyp-positive frames and 634,988 polyp-negative frames) specifically enriched with flat lesions and SSLs, including a challenging dataset containing subtle advanced neoplasia. The challenging dataset was also evaluated by eight endoscopists (four independent, four trainees, according to the Joint Advisory Group on gastrointestinal endoscopy [JAG] standards in the UK). RESULTS: In the first two video datasets, the algorithm achieved per-polyp sensitivities of 100% and 98.9%. Per-frame sensitivities were 84.1% and 85.2%. In the subtle dataset, the algorithm detected a significantly higher number of polyps (P < 0.0001), compared to JAG-independent and trainee endoscopists, achieving per-polyp sensitivities of 79.5%, 37.2% and 11.5%, respectively. Furthermore, when considering subtle polyps detected by both the algorithm and at least one endoscopist, the AI detected polyps significantly faster on average. CONCLUSIONS: The AI based algorithm achieved high per-polyp sensitivities for advanced colorectal neoplasia, including flat lesions and SSLs, outperforming both JAG independent and trainees on a very challenging dataset containing subtle lesions that could have been overlooked easily and contribute to interval colorectal cancer. Further prospective trials should evaluate AI to detect subtle advanced neoplasia in higher risk populations for colorectal cancer.

Bariatric and Metabolic Endoscopy: A New Paradigm.

The prevalence of obesity, type 2 diabetes mellitus, and metabolic syndromes is increasing globally. Minimally invasive metabobariatric (MB) endoscopic therapies are adjunct treatments that can potentially bridge the gap between surgical interventions and medical therapy. A growing number of MB techniques are becoming available, allowing for more personalized and patient-targeted treatment options for specific disease states. MB techniques are less invasive than surgery and can precisely target different parts of the gastrointestinal tract that may be responsible for the pathophysiology of obesity and metabolic syndromes such as type 2 diabetes mellitus. These alternatives should be selected on an individualized patient basis to balance the expected clinical outcomes and desired anatomical targets with the level of invasiveness and degree of acceptable risk. Each MB intervention presents great flexibility allowing for a tailored intervention and different levels of patient engagement. Patient awareness and motivation are essential to avoid therapy withdrawal and failure. Differences between MB procedures in terms of weight loss and metabolic benefit will be discussed in this review, along with the insights on clinical decision-making processes to evaluate the potential of further evolution and growth of bariatric and metabolic endoscopy.

A clinically interpretable convolutional neural network for the real-time prediction of early squamous cell cancer of the esophagus: comparing diagnostic performance with a panel of expert European and Asian endoscopists.

BACKGROUND AND AIMS: Intrapapillary capillary loops (IPCLs) are microvascular structures that correlate with the invasion depth of early squamous cell neoplasia and allow accurate prediction of histology. Artificial intelligence may improve human recognition of IPCL patterns and prediction of histology to allow prompt access to endoscopic therapy for early squamous cell neoplasia where appropriate. METHODS: One hundred fifteen patients were recruited at 2 academic Taiwanese hospitals. Magnification endoscopy narrow-band imaging videos of squamous mucosa were labeled as dysplastic or normal according to their histology, and IPCL patterns were classified by consensus of 3 experienced clinicians. A convolutional neural network (CNN) was trained to classify IPCLs, using 67,742 high-quality magnification endoscopy narrow-band images by 5-fold cross validation. Performance measures were calculated to give an average F1 score, accuracy, sensitivity, and specificity. A panel of 5 Asian and 4 European experts predicted the histology of a random selection of 158 images using the Japanese Endoscopic Society IPCL classification; accuracy, sensitivity, specificity, positive and negative predictive values were calculated. RESULTS: Expert European Union (EU) and Asian endoscopists attained F1 scores (a measure of binary classification accuracy) of 97.0% and 98%, respectively. Sensitivity and accuracy of the EU and Asian clinicians were 97%, 98% and 96.9%, 97.1%, respectively. The CNN average F1 score was 94%, sensitivity 93.7%, and accuracy 91.7%. Our CNN operates at video rate and generates class activation maps that can be used to visually validate CNN predictions. CONCLUSIONS: We report a clinically interpretable CNN developed to predict histology based on IPCL patterns, in real time, using the largest reported dataset of images for this purpose. Our CNN achieved diagnostic performance comparable with an expert panel of endoscopists.

Surveillance of patients with Barrett's esophagus after complete eradication of intestinal metaplasia

A 55-year-old Caucasian male with a long history of smoking and reflux disease underwent endoscopic evaluation for dyspepsia. During upper endoscopy, a 4 cm long Barrett's segment with an 8 mm nodular lesion was detected. The lesion was removed en-bloc by endoscopic mucosal resection and biopsies were taken from the adjacent columnar epithelium. The histology of the lesion revealed high-grade dysplasia with clear resection margins and no lymphovascular invasion. The remaining biopsies did not show any dysplastic changes. He subsequently underwent three sequential sessions of radiofrequency ablation (RFA) to eradicate the remaining Barrett's epithelium. When this type of case presents to the clinic for follow-up, what do you do next?

No disponible

Surveillance of patients with Barrett's esophagus after complete eradication of intestinal metaplasia.

A 55-year-old Caucasian male with a long history of smoking and reflux disease underwent endoscopic evaluation for dyspepsia. During upper endoscopy, a 4 cm long Barrett's segment with an 8 mm nodular lesion was detected. The lesion was removed en-bloc by endoscopic mucosal resection and biopsies were taken from the adjacent columnar epithelium. The histology of the lesion revealed high-grade dysplasia with clear resection margins and no lymphovascular invasion. The remaining biopsies did not show any dysplastic changes. He subsequently underwent three sequential sessions of radiofrequency ablation (RFA) to eradicate the remaining Barrett's epithelium. When this type of case presents to the clinic for follow-up, what do you do next?

Learning curves and the influence of procedural volume for the treatment of dysplastic Barrett's esophagus.

BACKGROUND AND AIMS: Endoscopic resections and radiofrequency ablation (RFA) are the established treatments for Barrett's-associated dysplasia and early esophageal neoplasia. The UK RFA Registry collects patient outcomes from 24 centers treating patients in the United Kingdom and Ireland. Learning curves for treatment of Barrett's dysplasia and the impact of center caseload on patient outcomes is still unknown. METHODS: We examined outcomes of 678 patients treated with RFA in the UK Registry using risk-adjusted cumulative sum control chart (RA-CUSUM) analysis to identify change points in complete resolution of intestinal metaplasia (CR-IM) and complete resolution of dysplasia (CR-D) outcomes. We compared outcomes between those treated at high-volume (>100 enrolled patients), medium-volume (51-100), and low-volume (<50) centers. RESULTS: There was no association between center volume and CR-IM and CR-D rates, but recurrence rates were lower in high-volume versus low-volume centers (log rank P = .001). There was a significant change point for outcomes at 12 cases for CR-D (reduction from 24.5% to 10.4%; P < .001) and at 18 cases for CR-IM (30.7% to 18.6%; P < .001) from RA-CUSUM curve analysis. CONCLUSION: Our data suggest that 18 supervised cases of endoscopic ablation may be required before competency in endoscopic treatment of Barrett's dysplasia can be achieved. The difference in outcomes between a high-volume and low-volume center does not support further centralization of services to only high-volume centers.

Deep sedation and anaesthesia in complex gastrointestinal endoscopy: a joint position statement endorsed by the British Society of Gastroenterology (BSG), Joint Advisory Group (JAG) and Royal College of Anaesthetists (RCoA).

In the UK, more than 2.5 million endoscopic procedures are carried out each year. Most are performed under conscious sedation with benzodiazepines and opioids administered by the endoscopist. However, in prolonged and complex procedures, this form of sedation may provide inadequate patient comfort or result in oversedation. As a result, this may have a negative impact on procedural success and patient outcome. In addition, there have been safety concerns on the high doses of benzodiazepines and opioids used particularly in prolonged and complex procedures such as endoscopic retrograde cholangiopancreatography. Diagnostic and therapeutic endoscopy has evolved rapidly over the past 5 years with advances in technical skills and equipment allowing interventions and procedural capabilities that are moving closer to minimally invasive endoscopic surgery. It is vital that safe and appropriate sedation practices follow the inevitable expansion of this portfolio to accommodate safe and high-quality clinical outcomes. This position statement outlines the current use of sedation in the UK and highlights the role for anaesthetist-led deep sedation practice with a focus on propofol sedation although the choice of sedative or anaesthetic agent is ultimately the choice of the anaesthetist. It outlines the indication for deep sedation and anaesthesia, patient selection and assessment and procedural details. It considers the setup for a deep sedation and anaesthesia list, including the equipment required, the environment, staffing and monitoring requirements. Considerations for different endoscopic procedures in both emergency and elective setting are also detailed. The role for training, audit, compliance and future developments are discussed.

Self-sizing radiofrequency ablation balloon for eradication of Barrett's esophagus: results of an international multicenter randomized trial comparing 3 different treatment regimens.

BACKGROUND AND AIMS: Recently, the 360 Express radiofrequency ablation balloon catheter (360 Express, Medtronic, Minneapolis, Minn, USA) has replaced the traditional system for circumferential radiofrequency ablation (RFA) of Barrett's esophagus (BE). The aim was to compare 3 different ablation regimens for the 360 Express. METHODS: An international multicenter noninferiority randomized controlled trial was conducted in which patients with a BE (2-15 cm) with dysplasia or early cancer were randomly assigned to the standard (1 × 10 J/cm2-clean-1 × 10 J/cm2), simple-double (2 × 10 J/cm2-no clean), or simple-single ablation regimen (1 × 10 J/cm2-no clean). The primary outcome was the percentage endoscopically visual BE regression at 3 months. Secondary outcomes were procedure time, adverse events, and patient discomfort. RESULTS: Between September 2015 and October 2017, 104 patients were enrolled. The simple-double ablation arm was closed prematurely because of a 21% stenosis rate. The trial continued with the standard (n = 37) and simple-single arm (n = 38). Both arms were comparable at baseline. Noninferiority of the simple-single arm could not be demonstrated: BE regression was 73% in the simple-single arm versus 85% in the standard arm; the median difference was 13% (95% confidence interval, 5%-23%). The procedure time was significantly longer in the standard arm (31 vs 17 minutes, P < .001). Both groups were comparable with regard to adverse events and patient discomfort. CONCLUSIONS: This randomized trial shows that circumferential RFA with the 360 Express using the simple-double ablation regimen results in an unacceptable high risk of stenosis. Furthermore, the results suggest that a single ablation at 10 J/cm2 results in inferior BE regression at 3 months. We therefore advise using the standard ablation regimen (1 × 10 J/cm2-clean-1 × 10 J/cm2) for treatment of BE using the 360 Express. (Clinical trial registration number: NTR5191.).

Duodenal mucosal resurfacing: proof-of-concept, procedural development, and initial implementation in the clinical setting.

BACKGROUND AND AIMS: We aimed to develop duodenal mucosal resurfacing (DMR), a minimally invasive upper endoscopic hydrothermal ablation procedure, to treat insulin-resistant metabolic diseases. METHODS: We completed a sham-controlled, rodent proof-of-concept study and longitudinal safety study in pigs to demonstrate feasibility to test DMR in humans. Subsequently, the DMR procedure was implemented in an open-label first-in-human (FIH) study of safety and efficacy in patients with type 2 diabetes (T2D). RESULTS: In rats, duodenal abrasion reduced hyperglycemia by 59 mg/dL on average, compared with no change from baseline in the sham treatment arm (P < .05). In pigs, the balloon catheter successfully and safely delivered hydrothermal ablation to the duodenal mucosa and superficial submucosa. Complete mucosal healing was demonstrated by week 6. In the FIH study, hydrothermal ablation was successfully administered with no evidence of perforation, pancreatitis, or hemorrhage. Duodenal biopsy specimens obtained 3 months postprocedure demonstrated full mucosal regrowth. No inflammation was observed, and there was minimal-to-mild collagen banding deposition observed in a proportion of ablation site biopsy specimens with no evidence of fibrotic scarring. Glycemic and hepatic measures improved through 6 months of follow-up. CONCLUSIONS: DMR shows potential as an endoscopic intervention that improves glycemic and hepatic parameters in patients with T2D. Further mechanistic and clinical studies are underway to further explore DMR as a treatment for metabolic disease.

Virtual chromoendoscopy by using optical enhancement improves the detection of Barrett's esophagus-associated neoplasia.

BACKGROUND AND AIMS: The Seattle protocol for endoscopic Barrett's esophagus (BE) surveillance samples a small portion of the mucosal surface area, risking a potentially high miss rate of early neoplastic lesions. We assessed whether the new iScan Optical Enhancement system (OE) improves the detection of early BE-associated neoplasia compared with high-definition white-light endoscopy (HD-WLE) in both expert and trainee endoscopists to target sampling of suspicious areas. Such a system may both improve early neoplasia detection and reduce the need for random biopsies. METHODS: A total of 41 patients undergoing endoscopic BE surveillance from January 2016 to November 2017 were recruited from 3 international referral centers. Matched still images in both HD-WLE (n = 130) and iScan OE (n = 132) were obtained from endoscopic examinations. Two experts, unblinded to the videos and histology, delineated known neoplasia, forming a consensus criterion standard. Seven expert and 7 trainee endoscopists marked 1 position per image where they would expect a target biopsy to identify dysplastic tissue. The same expert panel then reviewed magnification images and, using a previously validated classification system, attempted to classify mucosa as dysplastic or nondysplastic, based on the mucosal and vascular (MV) patterns observed on magnification endoscopy. Diagnostic accuracy, sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV) were calculated. Improvements in dysplasia detection in HD-WLE versus OE and interobserver agreement were assessed by multilevel logistic regression analysis and Krippendorff alpha, respectively. Improvements in diagnostic performance were expressed as an odds ratio between the odds of improvement in OE compared with the odds of improvement in HD-WLE. RESULTS: Accuracy of neoplasia detection was significantly higher in all trainees who used OE versus HD-WLE (76% vs 63%) and in 6 experts (84% vs 77%). OE improved sensitivity of dysplasia detection compared with HD-WLE in 6 trainees (81% vs 71%) and 5 experts (77% vs 67%). Specificity improved in 6 trainees who used OE versus HD-WLE (70% vs 55%) and in 5 experts (92% vs 86%). PPV improved in both an expert and trainee cohort, but NPV improved significantly only in trainees. By using the MV classification and OE magnification endoscopy compared with HD-WLE, we demonstrated improvements in accuracy (79.9% vs 66.7%), sensitivity (86.3% vs 83.4%), and specificity (71.2% vs 53.6%) of dysplasia detection. PPV improved (62%-76.6%), as did NPV (67.7%-78.5%). Interobserver agreement also improved by using OE from 0.30 to 0.55. CONCLUSION: iScan OE may improve dysplasia detection on endoscopic imaging of BE as well as the accuracy of histology prediction compared with HD-WLE, when OE magnification endoscopy is used in conjunction with a simple classification system by both expert and non-expert endoscopists.

A cost-effectiveness analysis of endoscopic eradication therapy for management of dysplasia arising in patients with Barrett's oesophagus in the United Kingdom.

BACKGROUND AND AIMS: Endoscopic eradication therapy (EET) is the first line approach for treating Barrett's oesophagus (BE) related neoplasia globally. The British Society of Gastroenterology (BSG) recommend EET with combined endoscopic resection (ER) for visible dysplasia followed by endoscopic ablation in patients with both low and high grade dysplasia (LGD and HGD). The aim of this study is to perform a cost-effectiveness analysis for EET for treatment of all grades of dysplasia in BE patients. METHODS: A Markov cohort model with a lifetime time horizon was used to undertake a cost-effectiveness analysis. A hypothetical cohort of UK patients diagnosed with BE entered the model. Patients in the treatment arm with LGD and HGD received EET and patients with non-dysplastic BE (NDBE) received endoscopic surveillance only. In the comparator arm, patients with LGD, HGD and NDBE received endoscopic surveillance only. A UK National Health Service (NHS) perspective was adopted and the incremental cost-effectiveness ratio (ICER) was calculated. Sensitivity analysis was conducted on key input parameters. RESULTS: EET for patients with LGD and HGD arising in BE is cost-effective compared to endoscopic surveillance alone (lifetime ICER £3006 per quality adjusted life year [QALY] gained). The results show that, as the time horizon increases, the treatment becomes more cost-effective. The 5 year financial impact to the UK NHS of introducing EET is £7.1m. CONCLUSIONS: EET for patients with low and high grade BE dysplasia, following updated guidelines from the BSG, has been shown to be cost-effective for patients with BE in the UK.

Machine Learning Creates a Simple Endoscopic Classification System that Improves Dysplasia Detection in Barrett's Oesophagus amongst Non-expert Endoscopists.

INTRODUCTION: Barrett's oesophagus (BE) is a precursor to oesophageal adenocarcinoma (OAC). Endoscopic surveillance is performed to detect dysplasia arising in BE as it is likely to be amenable to curative treatment. At present, there are no guidelines on who should perform surveillance endoscopy in BE. Machine learning (ML) is a branch of artificial intelligence (AI) that generates simple rules, known as decision trees (DTs). We hypothesised that a DT generated from recognised expert endoscopists could be used to improve dysplasia detection in non-expert endoscopists. To our knowledge, ML has never been applied in this manner. METHODS: Video recordings were collected from patients with non-dysplastic (ND-BE) and dysplastic Barrett's oesophagus (D-BE) undergoing high-definition endoscopy with i-Scan enhancement (PENTAX®). A strict protocol was used to record areas of interest after which a corresponding biopsy was taken to confirm the histological diagnosis. In a blinded manner, videos were shown to 3 experts who were asked to interpret them based on their mucosal and microvasculature patterns and presence of nodularity and ulceration as well as overall suspected diagnosis. Data generated were entered into the WEKA package to construct a DT for dysplasia prediction. Non-expert endoscopists (gastroenterology specialist registrars in training with variable experience and undergraduate medical students with no experience) were asked to score these same videos both before and after web-based training using the DT constructed from the expert opinion. Accuracy, sensitivity, and specificity values were calculated before and after training where p < 0.05 was statistically significant. RESULTS: Videos from 40 patients were collected including 12 both before and after acetic acid (ACA) application. Experts' average accuracy for dysplasia prediction was 88%. When experts' answers were entered into a DT, the resultant decision model had a 92% accuracy with a mean sensitivity and specificity of 97% and 88%, respectively. Addition of ACA did not improve dysplasia detection. Untrained medical students tended to have a high sensitivity but poor specificity as they "overcalled" normal areas. Gastroenterology trainees did the opposite with overall low sensitivity but high specificity. Detection improved significantly and accuracy rose in both groups after formal web-based training although it did it reach the accuracy generated by experts. For trainees, sensitivity rose significantly from 71% to 83% with minimal loss of specificity. Specificity rose sharply in students from 31% to 49% with no loss of sensitivity. CONCLUSION: ML is able to define rules learnt from expert opinion. These generate a simple algorithm to accurately predict dysplasia. Once taught to non-experts, the algorithm significantly improves their rate of dysplasia detection. This opens the door to standardised training and assessment of competence for those who perform endoscopy in BE. It may shorten the learning curve and might also be used to compare competence of trainees with recognised experts as part of their accreditation process.

Systematic assessment with I-SCAN magnification endoscopy and acetic acid improves dysplasia detection in patients with Barrett's esophagus.

Background and study aims Enhanced endoscopic imaging with chromoendoscopy may improve dysplasia recognition in patients undergoing assessment of Barrett's esophagus (BE). This may reduce the need for random biopsies to detect more dysplasia. The aim of this study was to assess the effect of magnification endoscopy with I-SCAN (Pentax, Tokyo, Japan) and acetic acid (ACA) on dysplasia detection in BE using a novel mucosal and vascular classification system. Methods BE segments and suspicious lesions were recorded with high definition white-light and magnification endoscopy enhanced using all I-SCAN modes in combination. We created a novel mucosal and vascular classification system based on similar previously validated classifications for narrow-band imaging (NBI). A total of 27 videos were rated before and after ACA application. Following validation, a further 20 patients had their full endoscopies recorded and analyzed to model use of the system to detect dysplasia in a routine clinical scenario. Results The accuracy of the I-SCAN classification system for BE dysplasia improved with I-SCAN magnification from 69 % to 79 % post-ACA (P = 0.01). In the routine clinical scenario model in 20 new patients, accuracy of dysplasia detection increased from 76 % using a "pull-through" alone to 83 % when ACA and magnification endoscopy were combined (P = 0.047). Overall interobserver agreement between experts for dysplasia detection was substantial (0.69). Conclusions A new I-SCAN classification system for BE was validated against similar systems for NBI with similar outcomes. When used in combination with magnification and ACA, the classification detected BE dysplasia in clinical practice with good accuracy.Trials registered at ISRCTN (58235785).

Upregulation of mucin glycoprotein MUC1 in the progression to esophageal adenocarcinoma and therapeutic potential with a targeted photoactive antibody-drug conjugate.

BACKGROUND: Mucin glycoprotein 1 (MUC1) is a glycosylated transmembrane protein on epithelial cells. We investigate MUC1 as a therapeutic target in Barrett's epithelium (BE) and esophageal adenocarcinoma (EA) and provide proof of concept for a light based therapy targeting MUC1. RESULTS: MUC1 was present in 21% and 30% of significantly enriched pathways comparing BE and EA to squamous epithelium respectively. MUC1 gene expression was x2.3 and x2.2 higher in BE (p=<0.001) and EA (p=0.03). MUC1 immunohistochemical expression increased during progression to EA and followed tumor invasion. HuHMFG1 based photosensitive antibody drug conjugates (ADC) showed cell internalization, MUC1 selective and light-dependent cytotoxicity (p=0.0006) and superior toxicity over photosensitizer alone (p=0.0022). METHODS: Gene set enrichment analysis (GSEA) evaluated pathways during BE and EA development and quantified MUC1 gene expression. Immunohistochemistry and flow cytometry evaluated the anti-MUC1 antibody HuHMFG1 in esophageal cells of varying pathological grade. Confocal microscopy examined HuHMFG1 internalization and HuHMFG1 ADCs were created to deliver a MUC1 targeted phototoxic payload. CONCLUSIONS: MUC1 is a promising target in EA. Molecular and light based targeting of MUC1 with a photosensitive ADC is effective in vitro and after development may enable treatment of locoregional tumors endoscopically.