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.

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

BACKGROUND & AIMS: Endoscopic detection of early Barrett's esophagus-related neoplasia (BORN) is a challenge. We aimed to develop a web-based teaching tool for improving detection and delineation of BORN. METHODS: We made high-definition digital videos during endoscopies of patients with BORN and non-dysplastic Barrett's esophagus. Three experts superimposed their delineations of BORN lesions on the videos using special tools. In phase one, 68 general endoscopists from 4 countries assessed 4 batches of 20 videos. After each batch, mandatory feedback compared the assessors' interpretations with those from experts. These data informed the selection of 25 videos for the phase 2 module, which was completed by 121 new assessors from 5 countries. A 5-video test batch was completed before and after scoring of the four 5-video training batches. Mandatory feedback was as in phase 1. Outcome measures were scores for detection, delineation, agreement delineation, and relative delineation of BORN. RESULTS: A linear mixed-effect model showed significant sequential improvement for all 4 outcomes over successive training batches in both phases. In phase 2, median detection rates of BORN in the test batch increased by 30% (P < .001) after training. From baseline to the end of the study, there were relative increases in scores of 46% for detection, 129% for delineation, 105% for agreement delineation, and 106% for relative delineation (all, P < .001). Scores improved independent of assessors' country of origin or level of endoscopic experience. CONCLUSIONS: We developed a web-based teaching tool for endoscopic recognition of BORN that is easily accessible, efficient, and increases detection and delineation of neoplastic lesions. Widespread use of this tool might improve management of Barrett's esophagus by general endoscopists.

UK guidelines on oesophageal dilatation in clinical practice

These are updated guidelines which supersede the original version published in 2004. This work has been endorsed by the Clinical Services and Standards Committee of the British Society of Gastroenterology (BSG) under the auspices of the oesophageal section of the BSG. The original guidelines have undergone extensive revision by the 16 members of the Guideline Development Group with representation from individuals across all relevant disciplines, including the Heartburn Cancer UK charity, a nursing representative and a patient representative. The methodological rigour and transparency of the guideline development processes were appraised using the revised Appraisal of Guidelines for Research and Evaluation (AGREE II) tool.Dilatation of the oesophagus is a relatively high-risk intervention, and is required by an increasing range of disease states. Moreover, there is scarcity of evidence in the literature to guide clinicians on how to safely perform this procedure. These guidelines deal specifically with the dilatation procedure using balloon or bougie devices as a primary treatment strategy for non-malignant narrowing of the oesophagus. The use of stents is outside the remit of this paper; however, for cases of dilatation failure, alternative techniques-including stents-will be listed. The guideline is divided into the following subheadings: (1) patient preparation; (2) the dilatation procedure; (3) aftercare and (4) disease-specific considerations. A systematic literature search was performed. The Grading of Recommendations Assessment, Develop-ment and Evaluation (GRADE) tool was used to evaluate the quality of evidence and decide on the strength of recommendations made.

Evaluation of a novel infra-red endoscopy system in the assessment of early neoplasia in Barretts esophagus: pilot study from a single center.

Infrared endoscopy (IRE) has been shown to be useful in detecting submucosal (SM) invasion in early gastric cancer. Its role in the endoscopic assessment of Barrett's neoplasia has not been reported to date. We aimed in this study to evaluate the role of IRE in the detection and characterization of early neoplastic lesions within Barrett's esophagus (BE). The secondary aim was to explore its usefulness for the assessment of the presence of submucosal invasion in these early neoplastic Barrett's lesions. We included in the study patients with dysplastic BE who were referred to our institution for endoscopic therapy of a previously diagnosed early Barrett's neoplasia. An examination with white light high resolution endoscopy (HRE) and near IRE after intravenous injection of indocyanine green was performed for all patients using an infrared endoscope prototype. Staining on IRE and correlation with final histological staging by endoscopic mucosal resection/surgery or histological diagnosis on mapping biopsies was analyzed. A total of 23 patients were enrolled in our study: 17 of them with 19 visible lesions and 6 patients with flat BE and no lesions. Staining on IRE was noted in 18 cases: 17 (94%) had at least high grade dysplasia (HGD). No stain was noted in 7 cases: final histology was

Development of an E-learning System for the Endoscopic Diagnosis of Early Gastric Cancer: An International Multicenter Randomized Controlled Trial.

BACKGROUND: In many countries, gastric cancer is not diagnosed until an advanced stage. An Internet-based e-learning system to improve the ability of endoscopists to diagnose gastric cancer at an early stage was developed and was evaluated for its effectiveness. METHODS: The study was designed as a randomized controlled trial. After receiving a pre-test, participants were randomly allocated to either an e-learning or non-e-learning group. Only those in the e-learning group gained access to the e-learning system. Two months after the pre-test, both groups received a post-test. The primary endpoint was the difference between the two groups regarding the rate of improvement of their test results. FINDINGS: 515 endoscopists from 35 countries were assessed for eligibility, and 332 were enrolled in the study, with 166 allocated to each group. Of these, 151 participants in the e-learning group and 144 in the non-e-learning group were included in the analysis. The mean improvement rate (standard deviation) in the e-learning and non-e-learning groups was 1·24 (0·26) and 1·00 (0·16), respectively (P<0·001). INTERPRETATION: This global study clearly demonstrated the efficacy of an e-learning system to expand knowledge and provide invaluable experience regarding the endoscopic detection of early gastric cancer (R000012039).

Incidence of metachronous visible lesions in patients referred for radiofrequency ablation (RFA) therapy for early Barrett's neoplasia: a single-centre experience.

OBJECTIVE: Evaluate the incidence of metachronous visible lesions (VLs) in patients referred for radiofrequency ablation (RFA) for early Barrett's neoplasia. DESIGN: This study was conducted as part of the service evaluation audit. SETTING: Tertiary referral centre. PATIENTS: All patients with dysplastic Barrett's oesophagus referred for RFA were included for analysis. White light high-resolution endoscopy (HRE), autofluorescence imaging and narrow band imaging were sequentially performed. Endoscopic mucosal resection (EMR) was performed for all VL. Three to six months after EMR, all patients underwent initial RFA and then repeat RFA procedures at three monthly intervals. INTERVENTIONS: All endoscopy reports and final staging by EMR/surgery were evaluated and included for analysis. RESULTS: Fifty patients were analysed; median age 73 years, 84% men. 38/50 patients (76%) had a previous EMR due to the presence of VL before referred for ablation; twelve patients had no previous treatment. In total, 151 ablation procedures were performed, median per patient 2.68. Twenty metachronous VL were identified in 14 patients before the first ablation or during the RFA protocol; incidence was 28%. All metachronous lesions were successfully resected by EMR. Upstaging after rescue EMR compared with the initial histology was observed in four patients (28%). CONCLUSIONS: In total, 28% of patients enrolled in the RFA programme were diagnosed to have metachronous lesions. This high-incidence rate highlights the importance of a meticulous examination to identify and resect any VL before every ablation session. RFA treatment for early Barrett's neoplasia should be performed in tertiary referral centres with HRE and EMR facilities and expertise.

Systematic review with meta-analysis: endoscopic balloon dilatation for Crohn's disease strictures.

BACKGROUND: Endoscopic balloon dilatation (EBD) is recognised treatment for symptomatic Crohn's strictures. Several case series report its efficacy. A systematic analysis for overall efficacy can inform the design of future studies. AIM: To examine symptomatic (SR) and technical response (TR) and adverse events (AE) of EBD. Stricture characteristics were also explored. METHODS: A systematic search strategy of COCHRANE, MEDLINE and EMBASE was performed. All original studies reporting outcomes of EBD for Crohn's strictures were included. SR was defined as obstructive symptom-free outcome at the end of follow-up, TR as post-dilatation passage of the endoscope through a stricture, and adverse event as the presence of complication (perforation and/or bleeding). Pooled event rates across studies were expressed with summative statistics. RESULTS: Twenty-five studies included 1089 patients and 2664 dilatations. Pooled event rates for SR, TR, complications and perforations were 70.2% (95% CI: 60-78.8%), 90.6% (95% CI: 87.8-92.8%), 6.4% (95% CI: 5.0-8.2) and 3% (95% CI: 2.2-4.0%) respectively. Cumulative surgery rate at 5 year follow-up was 75%. Pooled unweighted TR, SR, complication, perforation and surgery rates were 84%, 45%, 15%, 9% and 21% for de novo and 84%, 58%, 22%, 5% and 32% for anastomotic strictures. Outcomes between two stricture types were no different on subgroup meta-analysis. CONCLUSIONS: Efficacy and complication rates for endoscopic balloon dilatation were higher than previously reported. From the few studies with 5 year follow-up the majority required surgery. Future studies are needed to determine whether endoscopic balloon dilatation has significant long-term benefits.

Analysis of lymphatic and blood vessel invasion biomarkers in T1 esophagogastric adenocarcinomas for improved patient prognostication.

Lymphovascular invasion (LVI) in T1 esophagogastric adenocarcinoma may predict risk of recurrence despite definitive treatment with surgery or endoscopic resection. Podoplanin and CD34 are emerging biomarkers of lymphatic and blood vessel invasion, respectively, and could be adopted to refine LVI assessment. A consecutive series of 65 patients with T1 adenocarcinomas diagnosed at Nottingham University Hospitals were investigated. T1 tumors from 43/65 patients who received primary surgery only were suitable for LVI evaluation by hematoxylin and eosin (H&E) staining as well as by CD34 and Podoplanin immunohistochemistry. LVI was correlated to clinicopathological features and recurrence free survival. H&E staining detected LVI in 11.6% (5/43) of T1 tumors. CD34 and Podoplanin immunohistochemistry significantly improved LVI detection to 25.6% (11/43). Compared with LVI by H&E, immunohistochemical evaluation of blood vessel invasion (CD34) or lymphatic vessel invasion (Podoplanin) was significantly associated with higher grade (P = 0.005), submucosal invasion (T1b) (P = 0.018), lymph node positivity (N1) (P = 0.029) and poor recurrence free survival (P = 0.0003). Our study provides evidence that CD34 and Podoplanin immunohistochemistry could improve LVI detection and allow better prognostication of patients and optimum selection of definitive treatment. Larger multicenter studies are required for further validation that could have significant clinical implications.

High definition versus standard definition white light endoscopy for detecting dysplasia in patients with Barrett's esophagus.

High-definition endoscopy systems provide superior image resolution. The aim of this study was to assess the utility of high definition compared with standard definition endoscopy system for detecting dysplastic lesions in patients with Barrett's esophagus. A retrospective cohort study of patients with non-dysplastic Barrett's esophagus undergoing routine surveillance was performed. Data were retrieved from the central hospital electronic database. Procedures performed for non-surveillance indications, Barrett's esophagus Prague C0M1 classification with no specialized intestinal metaplasia on histology, patients diagnosed with any dysplasia or cancer on index endoscopy, and procedures using advanced imaging techniques were excluded. Logistic regression models were constructed to estimate adjusted odds ratios and 95% confidence intervals comparing outcomes with standard definition and high-definition systems. The high definition was superior to standard definition system in targeted detection of all dysplastic lesions (odds ratio 3.27, 95% confidence interval 1.27-8.40) as well as overall dysplasia detected on both random and target biopsies (odds ratio 2.36, 95% confidence interval 1.50-3.72). More non-dysplastic lesions were detected with the high-definition system (odds ratio 1.16, 95% confidence interval 1.01-1.33). There was no difference between high definition and standard definition endoscopy in the overall (random and target) high-grade dysplasia or cancers detected (odds ratio 0.93, 95% confidence interval 0.83-1.04). Trainee endoscopists, number of biopsies taken, and male sex were all significantly associated with a higher yield for dysplastic lesions. The use of the high-definition endoscopy system is associated with better targeted detection of any dysplasia during routine Barrett's esophagus surveillance. However, high-definition endoscopy cannot replace random biopsies at present time.

Improvement over time in outcomes for patients undergoing endoscopic therapy for Barrett's oesophagus-related neoplasia: 6-year experience from the first 500 patients treated in the UK patient registry.

BACKGROUND: Barrett's oesophagus (BE) is a pre-malignant condition leading to oesophageal adenocarcinoma (OAC). Treatment of neoplasia at an early stage is desirable. Combined endoscopic mucosal resection (EMR) followed by radiofrequency ablation (RFA) is an alternative to surgery for patients with BE-related neoplasia. METHODS: We examined prospective data from the UK registry of patients undergoing RFA/EMR for BE-related neoplasia from 2008 to 2013. Before RFA, visible lesions were removed by EMR. Thereafter, patients had RFA 3-monthly until all BE was ablated or cancer developed (endpoints). End of treatment biopsies were recommended at around 12 months from first RFA treatment or when endpoints were reached. Outcomes for clearance of dysplasia (CR-D) and BE (CR-IM) at end of treatment were assessed over two time periods (2008-2010 and 2011-2013). Durability of successful treatment and progression to OAC were also evaluated. RESULTS: 508 patients have completed treatment. CR-D and CR-IM improved significantly between the former and later time periods, from 77% and 56% to 92% and 83%, respectively (p<0.0001). EMR for visible lesions prior to RFA increased from 48% to 60% (p=0.013). Rescue EMR after RFA decreased from 13% to 2% (p<0.0001). Progression to OAC at 12 months is not significantly different (3.6% vs 2.1%, p=0.51). CONCLUSIONS: Clinical outcomes for BE neoplasia have improved significantly over the past 6 years with improved lesion recognition and aggressive resection of visible lesions before RFA. Despite advances in technique, the rate of cancer progression remains 2-4% at 1 year in these high-risk patients. TRIAL REGISTRATION NUMBER: ISRCTN93069556.

British Society of Gastroenterology guidelines on the diagnosis and management of Barrett's oesophagus

These guidelines provide a practical and evidence-based resource for the management of patients with Barrett's oesophagus and related early neoplasia. The Appraisal of Guidelines for Research and Evaluation (AGREE II) instrument was followed to provide a methodological strategy for the guideline development. A systematic review of the literature was performed for English language articles published up until December 2012 in order to address controversial issues in Barrett's oesophagus including definition, screening and diagnosis, surveillance, pathological grading for dysplasia, management of dysplasia, and early cancer including training requirements. The rigour and quality of the studies was evaluated using the SIGN checklist system. Recommendations on each topic were scored by each author using a five-tier system (A+, strong agreement, to D+, strongly disagree). Statements that failed to reach substantial agreement among authors, defined as >80% agreement (A or A+), were revisited and modified until substantial agreement (>80%) was reached. In formulating these guidelines, we took into consideration benefits and risks for the population and national health system, as well as patient perspectives. For the first time, we have suggested stratification of patients according to their estimated cancer risk based on clinical and histopathological criteria. In order to improve communication between clinicians, we recommend the use of minimum datasets for reporting endoscopic and pathological findings. We advocate endoscopic therapy for high-grade dysplasia and early cancer, which should be performed in high-volume centres. We hope that these guidelines will standardise and improve management for patients with Barrett's oesophagus and related neoplasia.

Review article: gastrointestinal angiodysplasia - pathogenesis, diagnosis and management.

BACKGROUND: Angiodysplasia (AD) of the gastrointestinal (GI) tract is an important condition that can cause significant morbidity and -rarely - mortality. AIM: To provide an up-to-date comprehensive summary of the literature evaluating this disease entity with a particular focus on pathogenesis as well as current and emerging diagnostic and therapeutic modalities. Recommendations for treatment will be made on the basis of the current available evidence and consensus opinion of the authors. METHODS: A systematic literature search was performed. The search strategy used the keywords 'angiodysplasia' or 'arteriovenous malformation' or 'angioectasia' or 'vascular ectasia' or 'vascular lesions' or 'vascular abnormalities' or 'vascular malformations' in the title or abstract. RESULTS: Most AD lesions (54-81.9%) are detected in the caecum and ascending colon. They may develop secondary to chronic low-grade intermittent obstruction of submucosal veins coupled with increased vascular endothelial growth factor-dependent proliferation. Endotherapy with argon plasma coagulation resolves bleeding in 85% of patients with colonic AD. In patients who fail (or are not suitable for) other interventions, treatment with thalidomide or octreotide can lead to a clinically meaningful response in 71.4% and 77% of patients respectively. CONCLUSIONS: Angiodysplasia is a rare, but important, cause of both overt and occult GI bleeding especially in the older patients. Advances in endoscopic imaging and therapeutic techniques have led to improved outcomes in these patients. The choice of treatment should be decided on a patient-by-patient basis. Further research is required to better understand the pathogenesis and identify potential therapeutic targets.

Predictive factors for initial treatment response after circumferential radiofrequency ablation for Barrett's esophagus with early neoplasia: a prospective multicenter study.

BACKGROUND AND STUDY AIMS: Radiofrequency ablation (RFA) is safe and effective for the eradication of neoplastic Barrett's esophagus; however, occasionally there is minimal regression after initial circumferential balloon-based RFA (c-RFA). This study aimed to identify predictive factors for a poor response 3 months after c-RFA, and to relate the percentage regression at 3 months to the final treatment outcome. METHODS: We included consecutive patients from 14 centers who underwent c-RFA for high grade dysplasia at worst. Patient and treatment characteristics were registered prospectively. "Poor initial response" was defined as < 50 % regression of the Barrett's esophagus 3 months after c-RFA, graded by two expert endoscopists using endoscopic images. Predictors of initial response were identified through logistic regression analysis. RESULTS: There were 278 patients included (median Barrett's segment C4M6). In poor initial responders (n = 36; 13 %), complete response for neoplasia (CR-neoplasia) was ultimately achieved in 86 % (vs. 98 % in good responders; P < 0.01) and complete response for intestinal metaplasia (CR-IM) in 66 % (vs. 95 %; P < 0.01). Poor responders required 13 months treatment (vs. 7 months; P < 0.01) for a median of four RFA sessions (vs. three; P < 0.01). We identified four independent baseline predictors of poor response: active reflux esophagitis (odds ratio [OR] 37.4; 95 % confidence interval [CI] 3.2 - 433.2); endoscopic resection scar regeneration with Barrett's epithelium (OR 4.7; 95 %CI 1.1 - 20.0); esophageal narrowing pre-RFA (OR 3.9; 95 %CI 1.0 - 15.1); and years of neoplasia pre-RFA (OR 1.2; 95 %CI 1.0 - 1.4). CONCLUSIONS: Patients with a poor initial response to c-RFA have a lower ultimate success rate for CR-neoplasia/CR-IM, require more treatment sessions, and a longer treatment period. A poor initial response to c-RFA occurs more frequently in patients who regenerate their endoscopic resection scar with Barrett's epithelium, and those with ongoing reflux esophagitis, neoplasia in Barrett's esophagus for a longer time, or a narrow esophagus.

An inter-observer agreement study of autofluorescence endoscopy in Barrett's esophagus among expert and non-expert endoscopists.

BACKGROUND: Autofluorescence imaging (AFI), which is a "red flag" technique during Barrett's surveillance, is associated with significant false positive results. The aim of this study was to assess the inter-observer agreement (IOA) in identifying AFI-positive lesions and to assess the overall accuracy of AFI. METHODS: Anonymized AFI and high resolution white light (HRE) images were prospectively collected. The AFI images were presented in random order, followed by corresponding AFI + HRE images. Three AFI experts and 3 AFI non-experts scored images after a training presentation. The IOA was calculated using kappa and accuracy was calculated with histology as gold standard. RESULTS: Seventy-four sets of images were prospectively collected from 63 patients (48 males, mean age 69 years). The IOA for number of AF positive lesions was fair when AFI images were presented. This improved to moderate with corresponding AFI and HRE images [experts 0.57 (0.44-0.70), non-experts 0.47 (0.35-0.62)]. The IOA for the site of AF lesion was moderate for experts and fair for non-experts using AF images, which improved to substantial for experts [κ = 0.62 (0.50-0.72)] but remained at fair for non-experts [κ = 0.28 (0.18-0.37)] with AFI + HRE. Among experts, the accuracy of identifying dysplasia was 0.76 (0.7-0.81) using AFI images and 0.85 (0.79-0.89) using AFI + HRE images. The accuracy was 0.69 (0.62-0.74) with AFI images alone and 0.75 (0.70-0.80) using AFI + HRE among non-experts. CONCLUSION: The IOA for AF positive lesions is fair to moderate using AFI images which improved with addition of HRE. The overall accuracy of identifying dysplasia was modest, and was better when AFI and HRE images were combined.

High definition colonoscopy vs. standard video endoscopy for the detection of colonic polyps: a meta-analysis.

BACKGROUND AND STUDY AIMS: High definition colonoscopy may improve adenoma detection rates but studies report conflicting results. The aim of this meta-analysis was to compare the diagnostic yield of colonic polyps between high definition colonoscopy and standard video endoscopy (SVE). METHODS: Various electronic databases were searched for articles reporting on high definition colonoscopy. The pooled incremental yield and pooled weighted mean difference of high definition colonoscopy over SVE for polyp detection was determined. RESULTS: Five studies involving 4422 patients provided data on the total number of polyps detected. The incremental yield of high definition colonoscopy for the detection of any polyp was 3.8 % (95 % confidence interval [CI] 1 % - 6.7 %) with a number needed to treat (NNT) of 26. For the detection of adenomatous polyps the incremental yield was 3.5 % (95 %CI 0.9 % - 6.1 %) with an NNT of 28. There were no differences between high definition and SVE in the detection of high risk adenomas, with an incremental yield of -0.1 % (95 %CI -1.7 % to 1.6 %). When grouped according to the overall adenoma detection rate of the studies (> 50 % or < 50 %) the pooled weighted mean difference in small adenoma detection was better with high definition colonoscopy ( P = 0.035). CONCLUSIONS: There were marginal differences between high definition colonoscopy and SVE for the detection of colonic polyps/adenomas. High definition colonoscopy did not improve the detection of high risk adenomas. Due to differences in the adenoma detection rate between the studies and the nonrandomized study design of three of the five studies, these results need to be interpreted with caution. Prospective randomized trials looking at long term outcomes such as rates of interval or missed cancers are needed to clarify the clinical implications.