Computer-aided characterization of early cancer in Barrett's esophagus on i-scan magnification imaging: a multicenter international study.

BACKGROUND AND AIMS: We aimed to develop a computer-aided characterization system that could support the diagnosis of dysplasia in Barrett's esophagus (BE) on magnification endoscopy. METHODS: Videos were collected in high-definition magnification white-light and virtual chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic and nondysplastic BE (NDBE) from 4 centers. We trained a neural network with a Resnet101 architecture to classify frames as dysplastic or nondysplastic. The network was tested on 3 different scenarios: high-quality still images, all available video frames, and a selected sequence within each video. RESULTS: Fifty-seven patients, each with videos of magnification areas of BE (34 dysplasia, 23 NDBE), were included. Performance was evaluated by a leave-1-patient-out cross-validation method. In all, 60,174 (39,347 dysplasia, 20,827 NDBE) magnification video frames were used to train the network. The testing set included 49,726 i-scan-3/optical enhancement magnification frames. On 350 high-quality still images, the network achieved a sensitivity of 94%, specificity of 86%, and area under the receiver operator curve (AUROC) of 96%. On all 49,726 available video frames, the network achieved a sensitivity of 92%, specificity of 82%, and AUROC of 95%. On a selected sequence of frames per case (total of 11,471 frames), we used an exponentially weighted moving average of classifications on consecutive frames to characterize dysplasia. The network achieved a sensitivity of 92%, specificity of 84%, and AUROC of 96%. The mean assessment speed per frame was 0.0135 seconds (SD ± 0.006). CONCLUSION: Our network can characterize BE dysplasia with high accuracy and speed on high-quality magnification images and sequence of video frames, moving it toward real-time automated diagnosis.

A new artificial intelligence system successfully detects and localises early neoplasia in Barrett's esophagus by using convolutional neural networks.

BACKGROUND AND AIMS: Seattle protocol biopsies for Barrett's Esophagus (BE) surveillance are labour intensive with low compliance. Dysplasia detection rates vary, leading to missed lesions. This can potentially be offset with computer aided detection. We have developed convolutional neural networks (CNNs) to identify areas of dysplasia and where to target biopsy. METHODS: 119 Videos were collected in high-definition white light and optical chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic and non-dysplastic BE (NDBE). We trained an indirectly supervised CNN to classify images as dysplastic/non-dysplastic using whole video annotations to minimise selection bias and maximise accuracy. The CNN was trained using 148,936 video frames (31 dysplastic patients, 31 NDBE, two normal esophagus), validated on 25,161 images from 11 patient videos and tested on 264 iscan-1 images from 28 dysplastic and 16 NDBE patients which included expert delineations. To localise targeted biopsies/delineations, a second directly supervised CNN was generated based on expert delineations of 94 dysplastic images from 30 patients. This was tested on 86 i-scan one images from 28 dysplastic patients. FINDINGS: The indirectly supervised CNN achieved a per image sensitivity in the test set of 91%, specificity 79%, area under receiver operator curve of 93% to detect dysplasia. Per-lesion sensitivity was 100%. Mean assessment speed was 48 frames per second (fps). 97% of targeted biopsy predictions matched expert and histological assessment at 56 fps. The artificial intelligence system performed better than six endoscopists. INTERPRETATION: Our CNNs classify and localise dysplastic Barrett's Esophagus potentially supporting endoscopists during surveillance.

Radiofrequency ablation for Barrett's oesophagus related neoplasia with the 360 Express catheter: initial experience from the United Kingdom and Ireland-preliminary results.

BACKGROUND: Radio-frequency ablation (RFA) for Barrett's oesophagus (BE)-related neoplasia is currently used after endoscopic resection of visible neoplasia. The HALO 360 balloon has been used to ablate long segment BE. The Barrx™ 360 Express RFA self-sizing catheter ('RFA Express') may potentially allow quicker ablation times and improved treatment outcomes. The aim of this paper is to present real world data on the use of the 360 Express Device. METHODS: Centres in the UK and Ireland submitted cases where the RFA Express was used. The primary outcome was regression of BE at 3 months. Secondary outcomes were the rate of symptomatic stricture formation and resolution of intestinal metaplasia (CR-IM) and dysplasia (CR-D) at End of Treatment (EoT). RESULTS: 11 centres submitted 123 consecutive patients. 112 had a follow up endoscopy. The median age was 67 years (IQR 62-75). 3 dosimetries were used. The mean reduction in Circumferential (C) length was 78% ± 36 and mean reduction in Maximal length (M) was 55% ± 36. 17 patients (15%) developed strictures requiring dilation. There was a higher rate of stricture formation when the 12 J energy was used (p < 0.05). 47 patients had EoT biopsies, 40 (85%) had CR-D and 34(76%) had CR-IM. CONCLUSIONS: The RFA 360 Express catheter shows reduction in length of baseline BE at 3 months after index treatment, and eradication of intestinal metaplasia and dysplasia at 12 months similar to other studies with earlier devices. It appears that the symptomatic stricture rate is slightly higher than previous series with the HALO 360 catheter. This study was performed as part of the HALO registry and has been approved by the Research Ethics Committee - MREC Number 08/H0714/27 Local project reference 08/0104 Project ID 15,033 IRAS Number 54678 EudraCT 2009-015980-1. Registered on ISRCTN as below: ISRCTN93069556. https://doi.org/10.1186/ISRCTN93069556.

Esophageal squamous dysplasia and cancer: Is artificial intelligence our best weapon?

Esophageal cancer is the eight most common cancer in the world and is associated with a poor prognosis. Significant efforts are necessary to improve the detection of early squamous cell cancer such that curative endoscopic therapy can be offered. Studies have shown an overall miss rate of esophageal cancer of up to 6.4%. Human factors including fatigue and lack of attention may be a contributory factor. Computer aided detection and characterisation of early squamous cell cancer can be a second reader which potentially offsets these factors. Recent studies developing artificial intelligence systems show real promise in the detection of early squamous cell cancer and predicting depth of invasion to aid in the management of patients in the same endoscopic session. This has the potential to revolutionise this area of 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.

Cryoballoon ablation for treatment of patients with refractory esophageal neoplasia after first line endoscopic eradication therapy.

Background and study aims Cryoablation with the Cryoballoon device is a novel ablative therapy that uses cycles of freezing and thawing to induce cell death. This single-center prospective study evaluated the feasibility of the focal cryoablation device for the treatment of areas of refractory esophageal neoplasia in patients who had undergone first line endoscopic eradication therapy (EET). Complete remission of dysplasia (CR-D) and complete remission of intestinal metaplasia (CR-IM) at first follow-up endoscopy, durability of disease reversal, rates of stenosis and adverse events were studied. Patients and methods Eighteen cases were treated. At baseline, nine patients had low-grade dysplasia (LGD), six had high-grade dysplasia (HGD) and three had intramucosal carcinoma (IMC). Median length of dysplastic Barrett's esophagus (BE) treated was 3 cm. The median number of ablations per patient was 11. Each selected area of visible dysplasia received 10 seconds of ablation. One session of cryoablation was performed per patient. Biopsies were performed at around 3 months post-ablation. Results CR-D was achieved in 78 % and CR-IM in 39 % of patients. There were no device malfunction or adverse events. Stenosis was noted in 11 % of cases. At a median follow up of 19-months, CR-D was maintained in 72 % of patients and CR-IM in 33 %. Conclusions Cryoablation appears to be a viable rescue strategy in patients with refractory neoplasia. It is well tolerated and successful in obtaining CR-D and CR-IM in patients with treatment-refractory BE. Further trials of dosimetry, efficacy and safety in treatment-naïve patients are underway.

Quality indicators for Barrett's endotherapy (QBET): UK consensus statements for patients undergoing endoscopic therapy for Barrett's neoplasia.

INTRODUCTION: Endoscopic therapy for the management of patients with Barrett's oesophagus (BE) neoplasia has significantly developed in the past decade; however, significant variation in clinical practice exists. The aim of this project was to develop expert physician-lead quality indicators (QIs) for Barrett's endoscopic therapy. METHODS: The RAND/UCLA Appropriateness Method was used to combine the best available scientific evidence with the collective judgement of experts to develop quality indicators for Barrett's endotherapy in four subgroups: pre-endoscopy, intraprocedure (resection and ablation) and postendoscopy. International experts, including gastroenterologists, surgeons, BE pathologist, clinical nurse specialist and patient representative, participated in a three-round process to develop 15 QIs that fulfilled the RAND/UCLA definition of appropriateness. RESULTS: 17 experts participated in round 1 and 20 in round 2. Of the 24 proposed QIs in round 1, 20 were ranked as appropriate (put through to round 2) and 4 as uncertain (discarded). At the end of round 2, a final list of 15 QIs were scored as appropriate. CONCLUSIONS: This UK national consensus project has successfully developed QIs for patients undergoing Barrett's endotherapy. These QIs can be used by service providers to ensure that all patients with BE neoplasia receive uniform and high-quality care.

Risk factors for serious adverse events associated with multiband mucosectomy in Barrett's esophagus: an international multicenter analysis of 3827 endoscopic resection procedures.

BACKGROUND AND AIMS: Multiband mucosectomy (MBM) is a widely used technique for the treatment of Barrett's esophagus (BE). However, large multicenter studies enabling a generalizable estimation of the risk of serious adverse events, such as perforation and postprocedural bleeding, are lacking. The aim of this study was to estimate the rate of, and risk factors for, serious adverse events associated with MBM. METHODS: In this retrospective analysis, consecutive patients who underwent MBM for treatment of BE in 14 tertiary referral centers in Europe, the United States, Canada, and Australia were included. Primary outcomes were perforation and postprocedural bleeding rate. Potential risk factors were identified by logistic regression. RESULTS: Between 2001 and 2016, a total of 3827 MBM procedures were performed in 2447 patients (84% male, mean age 66 years, median BE length C2M4). Perforation occurred in 17 procedures (0.4%; 95% confidence interval [CI], 0.3-0.7), of which 15 could be treated endoscopically or conservatively. Female gender was an independent risk factor for perforation (odds ratio [OR], 2.77; 95% CI, 1.02-7.57; P = .05). Postprocedural bleeding occurred after 35 procedures (0.9%; 95% CI, 0.6-1.3). The number of resections (OR, 1.15; 95% CI, 1.06-1.25; P < .001) was significantly associated with postprocedural bleeding. CONCLUSION: The results of this study show that MBM for BE is safe with a low risk of serious adverse events. In addition, most of the adverse events could be managed endoscopically or conservatively. The number of resections was an independent risk factor for postprocedural bleeding.

Intrapapillary capillary loop classification in magnification endoscopy: open dataset and baseline methodology.

PURPOSE: Early squamous cell neoplasia (ESCN) in the oesophagus is a highly treatable condition. Lesions confined to the mucosal layer can be curatively treated endoscopically. We build a computer-assisted detection system that can classify still images or video frames as normal or abnormal with high diagnostic accuracy. METHODS: We present a new benchmark dataset containing 68K binary labelled frames extracted from 114 patient videos whose imaged areas have been resected and correlated to histopathology. Our novel convolutional network architecture solves the binary classification task and explains what features of the input domain drive the decision-making process of the network. RESULTS: The proposed method achieved an average accuracy of 91.7% compared to the 94.7% achieved by a group of 12 senior clinicians. Our novel network architecture produces deeply supervised activation heatmaps that suggest the network is looking at intrapapillary capillary loop patterns when predicting abnormality. CONCLUSION: We believe that this dataset and baseline method may serve as a reference for future benchmarks on both video frame classification and explainability in the context of ESCN detection. A future work path of high clinical relevance is the extension of the classification to ESCN types.

Radiofrequency ablation for patients with refractory symptomatic anaemia secondary to gastric antral vascular ectasia.

Background: Gastric antral vascular ectasia (GAVE) is a rare cause of gastrointestinal bleeding, often causing iron deficiency anaemia. Previous studies have looked at the management of this with argon plasma coagulation, laser therapy and endoscopic band ligation. Methods: This was a single-centre prospective study to evaluate the efficacy and safety of radiofrequency ablation (RFA) in patients with GAVE with persistent anaemia refractory to at least one session of first-line endoscopic therapy. Patients were treated with a through-the-scope (TTS) radiofrequency catheter at two endoscopic sessions six weeks apart. The primary outcome was change in haemoglobin at six months posttreatment. The secondary outcomes were reduction in blood or iron requirements, endoscopic surface area regression and complications. Results: Twenty patients were treated. The mean change in haemoglobin at six months was +12.6 g/l (95% confidence interval 11.7-24.3 g/l), paired t test p < 0.001. At six months, three of 14 individuals who had required blood transfusions had ongoing blood transfusions and five of 17 who had required iron had ongoing iron needs. Surface area regression was scored as 74% ± 25% but no correlation was seen between this and other outcomes. Three of 20 patients experienced pain which was managed with oral analgesia. Of the 14 patients who had reached 12-month follow-up, three required retreatment (21%). Discussion: This small study suggests that RFA is a safe and effective treatment for GAVE. Our study uses the TTS catheter compared to other studies, and demonstrates prolonged improvement in haemoglobin and reduction in blood and iron requirements with a novel assessment of surface area regression.

Comparison of two multiband mucosectomy devices for endoscopic resection of Barrett's esophagus-related neoplasia.

BACKGROUND: Esophageal adenocarcinoma carries a poor prognosis and therefore treatment of early neoplasia arising in the precursor condition Barrett's esophagus (BE) is desirable. Visible lesions arising in BE need endoscopic mucosal resection for accurate staging and removal. Resection modalities include a cap-based system with snare and custom-made multiband mucosectomy (MBM) devices (Duette, Cook Medical Ltd). A new MBM device has recently become available (Captivator, Boston Scientific Ltd). OBJECTIVES: A retrospective pilot study to compare the efficacy, safety, specimen size and histology of endoscopic mucosal resection (EMR) specimens resected with two MBM devices (Cook Duette and Boston Captivator) in treatment naive patients undergoing endoscopic therapy for BE neoplasia. METHODS: Consecutive EMR procedures carried out by a single experienced endoscopist were analysed. All visible lesions were marked and resected using one of the two MBM devices. All resected specimens were analysed by the same two experienced pathologists. The resected specimens in both groups were analysed for maximum diameter, minimum diameter, surface area and depth. RESULTS: Twenty consecutive patients were analysed (18M + 2F; mean age 74) in the Duette group and 20 (17M + 3F; mean age 72) in the Captivator group. A total of 58 specimens were resected in the Duette and 63 in the Captivator group. Min diameter, max diameter, surface area and depth of the ER specimens resected by the Captivator device were significantly larger than that by the Duette device [min diameter 9.89 mm vs 9.07 mm (p = 0.019); max diameter: 13.54 mm vs 12.38 mm (p = 0.024); surface area: 135.40 mm2 vs 113.89 mm2 (p = 0.005); depth 3.71 mm vs 2.89 (p = 0.001)]. CONCLUSIONS: These two MBM devices showed equivalent efficacy and safety outcomes, but the EMR Captivator device resected specimens with a larger area in the esophagus when compared with the Duette device. A possible advantage of this is in situations where en bloc resections with fewer EMRs are desirable for larger lesions.

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.