Observer agreement in the assessment of narrowband imaging system surface patterns in Barrett's esophagus: a multicenter study

A simpler diagnostic algorithm of the Japan Esophageal Society classification for Barrett's esophagus-related superficial neoplasia

BACKGROUND

We previously developed a Japan Esophageal Society Barrett's Esophagus (JES-BE) magnifying endoscopic classification for superficial BE-related neoplasms (BERN) and validated it in a nationwide multicenter study that followed a diagnostic flow chart based on mucosal and vascular patterns (MP, VP) with nine diagnostic criteria. Our present post hoc analysis aims to further simplify the diagnostic criteria for superficial BERN.

METHODS

We used data from our previous study, including 10 reviewers' assessments for 156 images of high-magnifying narrow-band imaging (HM-NBI) (67 dysplastic and 89 non-dysplastic histology). We statistically analyzed the diagnostic performance of each diagnostic criterion of MP (form, size, arrangement, density, and white zone), VP (form, caliber change, location, and greenish thick vessels [GTV]), and all their combinations to achieve a simpler diagnostic algorithm to detect superficial BERN.

RESULTS

Diagnostic accuracy values based on the MP of each single criterion or combined criteria showed a marked trend of being higher than those based on VP. In reviewers' assessments of visible MPs, the combination of irregularity for form, size, or white zone had the highest diagnostic performance, with a sensitivity of 87% and a specificity of 91% for dysplastic histology; in the assessments of invisible MPs, GTV had the highest diagnostic performance among the VP of each single criterion and all combinations of two or more criteria (sensitivity, 93%; specificity, 92%).

CONCLUSION

The present post hoc analysis suggests the feasibility of further simplifying the diagnostic algorithm of the JES-BE classification. Further studies in a practical setting are required to validate these results.

Diagnostic utility of a novel magnifying endoscopic classification system for superficial Barrett's esophagus-related neoplasms: a nationwide multicenter study

BACKGROUND

Currently, no classification system using magnification endoscopy for the diagnosis of superficial Barrett's esophagus (BE)-related neoplasia has been widely accepted. This nationwide multicenter study aimed to validate the diagnostic accuracy and reproducibility of the magnification endoscopy classification system, including the diagnostic flowchart developed by the Japan Esophageal Society-Barrett's esophagus working group (JES-BE) for superficial Barrett's esophagus-related neoplasms.

METHODS

The JES-BE acquired high-definition magnification narrow-band imaging (HM-NBI) images of non-dysplastic and dysplastic BE from 10 domestic institutions. A total of 186 high-quality HM-NBI images were selected. Thirty images were used for the training phase and 156 for the validation (test) phase. We invited five non-experts and five expert reviewers. In the training phase, the reviewers discussed how to correctly predict the histology based on the JES-BE criteria. In the validation phase, they evaluated whether the criteria accurately predicted the histology results according to the diagnostic flowchart. The validation phase was performed immediately after the training phase and at 6 weeks thereafter.

RESULTS

The sensitivity and specificity for all reviewers were 87% and 97%, respectively. Overall accuracy, positive predictive value, and negative predictive value were 91%, 98%, and 83%, respectively. The overall strength of inter-observer and intra-observer agreements for dysplastic histology prediction was κ = 0.77 and κ = 0.83, respectively. No significant difference in diagnostic accuracy and reproducibility between experts and non-experts was found.

CONCLUSION

The JES-BE classification system, including the diagnostic flowchart for predicting dysplastic BE, is acceptable and reliable, regardless of the clinician's experience level.

Feasibility of a simplified narrow-band imaging classification system for Barrett's esophagus for novice endoscopists

BACKGROUND

Narrow-band imaging (NBI) classifications for Barrett's esophagus have been proposed for the detection of early esophageal adenocarcinoma. We developed a simplified classification system with demonstrated high diagnostic accuracy and reproducibility among experienced endoscopists, but the feasibility of this system among novice endoscopists was unclear.

METHODS

In the present study, eight novice endoscopists with no experience of magnification endoscopy were asked to review 248 images of Barrett's esophagus (72 dysplastic, 176 non-dysplastic) obtained using high-definition magnification endoscopy with NBI 6 weeks before (1st test), immediately after (2nd test), and 6 weeks after (3rd test) being taught the simplified classification system. The primary outcomes were differences in diagnostic accuracy for dysplasia among the three tests.

RESULTS

The specificity and overall accuracy improved significantly in the 2nd vs. 1st test [97% vs. 80% (p < 0.001) and 94% vs. 82% (p < 0.001), respectively], but sensitivity was comparable (87% in both tests; p = 0.42). In the 3rd test, the sensitivity and overall accuracy decreased significantly compared with the 2nd test [82% vs. 87% (p < 0.001) and 93% vs. 94% (p < 0.05), respectively], but there was no significant difference in specificity (97% in both tests; p = 0.16). The kappa values for interobserver agreement for the mucosal pattern, vascular pattern, and predicted histology were substantial, and improved significantly in the 2nd vs. 1st test (0.78 vs. 0.59, 0.70 vs. 0.53, and 0.79 vs. 0.66, respectively; p < 0.001 for all).

CONCLUSIONS

The simplified NBI classification system may be appropriate for novice endoscopists to use in providing high accuracy and reproducibility.

Endoscopic diagnosis and treatment of esophageal adenocarcinoma: introduction of Japan Esophageal Society classification of Barrett's esophagus

Endoscopic surveillance of Barrett's esophagus has become a foundation of the management of esophageal adenocarcinoma (EAC). Surveillance for Barrett's esophagus commonly involves periodic upper endoscopy with biopsies of suspicious areas and random four-quadrant biopsies. However, targeted biopsies using narrow-band imaging can detect more dysplastic areas and thus reduce the number of biopsies required. Several specific mucosal and vascular patterns characteristic of Barrett's esophagus have been described, but the proposed criteria are complex and diverse. Simpler classifications have recently been developed focusing on the differentiation between dysplasia and non-dysplasia. These include the Japan Esophageal Society classification, which defines regular and irregular patterns in terms of mucosal and vascular shapes. Cancer invasion depth is diagnosed by endoscopic ultrasonography (EUS); however, a meta-analysis of EUS staging of superficial EAC showed favorable pooled values for mucosal cancer staging, but unsatisfactory diagnostic results for EAC at the esophagogastric junction. Endoscopic resection has recently been suggested as a more accurate staging modality for superficial gastrointestinal cancers than EUS. Following endoscopic resection for gastrointestinal cancers, the risk of metastasis can be evaluated based on the histology of the resected specimen. European guidelines describe endoscopic resection as curative for well- or moderately differentiated mucosal cancers without lymphovascular invasion, and these criteria might be extended to lesions invading the submucosa (≤ 500 μm), i.e., to low-risk, well- or moderately differentiated tumors without lymphovascular involvement, and < 3 cm. These criteria were confirmed by a recent study in Japan.

Usefulness of Non-magnifying Narrow Band Imaging in EVIS EXERA III Video Systems and High-Definition Endoscopes to Diagnose Dysplasia in Barrett's Esophagus Using the Barrett International NBI Group (BING) Classification

BACKGROUND

Narrow band imaging (NBI) allows identification of abnormal areas of Barrett's esophagus (BE) and could facilitate targeted biopsies.

AIMS

We evaluated the diagnostic accuracy for dysplasia prediction using non-magnifying NBI in Evis Exera III processors and high-definition endoscopes using the Barrett International NBI Group (BING) classification, as well as inter/intraobserver agreement for dysplasia prediction and mucosal/vascular patterns.

METHODS

Eight observers (4 staff endoscopists and 4 trainee endoscopists) evaluated 100 images selected from an anonymized bank of 470 photographs using the BING classification. Observers were to assign their individual assessment of the mucosal and vascular pattern, and prediction for dysplasia. Accuracy for dysplasia prediction and intra/interobserver agreement was calculated.

RESULTS

Dysplasia prediction had an accuracy of 81.1%, sensitivity of 48.4%, and a specificity of 91%. Positive predictive value and negative predictive value (NPV) were 61.4 and 85.5%, respectively. Dysplasia prediction done with a high degree of confidence (vs. low degree of confidence) had better diagnostic accuracy (85.8 vs. 70.7%). Interobserver concordance for dysplasia was weak: Κ = 0.40. Agreement for mucosal and vascular patterns was 0.39 and 0.30, respectively. Intraobserver concordance (assessed 6 months after initial test) for mucosal pattern, vascular pattern, and dysplasia prediction was moderate: Κ = 0.56, Κ = 0.47 and Κ = 0.60, respectively.

CONCLUSIONS

Our results showed that NBI had a significant accuracy in BE assessment for dysplasia prediction, high specificity (>90%), and NPV (>85%), with suboptimal sensitivity. NBI could be a useful additional tool for BE inspection and targeted biopsies, but cannot avoid the need for biopsies following the Seattle protocol.

Image assessment of Barrett's esophagus using the simplified narrow band imaging classification

BACKGROUND

A simplified narrow band imaging (NBI) classification has been proposed with the objective of integrating multiple classifications of NBI surface patterns in Barrett's esophagus (BE). Little is known about the impact of the simplified NBI classification on the diagnosis of BE when using high-definition magnification endoscopy with NBI (HM-NBI). This study aimed to evaluate (a) the reproducibility of NBI surface patterns and predicted histology and (b) the diagnostic accuracy of interpreting HM-NBI images by using the simplified NBI classification.

METHODS

Two hundred and forty-eight HM-NBI images from macroscopically normal areas in patients with BE were retrieved from endoscopy databases and randomized for review by four endoscopists (two experts, two non-experts). We evaluated inter- and intra-observer agreement of the interpretation of NBI surface patterns and the predicted histology (dysplasia vs. non-dysplasia), as calculated by using κ statistics, and diagnostic values of the prediction.

RESULTS

The overall inter-observer agreements were substantial for mucosal pattern (κ = 0.73) and vascular pattern (κ = 0.71), and almost perfect for predicting dysplastic histology (κ = 0.80). The overall intra-observer agreements were almost perfect for mucosal (κ = 0.84) and vascular patterns (κ = 0.86), and predicting dysplastic histology (κ = 0.89). The mean accuracy in predicting dysplastic histology for all reviewers was 95 % (experts: 96.8 %, non-experts: 93.1 %).

CONCLUSIONS

The simplified NBI classification has the potential to provide high diagnostic reproducibility and accuracy when using HM-NBI.

Ultrahigh speed en face OCT capsule for endoscopic imaging

Depth resolved and en face OCT visualization in vivo may have important clinical applications in endoscopy. We demonstrate a high speed, two-dimensional (2D) distal scanning capsule with a micromotor for fast rotary scanning and a pneumatic actuator for precision longitudinal scanning. Longitudinal position measurement and image registration were performed by optical tracking of the pneumatic scanner. The 2D scanning device enables high resolution imaging over a small field of view and is suitable for OCT as well as other scanning microscopies. Large field of view imaging for screening or surveillance applications can also be achieved by proximally pulling back or advancing the capsule while scanning the distal high-speed micromotor. Circumferential en face OCT was demonstrated in living swine at 250 Hz frame rate and 1 MHz A-scan rate using a MEMS tunable VCSEL light source at 1300 nm. Cross-sectional and en face OCT views of the upper and lower gastrointestinal tract were generated with precision distal pneumatic longitudinal actuation as well as proximal manual longitudinal actuation. These devices could enable clinical studies either as an adjunct to endoscopy, attached to an endoscope, or as a swallowed tethered capsule for non-endoscopic imaging without sedation. The combination of ultrahigh speed imaging and distal scanning capsule technology could enable both screening and surveillance applications.

Endoscopic diagnosis of dysplasia in Barrett's esophagus

Barrett's esophagus, or columnar metaplasia with gastric cardiac cells or intestinal cells, develops in the squamous epithelium of the esophageal mucosa in relation to gastroesophageal reflux. An increased risk of neoplasia justifies surveillance at regular intervals. Conventional guidelines recommend detection of areas with intestinal metaplasia or dysplasia by taking random four-quadrant biopsies at every 1 or 2 cm. Alternatively, image processing with narrow band imaging (NBI), is proposed to improve detection. This international and randomized study in persons with Barrett's esophagus compares conventional endoscopy in white light with random four-quadrant biopsies and NBI imaging with focused biopsies only. Randomization enrolled 123 patients with Barrett's esophagus who successively underwent exploration with the two methods. The study confirmed that NBI had the same efficacy as white light in the detection of intestinal metaplasia, with a higher proportion of dysplasia detected (30 vs 21%) and a lower number of biopsies per patient (3.6 vs 7.6).

Endoscopic assessment and grading of Barrett's esophagus using magnification endoscopy and narrow band imaging: impact of structured learning and experience on the accuracy of the Amsterdam classification system

OBJECTIVE

Several classification systems have been launched to characterize Barrett's esophagus (BE) mucosa using magnification endoscopy with narrow band imaging (ME-NBI). The good accuracy and interobserver agreement described in the early reports were not reproduced subsequently. Recently, we reported somewhat higher accuracy of the classification developed by the Amsterdam group. The critical question then formulated was whether a structured learning program and the level of experience would affect the clinical usefulness of this classification.

MATERIAL & METHODS

Two hundred and nine videos were prospectively captured from patients with BE using ME-NBI. From these, 70 were randomly selected and evaluated by six endoscopists with different levels of expertise, using a dedicated software application. First, an educational set was studied. Thereafter, the 70 test videos were evaluated. After classification of each video, the respective histological feedback was automatically given.

RESULTS

Within the learning process, there was a decrease in the time needed for evaluation and an increase in the certainty of prediction. The accuracy did not increase with the learning process. The sensitivity for detection of intestinal metaplasia ranged between 39% and 57%, and for neoplasia between 62% and 90%, irrespective of assessor's expertise. The kappa coefficient for the interobserver agreement ranged from 0.25 to 0.30 for intestinal metaplasia, and from 0.39 to 0.48 for neoplasia.

CONCLUSION

Using a dedicated learning program, the ME-NBI Amsterdam classification system is suboptimal in terms of accuracy and inter- and intraobserver agreements. These results reiterate the questionable utility of corresponding classification system in clinical routine practice.