The utility of a novel narrow band imaging endoscopy system in patients with Barrett's esophagus

Exploring vision transformers for classifying early Barrett's dysplasia in endoscopic images: A pilot study on white-light and narrow-band imaging

BACKGROUND AND AIM

Various deep learning models, based on convolutional neural network (CNN), have been shown to improve the detection of early esophageal neoplasia in Barrett's esophagus. Vision transformer (ViT), derived from natural language processing, has emerged as the new state-of-the-art for image recognition, outperforming predecessors such as CNN. This pilot study explores the use of ViT to classify the presence or absence of early esophageal neoplasia in endoscopic images of Barrett's esophagus.

METHODS

A BO dataset of 1918 images of Barrett's esophagus from 267 unique patients was used. The images were classified as dysplastic (D-BO) or non-dysplastic (ND-BO). A pretrained vision transformer model, ViTBase16, was used to develop our classifier models. Three ViT models were developed for comparison based on imaging modality: white-light imaging (WLI), narrow-band imaging (NBI), and combined modalities. Performance of each model was evaluated based on accuracy, sensitivity, specificity, confusion matrices, and receiver operating characteristic curves.

RESULTS

The ViT models demonstrated the following performance: WLI-ViT (Accuracy: 92%, Sensitivity: 82%, Specificity: 95%), NBI-ViT (Accuracy: 99%, Sensitivity: 97%, Specificity: 99%), and combined modalities-ViT (Accuracy: 93%, Sensitivity: 87%, Specificity: 95%). Combined modalities-ViT showed greater accuracy (94% vs 90%) and sensitivity (80% vs 70%) compared with WLI-ViT when classifying WLI images on a subgroup testing set.

CONCLUSION

ViT exhibited high accuracy in classifying the presence or absence of EON in endoscopic images of Barrett's esophagus. ViT has the potential to be widely applicable to other endoscopic diagnoses of gastrointestinal diseases.

Curative criteria for endoscopic treatment of oesophageal adenocarcinoma

The incidence of oesophageal adenocarcinoma has been increasing rapidly in the Western world. A well-known risk factor for developing this type of tumour is reflux disease, which can cause metaplasia from the squamous cell mucosa to columnar epithelium (Barrett's Oesophagus) which can progress to dysplasia and eventually adenocarcinoma. With the rise of the incidence of oesophageal adenocarcinoma, research on the best way to manage this disease is of great importance and has changed treatment modalities over the last decades. The gold standard for superficial adenocarcinoma has shifted from surgical to endoscopic management when certain criteria are met. This review will discuss the different curative criteria for endoscopic treatment of oesophageal adenocarcinoma.

Intestinal metaplasia in follow-up endoscopies among Asian patients with short-segment Barrett's esophagus: Regression, sampling error, and associated factors

BACKGROUND

The percentage of and factors associated with the regression of Barrett's esophagus (BE) or its characteristic intestinal metaplasia (IM) remain unclear, and conflicting results have been reported because of diverse regression and sampling error definitions. Thus, we investigated the rates of IM regression, sampling error, and associated factors.

METHODS

Forty-two patients with proven short-segment BE with IM who underwent two follow-up endoscopies with biopsies of Barrett's mucosa were retrospectively analyzed. Additional Alcian blue and MUC2 staining were done on the biopsy specimens without IM in hematoxylin-eosin staining. Only patients with negative hematoxylin-eosin, Alcian blue, and MUC2 staining for IM in both follow-up endoscopies were considered to have true regression. When all three stains were negative for IM in the first, but positive in the second follow-up endoscopy, we considered IM persisting and declared sampling error.

RESULTS

Among the 18 patients without IM at the first follow-up endoscopy, only five (11.9%) were judged to have true regression. Prolonged proton-pump inhibitor use was significantly associated with regression. Limited experience of the endoscopist, and insufficient biopsy number were significantly related to sampling error. Receiver operating characteristic (ROC) curve analysis showed the best cut-off value of the biopsy number/maximal-length (cm) ratio to predict sampling error was 2.25.

CONCLUSION

In our patients with short-segment BE, 11.9% experienced regression of IM. Prolonged proton-pump inhibitors treatment was associated with regression. An insufficient biopsy number was related to a missed IM, which may be eliminated by maintaining biopsy number/maximal-length (cm) ratio ≥2.25.

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.

Carcinogenic potential in regenerated mucosa after endoscopic resection of esophageal squamous cell carcinoma

BACKGROUND AND AIM

Little is known about genetic mutations in the regenerated mucosa (RM) after endoscopic resection (ER) of esophageal carcinoma. Thus, this study investigates the status of genetic variation in RM after ER of esophageal squamous cell carcinoma (ESCC).

METHODS

The study cohort included 19 patients with ESCC. We used an esophageal carcinoma panel to identify target sequences for squamous cell carcinoma (SCC), background mucosa (BM), and RM after ER of ESCC. We used OncoKB to check whether each mutation was a putative driver.

RESULTS

We identified 77 mutations of 32 genes in SCC, 133 mutations of 34 genes in BM, and 100 mutations of 29 genes in RM. Putative driver mutations were identified in 20 mutations in 14 cases in SCC, 16 mutations in 10 cases in BM, and 7 mutations in 11 cases in RM. The rate of putative driver mutations to total mutations was significantly lower in RM (26% in SCC vs 12% in BM vs 7% in RM, P = 0.009). Additionally, the rate of cases with TP53 putative driver mutations was significantly lower in RM (63% in SCC vs 37% in BM vs 16% in RM, P = 0.011). The percentage of putative driver mutations and the percentage of cases with a putative driver of TP53 were significantly lower in RM.

CONCLUSION

Esophageal RM after ER of ESCC could have a lower risk of carcinogenesis.

Microarchitectures of Barrett's esophagus associated with DNA methylation status

Aim: DNA methylation is involved in esophageal adenocarcinoma (EAC) and Barrett's esophagus (BE). Microarchitectures of on-neoplastic BE associated with DNA methylation status were examined using magnifying narrow-band imaging (NBI) endoscopy. Patients and methods: Using biopsies from non-neoplastic BE without cancer (n = 66; N group), with EAC (n = 27; ADJ group) and EAC tissue (n = 22; T group), methylation of N33, DPYS, SLC16A12, miR124a3 and miR34bc genes were quantified. Magnifying NBI features of non-neoplastic BE were classified according to their morphologies. Results: The ADJ and T groups presented higher DNA methylation compared with the N group. Magnifying NBI endoscopic features of non-neoplastic BE also correlated with DNA methylation as an independent factor. Conclusion: Microarchitectures of BE visualized by magnifying NBI endoscopy correlated with DNA methylation.

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.

Global variations in diagnostic guidelines for Barrett's esophagus

Endoscopic diagnosis of gastroesophageal junction and Barrett's esophagus is essential for surveillance and early detection of esophageal adenocarcinoma and esophagogastric junction cancer. Despite its small size, the gastroesophageal junction has many inherent problems, including marked differences in diagnostic methods for Barrett's esophagus in international guidelines. To define Barrett's esophagus, gastroesophageal junction location should be clarified. Although gastric folds and palisade vessels are landmarks for identifying this junction, they are sometimes difficult to observe due to air entry or reflux esophagitis. The possibility of diagnosing a malignancy associated with Barrett's esophagus <1 cm, identified using palisade vessels, should be re-examined. Nontargeted biopsies of Barrett's esophagus are commonly used to detect intestinal metaplasia, dysplasia, and cancer as described in the Seattle protocol. Barrett's esophagus with intestinal metaplasia has a high risk of becoming cancerous. Furthermore, the frequency of cancer in patients with Barrett's esophagus without intestinal metaplasia is high, and the guidelines differ on whether to include the presence of intestinal metaplasia in the diagnosis of Barrett's esophagus. Use of advanced imaging technologies, including narrow-band imaging with magnifying endoscopy and linked color imaging, is reportedly valid for diagnosing Barrett's esophagus. Furthermore, artificial intelligence has facilitated the diagnosis of Barrett's esophagus through its deep learning and image recognition capabilities. However, it is necessary to first use the endoscopic definition of the gastroesophageal junction, which is common in all countries, and then elucidate the characteristics of Barrett's esophagus in each region, for example, length differences in the risk of carcinogenesis with and without intestinal metaplasia.

Which factors make Barrett's esophagus lesions difficult to diagnose?

Background and study aims  Although the Japan Esophageal Society's magnifying endoscopic classification for Barrett's epithelium (JES-BE) offers high diagnostic accuracy, some cases are challenging to diagnose as dysplastic or non-dysplastic in daily clinical practice. Therefore, we investigated the diagnostic accuracy of this classification and the clinicopathological features of Barrett's esophagus cases that are difficult to diagnose correctly. Patients and methods  Five endoscopists with experience with fewer than 10 cases of magnifying observation for superficial Barrett's esophageal carcinoma reviewed 132 images of Barrett's mucosa or carcinoma (75 dysplastic and 57 non-dysplastic cases) obtained using high-definition magnification endoscopy with narrow-band imaging (ME-NBI). They diagnosed each image as dysplastic or non-dysplastic according to the JES-BE classification, and the diagnostic accuracy was calculated. To identify risk factors for misdiagnosed images, images with a correct rate of less than 40 % were defined as difficult-to-diagnose, and those with 60 % or more were defined as easy-to-diagnose. Logistic regression analysis was performed to identify risk factors for difficult-to-diagnose images. Results  The sensitivity, specificity and overall accuracy were 67 %, 80 % and 73 %, respectively. Of the 132 ME-NBI images, 34 (26 %) were difficult-to-diagnose and 99 (74 %) were easy-to-diagnose. Logistic regression analysis showed low-grade dysplasia (LGD) and high-power magnification images were each significant risk factors for difficult-to-diagnose images (OR: 6.80, P  = 0.0017 and OR: 3.31, P  = 0.0125, respectively). Conclusions  This image assessment study suggested feasibility of the JES-BE classification for diagnosis of Barrett's esophagus by non-expert endoscopists and risk factors for difficult diagnosis as high-power magnification and LGD histology. For non-experts, high-power magnification images are better evaluated in combination with low-power magnification images.

Kyoto international consensus report on anatomy, pathophysiology and clinical significance of the gastro-oesophageal junction

OBJECTIVE

An international meeting was organised to develop consensus on (1) the landmarks to define the gastro-oesophageal junction (GOJ), (2) the occurrence and pathophysiological significance of the cardiac gland, (3) the definition of the gastro-oesophageal junctional zone (GOJZ) and (4) the causes of inflammation, metaplasia and neoplasia occurring in the GOJZ.

DESIGN

Clinical questions relevant to the afore-mentioned major issues were drafted for which expert panels formulated relevant statements and textural explanations.A Delphi method using an anonymous system was employed to develop the consensus, the level of which was predefined as ≥80% of agreement. Two rounds of voting and amendments were completed before the meeting at which clinical questions and consensus were finalised.

RESULTS

Twenty eight clinical questions and statements were finalised after extensive amendments. Critical consensus was achieved: (1) definition for the GOJ, (2) definition of the GOJZ spanning 1 cm proximal and distal to the GOJ as defined by the end of palisade vessels was accepted based on the anatomical distribution of cardiac type gland, (3) chemical and bacterial (Helicobacter pylori) factors as the primary causes of inflammation, metaplasia and neoplasia occurring in the GOJZ, (4) a new definition of Barrett's oesophagus (BO).

CONCLUSIONS

This international consensus on the new definitions of BO, GOJ and the GOJZ will be instrumental in future studies aiming to resolve many issues on this important anatomic area and hopefully will lead to better classification and management of the diseases surrounding the GOJ.

Usefulness of the Japan Esophageal Society Classification of Barrett's Esophagus for Diagnosing the Lateral Extent of Superficial Short-Segment Barrett's Esophageal Cancer

Introduction

The Japanese guidelines for endoscopic submucosal dissection (ESD) of Barrett's esophageal adenocarcinoma (BEA) recommend image-enhanced magnifying endoscopic examination for diagnosing the lateral extent of superficial esophageal adenocarcinoma. The Japan Esophageal Society Barrett's Esophagus (JES-BE) classification is proposed recently and is useful in terms of diagnostic accuracy. In this study, we retrospectively examined the usefulness of the JES-BE classification for differential diagnosis and determination of the extent of BEA originating in short-segment Barrett's esophagus.

Methods

The study reviewed 51 lesions which underwent ESD for BEA. The circumference of the esophagogastric junction was divided into four parts, and the lesions were divided into those in the right anterior portion (RA group; n = 33) and those in other portions (non-RA group; n = 18). Clinicopathological characteristics and clinical outcomes were compared between the two groups.

Results

JES-BE classification findings as "dysplasia" were seen in 48 out of 51 (94.1%) BEA lesions retrospectively. There was no significant difference in histological type, tumor depth, lymphovascular invasion, or the proportion of tumors with a positive or unknown horizontal or vertical margin status between the groups. The proportion of tumors with type 0-I morphology was significantly higher in the RA group (p = 0.023). The tumor size was significantly greater in the RA group (p = 0.034). According to the JES-BE classification, 31 lesions (93.9%) in the RA group and 17 lesions (94.4%) in the non-RA group were diagnosed as dysplasia. There was also no significant difference in the rate of consistency between the endoscopic and histopathological findings on the lateral extent of the lesion (90.9% vs. 83.3%; p = 0.612).

Discussion/Conclusions

The JES-BE classification may be useful for determining the extent of BEA.

Endoscopic OCT Angiography Using Clinical Proximal-End Scanning Catheters

Endoscopic optical coherence tomography angiography (OCTA) is a promising modality to inspect the microvasculature of inner organs in the early-stage tumor diagnosis. However, an endoscopic clinical proximal-end scanning catheter has limited flow imaging capability due to the nonuniform rotational distortion (NURD) and physiological motion. In this study, a combined local and global (CLG) optical flow algorithm was used to estimate the motion vectors caused by NURD and physiological motion. The motion vectors were used to bicubic-interpolation-resample the OCT structure to ensure that the circumferential pixels were equally spaced in the space domain. Then, angiograms were computed based on the statistical relation between inverse SNR (iSNR) and amplitude decorrelation (IDa), termed as IDa-OCTA. Finally, the ability of this technique for endoscopic OCTA imaging was demonstrated by flow phantom experiments and human nailfold capillary imaging.

Electronic chromo-endoscopy: technical details and a clinical perspective

Precise endoscopic assessment is necessary to detect neoplastic changes in an early stage. Electronic or virtual chromo-endoscopy (ECE) is an alternative to conventional dye-based chromo-endoscopy which markedly improves capillary pattern and hence can detect micro-vessel morphological changes of early neoplasia to target biopsies and aid in diagnosis. The clinical significance increased after the advent of endoscopic treatment modalities like ESD/EMR which requires precise delineation of extent and depth of lesion. Most of the studies have used narrow-band imaging (NBI) (Olympus Medical Systems Tokyo, Japan), although data from i-SCAN (PENTAX Endoscopy, Tokyo, Japan) and flexible spectral imaging color enhancement (FICE) (Fujinon, Fujifilm Medical Co, Saitama, Japan) are emerging. Electronic chromo-endoscopy is convenient compared to dye-based chromo-endoscopy in the sense that it is available at the push of a button in endoscope and reduces procedure time substantially with comparable efficacy. Scope of this review is to discuss available electronic chromo-endoscopy modalities and their role in the diagnosis, surveillance, and management of early GI neoplasia.

Hybrid Stomach-Intestinal Chromatin States Underlie Human Barrett's Metaplasia

BACKGROUND & AIMS

Tissue metaplasia is uncommon in adults because established cis-element programs resist rewiring. In Barrett's esophagus, the distal esophageal mucosa acquires a predominantly intestinal character, with notable gastric features, and is predisposed to developing invasive cancers. We sought to understand the chromatin underpinnings of Barrett's metaplasia and why it commonly displays simultaneous gastric and intestinal properties.

METHODS

We profiled cis-regulatory elements with active histone modifications in primary human biopsy materials using chromatin immunoprecipitation followed by DNA sequencing. Mutations in Barrett's esophagus were examined in relation to tissue-specific enhancer landscapes using a random forest machine-learning algorithm. We also profiled open chromatin at single-cell resolution in primary Barrett's biopsy specimens using the assay for transposase-accessible chromatin. We used 1- and 2-color immunohistochemistry to examine protein expression of tissue-restricted genes.

RESULTS

Barrett's esophagus bears epigenome fingerprints of human stomach and intestinal columnar, but not esophageal squamous, epithelia. Mutational patterns were best explained as arising on the epigenome background of active gastric cis-elements, supporting the view that adjoining stomach epithelium is a likely tissue source. Individual cells in Barrett's metaplasia coexpress gastric and intestinal genes, reflecting concomitant chromatin access at enhancers ordinarily restricted to one or the other epithelium. Protein expression of stomach-specific mucins; CLDN18; and a novel gastric marker, ANXA10, showed extensive tissue and subclonal heterogeneity of dual stomach-intestinal cell states.

CONCLUSIONS

These findings reveal mixed and dynamic tissue-restricted chromatin states and phenotypic heterogeneity in Barrett's esophagus. Pervasive intragland variation argues against stem-cell governance of this phenotype.

Current Status of Image-Enhanced Endoscopy for Early Identification of Esophageal Neoplasms

Advanced esophageal cancer is known to have a poor prognosis. The early detection of esophageal neoplasms, including esophageal dysplasia and early esophageal cancer, is highly important for the accurate treatment of the disease. However, esophageal dysplasia and early esophageal cancer are usually subtle and can be easily missed. In addition to the early detection, proper pretreatment evaluation of the depth of invasion of esophageal cancer is very important for curative treatment. The progression of non-invasive diagnosis via image-enhanced endoscopy techniques has been shown to aid the early detection and estimate the depth of invasion of early esophageal cancer and, as a result, may provide additional opportunities for curative treatment. Here, we review the advancement of image-enhanced endoscopy-related technologies and their role in the early identification of esophageal neoplasms.

Current Status of Mucosal Imaging with Narrow-Band Imaging in the Esophagus

Recent advances in endoscopic imaging of the esophagus have revolutionized the diagnostic capability for detecting premalignant changes and early esophageal malignancy. In this article, we review the practical application of narrow-band imaging focusing on diseases of the esophagus, including Barrett's esophagus, adenocarcinoma, and squamous cell carcinoma.

Barrett's Esophagus and Intestinal Metaplasia

Intestinal metaplasia refers to the replacement of the differentiated and mature normal mucosal epithelium outside the intestinal tract by the intestinal epithelium. This paper briefly describes the etiology and clinical significance of intestinal metaplasia in Barrett’s esophagus. This article summarizes the impact of intestinal metaplasia on the diagnosis, monitoring, and treatment of Barrett’s esophagus according to different guidelines. We also briefly explore the basis for the endoscopic diagnosis of intestinal metaplasia in Barrett’s esophagus. The identification techniques of goblet cells in Barrett’s esophagus are also elucidated by some scholars. Additionally, we further elaborate on the current treatment methods related to Barrett’s esophagus.

Taking the Next Steps in Endoscopic Visual Assessment of Barrett's Esophagus: A Pilot Study

Purpose

Patients with Barrett's esophagus (BE) undergo surveillance endoscopies to assess for pre-cancerous changes. We developed a simple endoscopic classification method for predicting non-dysplastic BE (NDBE), low-grade dysplasia (LGD)/indefinite for dysplasia (ID) and high-grade dysplasia (HGD)/early esophageal adenocarcinoma (EAC).

Patients and Methods

Twenty-two patients with BE underwent endoscopy using the PENTAX Medical MagniView gastroscope and OPTIVISTA processor. Sixty-six video-still images were analyzed to characterize the microsurface, microvasculature and the presence of a demarcation line. Class A was characterized by regular microvascular and microsurface patterns and absence of a demarcation line, class B by changes in the microvascular and/or microsurface patterns compared to the background mucosa with presence of a demarcation line, and class C by irregular microvascular and/or irregular microsurface patterns with presence of a demarcation line.

Results

Of the class A images, 97.9% were NDBE. For class B, 69.2% were LGD/ID and 30.8% NDBE. One hundred percent of the class C samples were HGD/EAC. The sensitivity of our classification system was 93.8%, specificity 92%, positive predictive value 78.9%, negative predictive value 97.9% and an accuracy 92.4%.

Conclusion

In this study, we developed a simple classification system for the prediction of NDBE, LGD/ID and HGD/EAC. Its real-time clinical applicability will be validated prospectively.

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.

Photoacoustic endoscopy: A progress review

Endoscopy has been widely used in biomedical imaging and integrated with various optical and acoustic imaging modalities. Photoacoustic imaging (PAI), one of the fastest growing biomedical imaging modalities, is a noninvasive and nonionizing method that owns rich optical contrast, deep acoustic penetration depth, multiscale and multiparametric imaging capability. Hence, it is preferred to miniaturize the volume of PAI and develop an emerged endoscopic imaging modality referred to as photoacoustic endoscopy (PAE). It has been developed for more than one decade since the first report of PAE. Unfortunately, until now, there is no mature photoacoustic endoscopic technique recognized in clinic due to various technical limitations. To address this concern, recent development of new scanning mechanisms, adoption of novel optical/acoustic devices, utilization of superior computation methods and exploration of multimodality strategies have significantly promoted the progress of PAE toward clinic. In this review, we comprehensively reviewed recent progresses in single- and multimodality PAE with new physics, mechanisms and strategies to achieve practical devices for potential applicable scenarios including esophageal, gastrointestinal, urogenital and intravascular imaging. We ended this review with challenges and prospects for future development of PAE.

Is Malignant Potential of Barrett's Esophagus Predictable by Endoscopy Findings?

Given that endoscopic findings can be used to predict the potential of neoplastic progression in Barrett's esophagus (BE) cases, the detection rate of dysplastic Barrett's lesions may become higher even in laborious endoscopic surveillance because a special attention is consequently paid. However, endoscopic findings for effective detection of the risk of neoplastic progression to esophageal adenocarcinoma (EAC) have not been confirmed, though some typical appearances are suggestive. In the present review, endoscopic findings that can be used predict malignant potential to EAC in BE cases are discussed. Conventional results obtained with white light endoscopy, such as length of BE, presence of esophagitis, ulceration, hiatal hernia, and nodularity, are used as indicators of a higher risk of neoplastic progression. However, there are controversies in some of those findings. Absence of palisade vessels may be also a new candidate predictor, as that reveals degree of intense inflammation and of cyclooxygenase-2 protein expression with accelerated cellular proliferation. Furthermore, an open type of mucosal pattern and enriched stromal blood vessels, which can be observed by image-enhanced endoscopy, including narrow band imaging, have been confirmed as factors useful for prediction of neoplastic progression of BE because they indicate more frequent cyclooxygenase-2 protein expression along with accelerated cellular proliferation. Should the malignant potential of BE be shown predictable by these endoscopic findings, that would simplify methods used for an effective surveillance, because patients requiring careful monitoring would be more easily identified. Development in the near future of a comprehensive scoring system for BE based on clinical factors, biomarkers and endoscopic predictors is required.

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

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

Adjunctive Yield of Wide-Area Transepithelial Sampling for Dysplasia Detection After Advanced Imaging and Random Biopsies in Barrett's Esophagus

INTRODUCTION

Little is known about the additive yield of wide-area transepithelial sampling with computer-assisted three-dimensional analysis (WATS-3D) after a thorough examination with advanced imaging. The aim was to evaluate the adjunctive yield of WATS-3D after advanced imaging.

METHODS

This is an observational cohort study from January 2017 to December 2018 for consecutive patients who underwent an examination that consists of high-definition white light endoscopy (HDWLE), narrow-band imaging (NBI), volumetric laser endomicroscopy (VLE), and Seattle protocol (SP) biopsies (collectively termed HDWLE-NBI-VLE-SP examination). Raised lesions were removed by endoscopic resection. Areas suspicious for dysplasia on NBI and VLE were biopsied. This was followed by random biopsies and WATS-3D brush biopsies.

RESULTS

One hundred thirty-eight cases were included in this study. Thirty-five cases (25% of the total) were identified as some degree of dysplasia on the HDWLE-NBI-VLE-SP examination. Adjunctive use of WATS-3D yielded an additional 12 new cases of dysplasia (9 with crypt dysplasia and 3 with low-grade dysplasia [LGD]), for added yield of 34.3% (=12/35, 95% confidence interval 14.6%-62.2%). When restricting the analysis to LGD and higher, 21 dysplastic cases (15% of the total cases) were identified by HDWLE-NBI-VLE-SP, while WATS-3D found 4 additional new cases (3 with LGD and 1 with high-grade dysplasia) for an added yield of 19% (=4/21, 95% confidence interval 0.6%-45.7%).

DISCUSSION

The addition of WATS-3D to an already thorough examination with HDWLE-NBI-VLE-SP may increase the yield of dysplasia detection.

Barrett's Esophagus in Romania: what do we know?

BACKGROUND AND AIMS

The incidence of Barrett's Esophagus (BE) is increasing worldwide, thus diagnosis is becoming a major key of interest in preventing esophageal adenocarcinoma. Because the status of BE in Romania is unclear, we performed a narrative review to comprehensively evaluate all published articles on BE from Romania.

METHODS

We conducted a systematic literature search of PubMed data base and of all Romanian medical journals. The abstracts and the titles of the identified studies were reviewed to exclude the studies that did not answer the search question. In addition we performed a manual search to identify articles on this topic published earlier in local journals or not indexed on internet.

RESULTS

A total of 17 articles were found. 8 studies and 9 reviews were identified, with a total of 8,829 participants enrolled. The results showed that the median age ranges between 54-59 years, with a predominance for male sex, the main risk factors, such as gastroesophageal reflux disease, obesity, smoking, hiatal hernia, are also present in Romania and infection with H. pylori has a protective effect. The diagnosis of Barrett's esophagus in Romania is established in agreement with international guidelines.

CONCLUSIONS

There are not many publications on BE in Romania. However the data in this country are similar to those reported in other countries. The management is carried out according to standard guidelines. Diagnosing BE relies on endoscopic techniques and classification systems. Risk factors such as gastroesophageal reflux, hiatal hernia, obesity and Helicobacter pylori are considered in Romanian articles. More studies are welcome on this matter in our country.

Features of Esophageal Adenocarcinoma in Magnifying Narrow-Band Imaging

BACKGROUND

Several endoscopic classifications for esophageal adenocarcinoma have been proposed; however, gastric adenocarcinoma is much more common than esophageal or esophagogastric junctional (EGJ) adenocarcinoma in East Asian countries. We, therefore, investigated whether an endoscopic diagnostic algorithm for gastric adenocarcinoma could be used for esophageal or EGJ adenocarcinoma.

METHODS

One hundred eighteen consecutive patients who underwent endoscopic resection or surgery for intramucosal esophageal or EGJ adenocarcinoma, at the Osaka International Cancer Institute between January 2006 and December 2017, were included in this retrospective study. Their lesions were classified as Siewert type 1 or 2, and the presence of endoscopic magnifying narrow-band imaging findings for diagnosing gastric adenocarcinoma was evaluated.

RESULTS

We evaluated 125 adenocarcinomas in 118 patients (29 type 1 and 96 type 2). Demarcation lines (DLs) were seen in 7 (24%) type 1 and 53 (55%) type 2 lesions. Irregular mucosal patterns were present in 2 (7%) type 1 and 22 (23%) type 2 lesions. Irregular vascular patterns were present in 26 (90%) type 1 and 50 (52%) type 2 lesions. According to the magnifying endoscopy diagnostic algorithm for gastric adenocarcinoma, only 7 (24%) type 1 and 52 (54%) type 2 lesions were correctly diagnosed as cancers (p = 0.005).

CONCLUSION

The magnifying endoscopy diagnostic algorithm for gastric cancer may not be useful for esophageal or EGJ adenocarcinomas because of the low visibility of DLs, especially in Siewert type 1 adenocarcinoma.

Endoscopic submucosal dissection/endoscopic mucosal resection guidelines for esophageal cancer

The Japan Gastroenterological Endoscopy Society has developed endoscopic submucosal dissection/endoscopic mucosal resection guidelines. These guidelines present recommendations in response to 18 clinical questions concerning the preoperative diagnosis, indications, resection methods, curability assessment, and surveillance of patients undergoing endoscopic resection for esophageal cancers based on a systematic review of the scientific literature.

A background correction method to compensate illumination variation in hyperspectral imaging

Hyperspectral imaging (HSI) can measure both spatial (morphological) and spectral (biochemical) information from biological tissues. While HSI appears promising for biomedical applications, interpretation of hyperspectral images can be challenging when data is acquired in complex biological environments. Variations in surface topology or optical power distribution at the sample, encountered for example during endoscopy, can lead to errors in post-processing of the HSI data, compromising disease diagnostic capabilities. Here, we propose a background correction method to compensate for such variations, which estimates the optical properties of illumination at the target based on the normalised spectral profile of the light source and the measured HSI intensity values at a fixed wavelength where the absorption characteristics of the sample are relatively low (in this case, 800 nm). We demonstrate the feasibility of the proposed method by imaging blood samples, tissue-mimicking phantoms, and ex vivo chicken tissue. Moreover, using synthetic HSI data composed from experimentally measured spectra, we show the proposed method would improve statistical analysis of HSI data. The proposed method could help the implementation of HSI techniques in practical clinical applications, where controlling the illumination pattern and power is difficult.

Development and validation of the international Blue Light Imaging for Barrett's Neoplasia Classification

BACKGROUND AND AIMS

Detecting subtle Barrett's neoplasia during surveillance endoscopy can be challenging. Blue-light imaging (BLI) is a novel advanced endoscopic technology with high-intensity contrast imaging that may improve the identification of Barrett's neoplasia. The aim of this study was to develop and validate the first classification to enable characterization of neoplastic and non-neoplastic Barrett's esophagus using BLI.

METHODS

In phase 1, descriptors pertaining to neoplastic and non-neoplastic Barrett's esophagus were identified to form the classification, named the Blue Light Imaging for Barrett's Neoplasia Classification (BLINC). Phase 2 involved validation of these component criteria by 10 expert endoscopists assessing 50 BLI images. In phase 3, a web-based training module was developed to enable 15 general (nonexpert) endoscopists to use BLINC. They then validated the classification with an image assessment exercise in phase 4, and their pre- and post-training results were compared.

RESULTS

In phase 1 the descriptors were grouped into color, pit, and vessel pattern categories to form the classification. In phase 2 the sensitivity of neoplasia identification was 96.0% with a very good level of agreement among the experts (κ = .83). In phase 3, 15 general endoscopists completed the training module. In phase 4 their pretraining sensitivity (85.3%) improved significantly to 95.7% post-training with a good level of agreement (κ = .67).

CONCLUSIONS

We developed and validated a new classification system (BLINC) for the optical diagnosis of Barrett's neoplasia using BLI. Despite the limitations of this image-based study with a high prevalence of neoplasia, we believe it has the potential to improve the optical diagnosis of Barrett's neoplasia given the high degree of sensitivity (96%) noted. It is also a promising tool for training in Barrett's esophagus optical diagnosis using BLI.

Challenges to diagnostic standardization of Barrett's esophagus in Asia

Barrett's esophagus (BE), a premalignant condition of the lower esophagus, is increasingly prevalent in Asia. However, endoscopic and histopathological criteria vary widely between studies across Asia, making it challenging to assess comparability between geographical regions. Furthermore, guidelines from various societies worldwide provide differing viewpoints and definitions, leading to diagnostic challenges that affect prognostication of the condition. In this review, the authors discuss the controversies surrounding the diagnosis of BE, particularly in Asia. Differences between guidelines worldwide are summarized with further discussion regarding various classifications of BE used, different definitions of gastroesophageal junction used across geographical regions and the clinical implications of intestinal metaplasia in the setting of BE. Although many guidelines recommend the Seattle protocol as the preferred approach regarding dysplasia surveillance in BE, some limitations exist, leading to poor adherence. Newer technologies, such as acetic acid-enhanced magnification endoscopy, narrow band imaging, Raman spectroscopy, molecular approaches and the use of artificial intelligence appear promising in addressing these problems, but further studies are required before implementation into routine clinical practice. The Asian Barrett's Consortium also outlines its ongoing plans to tackle the challenge of standardizing the diagnosis of BE in Asia.

Evaluation and Management of Premalignant Conditions of the Esophagus: A Systematic Survey of International Guidelines

Esophageal cancer represents one of the most lethal forms of malignancy. The growing incidence of esophageal adenocarcinoma represents an emerging public health concern. This review article summarizes current diagnostic, management, and therapeutic practices of premalignant conditions of the esophagus including Barrett's esophagus, tylosis, granular cell tumors, achalasia, and the ingestion of caustic substances. Our report provides clinicians and academics with a global clinical perspective regarding presentation, surveillance guidelines, and therapeutic management of these esophageal conditions.

Wide-field optical property mapping and structured light imaging of the esophagus with spatial frequency domain imaging

As the incidence of esophageal adenocarcinoma continues to rise, there is a need for improved imaging technologies with contrast to abnormal esophageal tissues. To inform the design of optical technologies that meet this need, we characterize the spatial distribution of the scattering and absorption properties from 471 to 851 nm of eight resected human esophagi tissues using Spatial Frequency Domain Imaging. Histopathology was used to categorize tissue types, including normal, inflammation, fibrotic, ulceration, Barrett's Esophagus and squamous cell carcinoma. Average absorption and reduced scattering coefficients of normal tissues were 0.211 ± 0.051 and 1.20 ± 0.18 mm-1 , respectively at 471 nm, and both values decreased monotonically with increasing wavelength. Fibrotic tissue exhibited at least 68% larger scattering signal across all wavelengths, while squamous cell carcinoma exhibited a 36% decrease in scattering at 471 nm. We additionally image the esophagus with high spatial frequencies up to 0.5 mm-1 and show strong reflectance contrast to tissue treated with radiation. Lastly, we observe that esophageal absorption and scattering values change by an average of 9.4% and 2.7% respectively over a 30 minute duration post-resection. These results may guide system design for the diagnosis, prevention and monitoring of esophageal pathologies.

Advanced imaging in surveillance of Barrett’s esophagus: Is the juice worth the squeeze?

Esophageal cancer is on the rise. The known precursor lesion is Barrett’s esophagus (BE). Patients with dysplasia are at higher risk of developing esophageal cancer. Currently the gold standard for surveillance endoscopy involves taking targeted biopsies of abnormal areas as well as random biopsies every 1-2 cm of the length of the Barrett’s. Unfortunately studies have shown that this surveillance can miss dysplasia and cancer. Advanced imaging technologies have been developed that may help detect dysplasia in BE. This opinion review discusses advanced imaging in BE surveillance endoscopy and its utility in clinical practice.

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.

A roadmap for the clinical implementation of optical-imaging biomarkers

Clinical workflows for the non-invasive detection and characterization of disease states could benefit from optical-imaging biomarkers. In this Perspective, we discuss opportunities and challenges towards the clinical implementation of optical-imaging biomarkers for the early detection of cancer by analysing two case studies: the assessment of skin lesions in primary care, and the surveillance of patients with Barrett's oesophagus in specialist care. We stress the importance of technical and biological validations and clinical-utility assessments, and the need to address implementation bottlenecks. In addition, we define a translational roadmap for the widespread clinical implementation of optical-imaging technologies.

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.

Enhancing the Detection of Barrett Esophagus

In Western countries, the incidence of esophageal adenocarcinoma has increased rapidly in parallel with its premalignant condition, Barrett esophagus (BE). Unlike colonoscopy, endoscopic screening for BE is not currently recommended for all patients; however, surveillance endoscopy is advocated for patients with established BE. Novel imaging and sampling techniques have been developed and investigated for the purpose of improving the detection of Barrett esophagus, dysplasia, and neoplasia. This article discusses several screening and surveillance techniques, including Seattle protocol, chromoendoscopy, electronic chromoendoscopy, wide area transepithelial sampling with 3-dimensional analysis, nonendoscopic sampling devices, and transnasal endoscopy.

A Survey of Expert Practice and Attitudes Regarding Advanced Imaging Modalities in Surveillance of Barrett's Esophagus

BACKGROUND

Published guidelines do not address what the minimum incremental diagnostic yield (IDY) for detection of dysplasia/cancer is required over the standard Seattle protocol for an advanced imaging modality (AIM) to be implemented in routine surveillance of Barrett's esophagus (BE) patients. We aimed to report expert practice patterns and attitudes, specifically addressing the minimum IDY in the use of AIMs in BE surveillance.

METHODS

An international group of BE experts completed an anonymous electronic survey of domains relevant to surveillance practice patterns and use of AIMs. The evaluated AIMs were conventional chromoendoscopy (CC), virtual chromoendoscopy (VC), volumetric laser endomicroscopy (VLE), confocal laser endomicroscopy (CLE), and wide-area transepithelial sampling (WATS3D). Responses were recorded using five-point balanced Likert items and analyzed as continuous variables.

RESULTS

The survey response rate was 84% (61/73)-41 US and 20 non-US. Experts were most comfortable with and routinely use VC and CC, and least comfortable with and rarely use VLE, CLE, and WATS3D. Experts rated data from randomized controlled trials (1.4 ± 0.9) and guidelines (2.6 ± 1.2) as the two most influential factors for implementing AIMs in clinical practice. The minimum IDY of AIMs over standard biopsies to be considered of clinical benefit was lowest for VC (15%, IQR 10-29%) and highest for VLE (30%, IQR 20-50%). Compared to US experts, non-US experts reported higher use of CC for BE surveillance (p < 0.001).

CONCLUSION

These results should inform benchmarks that need to be met for guidelines to recommend the routine use of AIMs in the surveillance of BE patients.

Narrow band imaging and serology in the assessment of premalignant gastric pathology

BACKGROUND

Patient outcomes in gastric adenocarcinoma are poor due to late diagnosis. Detecting and treating at the premalignant stage has the potential to improve this. Helicobacter pylori is also a strong risk factor for this disease.

AIMS

Primary aims were to assess the diagnostic accuracy of magnified narrow band imaging (NBI-Z) endoscopy and serology in detecting normal mucosa, H. pylori gastritis and gastric atrophy. Secondary aims were to compare the diagnostic accuracies of two classification systems using both NBI-Z and white light endoscopy with magnification (WLE-Z) and evaluate the inter-observer agreement.

METHODS

Patients were prospectively recruited. Images of gastric mucosa were stored with histology and serum for IgG H. pylori and Pepsinogen (PG) I/II ELISAs. Blinded expert endoscopists agreed on mucosal pattern. Mucosal images and serological markers were compared with histology. Kappa statistics determined inter-observer variability for randomly allocated images among four experts and four non-experts.

RESULTS

116 patients were prospectively recruited. Diagnostic accuracy of NBI-Z for determining normal gastric mucosa was 0.87(95%CI 0.82-0.92), H. pylori gastritis 0.65(95%CI 0.55-0.75) and gastric atrophy 0.88(95%CI 0.81-0.94). NBI-Z was superior to serology at detecting gastric atrophy: NBI-Z gastric atrophy 0.88(95%CI 0.81-0.94) vs PGI/II ratio < 3 0.74(95%CI 0.62-0.85) p<.0001. Overall NBI-Z was superior to WLE-Z in detecting disease using two validated classifications. Inter-observer agreement was 0.63(95%CI 0.51-0.73).

CONCLUSIONS

NBI-Z accurately detects changes in the GI mucosa which currently depend on histology. NBI-Z is useful in the detection of precancerous conditions, potentially improving patient outcomes with early intervention to prevent gastric cancer.

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.

Miniature ureteroscope distal tip designs for potential use in thulium fiber laser lithotripsy

Thulium fiber laser lithotripsy using smaller optical fibers may enable development of miniature ureteroscopes. Two ureteroscope distal tip prototypes were built and characterized. The first design was 4.5-French (Fr) [1.5-mm outer diameter (OD)], five channel tip, housing 200-μm inner diameter (ID) dedicated central channel for insertion of 100-μm core fibers and four surrounding channels, each with 1.5 Fr (510-μm ID) for instrumentation, irrigation, imaging, and illumination, respectively. The second design was 6.0-Fr (2.0-mm OD), three-dimensional printed tip with larger, hemispherical common working channel and separate detection port integrated with ring lighting. Standard instruments, including optical fibers, guidewires, and stone baskets, were inserted through working channels to demonstrate feasibility. Gravitational and manual pump-assisted saline irrigation rates were measured. Luminous intensity distribution curves (LIDCs) were modeled for both ring and conventional lighting designs. Imaging was conducted using 3000, 6000, and 10,000 pixel, miniature, flexible endoscopes with 0.4-, 0.6-, and 0.9-mm OD, to differentiate between urinary stones and ureter wall, for potential clinical application. The multichannel ureteroscope tip with 1.5-Fr working channel yielded a gravitational saline flow rate of 3.9  ±  0.2  mL  /  min compared to 31.3  ±  0.6  mL  /  min for standard (3.6 Fr) ureteroscope channel. Manual, pump-assisted irrigation increased flow rate to 32.5  ±  3.0  mL  /  min. The 6000 pixel, 0.6-mm OD, flexible endoscope provided a balance of clear differentiation between stones and ureter wall and sufficiently small OD. A ring lighting configuration provided more uniform illumination than conventional cross-lighting geometry as demonstrated by LIDCs. With further development, these miniature ureteroscope tip designs may be integrated into a fully functional ureteroscope to permit ureteral access with minimal trauma and improved patient safety and comfort.

Newly developed magnifying endoscopic classification of the Japan Esophageal Society to identify superficial Barrett's esophagus-related neoplasms

AIM AND METHODS

The Japan Esophageal Society created a working committee group consisting of 11 expert endoscopists and 2 pathologists with expertise in Barrett's esophagus (BE) and esophageal adenocarcinoma. The group developed a consensus-based classification for the diagnosis of superficial BE-related neoplasms using magnifying endoscopy.

RESULTS

The classification has three characteristics: simplified, an easily understood classification by incorporating the diagnostic criteria for the early gastric cancer, including the white zone and demarcation line, and the presence of a modified flat pattern corresponding to non-dysplastic histology by adding novel diagnostic criteria. Magnifying endoscopic findings are composed of mucosal and vascular patterns, and are initially classified as "visible" or "invisible." Morphologic features were evaluated for "visible" patterns, and were subsequently rated as "regular" or "irregular," and the histology, non-dysplastic or dysplastic, was predicted.

CONCLUSION

We introduce the process and outline of the magnifying endoscopic classification.

Prospective Comparative Study of Laparoscopic Narrow Band Imaging (NBI) Versus Standard Imaging in Gynecologic Oncology

BACKGROUND

Narrow band imaging (NBI) is an optic filtration enhancement for endoscopy that uses two wavelengths of light (415 and 540 nm) to highlight superficial microvascular patterns. It has been successfully utilized to improve identification of lesions with abnormal vasculature, which is associated with endometriosis and endometrial cancer. Case studies suggest it may also facilitate surgical staging of gynecologic cancer, which is critical in determining appropriate adjuvant therapies. A technology that enhances the ability to identify metastatic disease during minimally invasive surgery (MIS) could make an important difference in patient outcomes.

METHODS

A prospective comparative study was conducted to evaluate patients with clinical indication for diagnostic or operative laparoscopy. All received white light imaging followed by NBI during the same procedure. Suspicious lesions were examined and photographed, using both modalities, before excision. The two techniques were compared. Positive predictive value, negative predictive value, and diagnostic accuracy in identifying histologically confirmed metastatic lesions were assessed, using appropriate statistical methods.

RESULTS

Of 124 patients enrolled in the study, 94 were evaluable; 30 did not undergo MIS and were therefore excluded. A significantly higher number of peritoneal abnormalities were identified with NBI versus white light imaging (P = 0.0239). However, no statistically significant difference (P = 0.18, patient level) was observed in identification of histologically confirmed metastatic disease.

CONCLUSIONS

NBI imaging provides a unique contrast between peritoneal surface and microvascular patterns. However, the results of this study suggest that NBI-enhanced laparoscopy does not provide superior detection of peritoneal surface malignancy compared with standard white light high-definition laparoscopy.

Comparison of narrow-band imaging and confocal laser endomicroscopy for the detection of neoplasia in Barrett's esophagus: A meta-analysis

AIMS

Barrett's esophagus (BE) predisposes to the development of esophageal neoplasia, including high-grade dysplasia (HGD) and esophageal adenocarcinoma (EAC). A systematic literature review and meta-analysis were performed to assess the accuracy of within-patient comparisons of narrow band imaging (NBI) and confocal laser endomicroscopy (CLE) for diagnosis of HGD/EAC in patients with BE.

METHODS

The following databases were examined up to April 2016 without language restriction: PubMed, Embase, Medline, Web of Science and the Cochrane Library. The QUADAS-2 tool for assessing the quality of included studies was used. The meta-analysis included pooled additional detection rate (ADR), diagnostic accuracy, and 95% confidence intervals (CI). The I² and Q-test were used to determine study heterogeneity.

RESULTS

Five studies involving 251 patients, reported within-patient comparisons of NBI and CLE, were eligible for meta-analysis. Compared with NBI, pooled ADR of CLE for per-lesion detection of neoplasia in patients with BE was 19.3% (95% CI: 0.05-0.33, I²=74.6%). The pooled sensitivity of NBI was 62.8% (95% CI: 0.56-0.69, I²=94.6%), which was lower (not significantly) than that of CLE (72.3%, 95% CI: 0.66-0.78, I²=89.3%). The pooled specificity of NBI and CLE were similar [85.3% (95% CI: 0.84-0.87, I²=92.1%) vs 83.8% (95% CI: 0.82-0.85, I²=96.8%)].

CONCLUSIONS

When compared with NBI, CLE significantly increased the per-lesion detection rate of esophageal neoplasia, HGD, and EAC in BE patients. Whether CLE is superior to NBI in neoplasia detection at per-patient level needs to be further investigated.