Magnifying endoscopy simple diagnostic algorithm for early gastric cancer (MESDA-G)

Fundamentals, Diagnostic Capabilities and Perspective of Narrow Band Imaging for Early Gastric Cancer

The development of image-enhanced endoscopy has dramatically improved the qualitative and quantitative diagnosis of gastrointestinal tumors. In particular, narrow band imaging (NBI) has been widely accepted by endoscopists around the world in their daily practice. In 2009, Yao et al. proposed vessel plus surface (VS) classification, a diagnostic algorithm for early gastric cancer using magnifying endoscopy with NBI (ME-NBI), and in 2016, Muto et al. proposed a magnifying endoscopy simple diagnostic algorithm for early gastric cancer (MESDA-G) based on VS classification. In addition, the usefulness of ME-NBI in the differential diagnosis of gastric cancer from gastritis, diagnosis of lesion extent, inference of histopathological type, and diagnosis of depth has also been investigated. In this paper, we narrative review the basic principles, current status, and future prospects of NBI.

Systematic Review on Optical Diagnosis of Early Gastrointestinal Neoplasia

BACKGROUND

Meticulous endoscopic characterization of gastrointestinal neoplasias (GN) is crucial to the clinical outcome. Hereby the indication and type of resection (endoscopically, en-bloc or piece-meal, or surgical resection) are determined. By means of established image-enhanced (IEE) and magnification endoscopy (ME) GN can be characterized in terms of malignancy and invasion depth. In this context, the statistical evidence and accuracy of these diagnostic procedures should be elucidated. Here, we present a systematic review of the literature.

RESULTS

21 Studies could be found which met the inclusion criteria. In clinical prospective trials and meta-analyses, the diagnostic accuracy of >90% for characterization of malignant neoplasms could be documented, if ME with IEE was used in squamous cell esophageal cancer, stomach, or colonic GN.

CONCLUSIONS

Currently, by means of optical diagnosis, today's gastrointestinal endoscopy is capable of determining the histological subtype, exact lateral spread, and depth of invasion of a lesion. The prerequisites for this are an exact knowledge of the anatomical structures, the endoscopic classifications based on them, and a systematic learning process, which can be supported by training courses. More prospective clinical studies are required, especially in the field of Barrett's esophagus and duodenal neoplasia.

Identifying early gastric cancer under magnifying narrow-band images with deep learning: a multicenter study

BACKGROUND AND AIMS

Narrow-band imaging with magnifying endoscopy (ME-NBI) has shown advantages in the diagnosis of early gastric cancer (EGC). However, proficiency in diagnostic algorithms requires substantial expertise and experience. In this study, we aimed to develop a computer-aided diagnostic model for EGM (EGCM) to analyze and assist in the diagnosis of EGC under ME-NBI.

METHODS

A total of 1777 ME-NBI images from 295 cases were collected from 3 centers. These cases were randomly divided into a training cohort (n = 170), an internal test cohort (ITC, n = 73), and an external test cohort (ETC, n = 52). EGCM based on VGG-19 architecture (Visual Geometry Group [VGG], Oxford University, Oxford, UK) with a single fully connected 2-classification layer was developed through fine-tuning and validated on all cohorts. Furthermore, we compared the model with 8 endoscopists with varying experience. Primary comparison measures included accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

EGCM acquired AUCs of .808 in the ITC and .813 in the ETC. Moreover, EGCM achieved similar predictive performance as the senior endoscopists (accuracy: .770 vs .755, P = .355; sensitivity: .792 vs .767, P = .183; specificity: .745 vs .742, P = .931) but better than the junior endoscopists (accuracy: .770 vs .728, P < .05). After referring to the results of EGCM, the average diagnostic ability of the endoscopists was significantly improved in terms of accuracy, sensitivity, PPV, and NPV (P < .05).

CONCLUSIONS

EGCM exhibited comparable performance with senior endoscopists in the diagnosis of EGC and showed the potential value in aiding and improving the diagnosis of EGC by endoscopists.

Image-Enhanced Endoscopy and Its Corresponding Histopathology in the Stomach

In recent years, the technological innovation and progress of endoscopic equipment have been remarkable, and various endoscopic observation techniques have been developed. Among them, representative techniques are magnified observation and narrow-band imaging. Magnifying endoscopy with narrow-band imaging (M-NBI) can visualize superficial microanatomies in the stomach. The normal morphology of the microanatomy visualized using M-NBI differs according to the part of the stomach. The vessel plus surface (VS) classification system has been developed as a diagnostic criterion for early gastric cancer using M-NBI, and its usefulness has been proven. Based on the VS classification system, a magnifying endoscopy simple diagnostic algorithm for early gastric cancer (MESDA-G), a simplified algorithm used for early gastric cancer diagnosis, was created. We aimed to describe the anatomic structure of the stomach that can be viewed using M-NBI and outline the principles and clinical application of the VS classification system and MESDA-G. (Gut Liver 2021;15:-337)

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.

A review on recent advancements in diagnosis and classification of cancers using artificial intelligence

Artificial intelligence has illustrated drastic changes in radiology and medical imaging techniques which in turn led to tremendous changes in screening patterns. In particular, advancements in these techniques led to the development of computer aided detection (CAD) strategy. These approaches provided highly accurate diagnostic reports which served as a "second-opinion" to the radiologists. However, with significant advancements in artificial intelligence strategy, the diagnostic and classifying capabilities of CAD system are meeting the levels of radiologists and clinicians. Thus, it shifts the CAD system from second opinion approach to a high utility tool. This article reviews the strategies and algorithms developed using artificial intelligence for the foremost cancer diagnosis and classification which overcomes the challenges in the traditional method. In addition, the possible direction of AI in medical aspects is also discussed in this study.

Establishing an endoscopic diagnostic process system (M-system) for gastric MALT lymphoma of superficial-spreading type

OBJECTIVE

Gastric mucosa-associated lymphoid tissue lymphoma is a rare disease, which is associated with a low endoscopic diagnostic accuracy even on tissue biopsy. We aimed to establish a diagnostic process system (M-system) using detailed magnifying endoscopy images to improve the diagnostic efficiency of this disease.

METHODS

First, 34 cases from 16 patients with the diagnosis of mucosa-associated lymphoid tissue lymphoma were collected as the study group. The control group included randomly selected patients who were diagnosed with early differentiated carcinoma, undifferentiated carcinoma or inflammation. Then, the endoscopic images of these patients were analyzed by senior physicians. Finally, the M-system was established based on the data extracted from the images reviewed, and its diagnostic efficiency for mucosa-associated lymphoid tissue lymphoma was validated by the junior physicians.

RESULTS

A series of elements with high sensitivity and specificity for the diagnosis of mucosa-associated lymphoid tissue lymphoma on endoscopic images were extracted for the establishment of the M-system. Using the M-system, the diagnostic accuracy, sensitivity, specificity and correct indices of mucosa-associated lymphoid tissue lymphoma rose from 65.4 to 79.4%, 41.2 to 76.5%, 73.5 to 80.4% and 0.147 to 0.569%, respectively, all of which were statistically significant.

CONCLUSIONS

The M-system can improve the diagnostic accuracy of mucosa-associated lymphoid tissue lymphoma of the superficial-spreading type on detailed magnifying endoscopy. This would help in the early diagnosis of the disease and treatment, which would translate into improved clinical outcomes.

Endoscopic and histological features of Helicobacter pylori-negative differentiated gastric adenocarcinoma arising in the antrum

BACKGROUND AND AIM

With the increasing prevalence of persons without Helicobacter pylori (HP) infection, cases of HP-negative gastric cancer are increasing. Although rare, cases of differentiated adenocarcinoma of the antrum have been reported in HP-negative patients. We collected cases with such lesions and investigated their endoscopic and histological features.

METHODS

Of 1965 consecutive patients with early gastric cancer who underwent endoscopic resection between January 2009 and December 2017, we extracted 9 cases of HP-negative differentiated adenocarcinoma located in the antrum (HPN-DAA). The clinical data, endoscopic findings, and histopathological findings were reviewed.

RESULTS

Of the nine patients with HPN-DAA, seven were male, and the median age was 53.8 years. The tumor arose from the pyloric gland mucosa in all cases. According to the endoscopic findings, the lesions were flat-elevated or depressed, mimicking varioliform gastritis. Magnifying endoscopy with narrow-band imaging showed the absence of a clear demarcation line or an irregular microvessel/surface pattern. As for the histopathological findings, eight of the nine lesions were diagnosed as high-grade dysplasia/intraepithelial neoplasia, while the remaining case was diagnosed as tubular adenocarcinoma with submucosal infiltration. The findings of immunohistochemistry confirmed that three cases were of the intestinal mucin phenotype and six were of the mixed gastric and intestinal mucin phenotype.

CONCLUSION

HPN-DAA is a very rarely occurring cancer that had never been recognized earlier. They belong to the new category of HP-negative cancers, and there seems to be a certain number of such cases.

Efficacy of Texture and Color Enhancement Imaging in visualizing gastric mucosal atrophy and gastric neoplasms

In 2020, Olympus Medical Systems Corporation introduced the Texture and Color Enhancement Imaging (TXI) as a new image-enhanced endoscopy. This study aimed to evaluate the visibility of neoplasms and mucosal atrophy in the upper gastrointestinal tract through TXI. We evaluated 72 and 60 images of 12 gastric neoplasms and 20 gastric atrophic/nonatrophic mucosa, respectively. The visibility of gastric mucosal atrophy and gastric neoplasm was assessed by six endoscopists using a previously reported visibility scale (1 = poor to 4 = excellent). Color differences between gastric mucosal atrophy and nonatrophic mucosa and between gastric neoplasm and adjacent areas were assessed using the International Commission on Illumination L*a*b* color space system. The visibility of mucosal atrophy and gastric neoplasm was significantly improved in TXI mode 1 compared with that in white-light imaging (WLI) (visibility score: 3.8 ± 0.5 vs. 2.8 ± 0.9, p < 0.01 for mucosal atrophy; visibility score: 2.8 ± 1.0 vs. 2.0 ± 0.9, p < 0.01 for gastric neoplasm). Regarding gastric atrophic and nonatrophic mucosae, TXI mode 1 had a significantly greater color difference than WLI (color differences: 14.2 ± 8.0 vs. 8.7 ± 4.2, respectively, p < 0.01). TXI may be a useful observation modality in the endoscopic screening of the upper gastrointestinal tract.

Characteristics of non-neoplastic epithelium that appears within gastric cancer with and without Helicobacter pylori eradication: A retrospective study

A non-neoplastic epithelium (NE) often appears in gastric cancer (GC). We explored the histological features of NE in comparison between HP-eradicated and HP-infected GCs. We enrolled 40 HP-eradicated and 40 HP-infected GCs matched by size, macroscopic and histological type. NE was classified into full gland type and surface type; the former was a non-neoplastic gland isolated within cancer, and the latter was NE on the surface of the cancer. Surface type was additionally divided into NE at the cancer margin (marginal surface type) and NE inside cancer (internal surface type). The primary endpoints were the frequency and the length ratio (the ratio to cancer length) of NE. The secondary endpoints were the relationships between NE and clinicopathological factors, including endoscopic findings of a gastritis-like appearance (GLA), reddish depressed lesion (RDL), and white nodular mucosa (WNM). The frequency and length ratio of the internal surface type in HP-eradicated GCs were significantly higher (82.5% vs 50%, P = 0.005) and larger (11.6 ± 10.6 vs 4.2 ± 9.9, P < 0.001) than those in HP-infected GCs, and the increase was more significant according to the passage of time since HP eradication. The frequency and length ratio of marginal surface type and full gland type were not significantly different between the two groups, but the coexistence of internal surface and full gland types was statistically significant (p < 0.001). The frequencies of GLA, RDLs, and WNM in HP-eradicated GCs were significantly higher than those in HP-infected GCs. GLA-positive GCs were covered more widely by internal surface type than GLA-negative GCs (13.3% vs. 6.6%, P = 0.003). Various types of NE were noted in gastric cancer, and the internal surface type of NE was shown to be significantly linked to HP-eradicated cancer and GLA.

Diagnostic performance in gastric cancer is higher using endocytoscopy with narrow-band imaging than using magnifying endoscopy with narrow-band imaging

BACKGROUND

For diagnosing gastric cancer, differences in the diagnostic performance between endocytoscopy with narrow-band imaging and magnifying endoscopy with narrow-band imaging have not been reported. We aimed to clarify these differences by analyzing diagnoses made by endoscopists in Japan.

METHODS

This single-center retrospective cohort study used 106 cancerous and 106 non-cancerous images obtained via both modalities (total, 424 images) for diagnosis. Sixty-one endoscopists with varying experience levels from 45 institutions were included. Diagnostic accuracy, sensitivity, specificity, and positive and negative predictive values were evaluated to determine the diagnostic performance of each modality and compared using the Mann-Whitney U test.

RESULTS

Among all endoscopists, diagnostic accuracy, sensitivity, positive predictive value, and negative predictive value were higher with endocytoscopy with narrow-band imaging than with magnifying endoscopy with narrow-band imaging (percentage [95% confidence interval]: 78.8% [76.4-83.0%] versus 72.2% [69.3-73.6%], p < 0.0001; 82.1% [78.3-85.9%] versus 64.2% [60.4-69.8%], p < 0.0001; 88.7% [82.6-90.7%] versus 78.5% [75.4-85.1%], p = 0.0023; 79.0% [75.3-80.5%] versus 68.5% [66.4-71.6%], p < 0.0001, respectively). In the magnifying endoscopy with narrow-band imaging-trained group, these values were also higher with endocytoscopy with narrow-band imaging than with magnifying endoscopy with narrow-band imaging (p < 0.0001, p = 0.0001, p = 0.0143, and p < 0.0001, respectively). Diagnostic accuracy, sensitivity, and negative predictive value were higher with endocytoscopy with narrow-band imaging than with magnifying endoscopy with narrow-band imaging in the magnifying endoscopy with narrow-band imaging-untrained group (p = 0.0041, p = 0.0049, and p = 0.0098, respectively).

CONCLUSIONS

Diagnostic performance was higher using endocytoscopy with narrow-band imaging than using magnifying endoscopy with narrow-band imaging. Our results may help change the technique used to diagnose gastric cancer.

Usefulness of vessel plus surface classification system for the diagnosis of early gastric cancer after Helicobacter pylori eradication

Background

It has been reported that it is sometimes difficult to make a diagnosis of gastric cancer detected after Helicobacter pylori (H. pylori) eradication. Therefore, we conducted a study to determine the usefulness of magnifying endoscopy using vessel plus surface classification system for making a diagnosis of early gastric cancer after H. pylori eradication.

Method

Usefulness of the markers of the vessel plus surface classification system for diagnosing gastric cancer using magnifying endoscopy with narrow-band imaging was investigated for gastric cancer detected after H. pylori eradication (H. pylori-eradicated group) vs. H. pylori-positive gastric cancer (H. pylori-positive group).

Results

85 lesions were included in this study. The H. pylori-eradicated group comprised 27 lesions, whereas the H. pylori-positive group comprised 58 lesions. As for magnified endoscopic findings based on the vessel plus surface classification system, the respective positivity rates in the H. pylori-eradicated group vs. those in the H. pylori-positive group were as follows: demarcation line, 100% (27/27) vs. 100% (58/58); irregular microvascular pattern, 100% (27/27) vs. 100% (58/58); and irregular microsurface pattern, 78% (21/27) vs. 95% (55/58). There was no significant difference in the positivity rates of the demarcation line and irregular microvascular pattern between the groups. The positivity rate of the irregular microsurface pattern was significantly lower in the H. pylori-eradicated group than in the H. pylori-positive group (P=0.03).

Conclusion

We presume that the microvascular pattern is more useful than the microsurface pattern as a diagnostic marker in cases of gastric cancer detected after H. pylori eradication.

Role of magnifying endoscopy with narrow-band imaging in the diagnosis of noninvasive gastric neoplasia

Background and Aim

There are no globally approved, distinguishing criteria enabling the classification of gastric adenomas and intramucosal carcinomas for differential diagnosis of noninvasive neoplasia (NIN).

Methods

Next‐generation sequencing of 50 cancer‐related genes was undertaken on 68 pathologically diagnosed microdissected gastric neoplasms (25 adenomas, 27 intramucosal carcinomas, and 16 submucosal carcinomas) obtained during endoscopic submucosal dissection. Findings from magnifying endoscopy with narrow‐band imaging (M‐NBI) of 52 NINs (the 25 adenomas and 27 intramucosal carcinomas) were compared with these data.

Results

Among all 68 neoplasms, the most frequently mutated genes were APC (76% in adenoma, 11.1% in intramucosal carcinoma, and 0% in submucosal carcinoma; P < 0.001) and TP53 in intramucosal and submucosal carcinomas (8% in adenoma, 48.1% in intramucosal carcinoma, and 75% in submucosal carcinoma; P < 0.001). Dividing the NIN neoplasms into five groups according to their mutational status (A1: APC mutation, A2: APC + α mutation, B: APC + TP53 mutation, C: TP53 mutation, D: no mutation in either APC or TP53) resulted in almost identical diagnoses by pathology and M‐NBI for groups A1 (12/13, 92%), C (12/13, 92%), and D (16/17, 94%) but not for groups A2 (3/7, 43%) or B (0/2, 0%). This finding implies that NINs with the APC + α mutation have carcinoma‐like endoscopic features despite most being judged as adenomas by pathology.

Conclusion

A diagnosis of NINs by pathology or M‐NBI in the subset of gastric tumors classified by cancer‐related mutations is not completely identical, suggesting the possible additional role of M‐NBI in diagnosing NINs. Further studies are needed to confirm this.

Quality Assessment of Endoscopic Forceps Biopsy Samples under Magnifying Narrow Band Imaging for Histological Diagnosis of Cervical Intraepithelial Neoplasia: A Feasibility Study

The current standard for diagnosing cervical intraepithelial neoplasia (CIN) is colposcopy followed by punch biopsy. We have developed flexible magnifying endoscopy with narrow band imaging (ME-NBI) for the diagnosis of CIN. Here, we investigated the feasibility of targeted endoscopic forceps biopsy (E-Bx) under guidance of ME-NBI for the diagnosis of CIN. We prospectively enrolled 32 consecutive patients with confirmed or suspected high-grade CIN undergoing cervical conization. Next to colposcopy, the same patients underwent ME-NBI just before conization. ME-NBI was performed, and 30 E-Bx samples were taken from lesions suspicious for high-grade CIN and 15 from non-suspicious mucosa. We recalled 82 punch biopsy (P-Bx) specimens taken from lesions suspicious for high-grade CIN under colposcopic examination before enrollment. The proportion of sufficient biopsy samples, which had an entire mucosal layer with subepithelial tissue, for the diagnosis of CIN was evaluated by both methods. Performance of targeted E-Bx for the final diagnosis of at least high-grade CIN was calculated. Seventeen P-Bx specimens were unavailable. The proportion of sufficient samples with E-Bx was 84%, which was similar to that with P-Bx (87%) (p = 0.672). The sensitivity, specificity, and accuracy of ME-NBI using E-Bx was 92%, 81%, and 88%, respectively. In conclusion, ME-NBI-guided E-Bx samples were feasible for histological diagnoses of CIN, and further investigation of its diagnostic accuracy is warranted.

Mixed histology poses a greater risk for noncurative endoscopic resection in early gastric cancers regardless of the predominant histologic types

OBJECTIVES

Clinicopathologic characteristics and treatment outcomes of mixed-histological-type (MT) early gastric cancers (EGCs) treated with endoscopic submucosal dissection (ESD) have not been sufficiently elucidated. We aimed to clarify them in comparison with pure-histological-type EGCs.

METHODS

We used 3022 consecutive EGCs in 2281 patients treated with ESD from our prospectively maintained database. Cases were stratified into four groups according to the final diagnosis of the resected specimen are as follows: 2780 pure differentiated-type (DT), 127 DT-predominant MT (D-MT), 87 pure undifferentiated-type (UDT), and 28 UDT-predominant MT (U-MT). Clinicopathologic characteristics and treatment outcome were compared between pure DT and D-MT, and between pure UDT and U-MT separately. Risk factors for deep submucosal invasion, lymphovascular invasion, and a final diagnosis of MT were identified using multivariate analysis.

RESULTS

Both D-MT (41.7 vs. 92.0%; P < 0.0001) and U-MT (35.7 vs. 75.9%; P = 0.0002) showed a significantly lower curative resection rate than their pure histologic counterparts. Multivariate analysis revealed that MT was an independent risk factor for deep submucosal (OR 6.55; 95% CI, 4.18-10.14) and lymphovascular (OR 4.74; 95% CI, 2.72-8.29) invasion. Preoperative biopsy results that did not show well-differentiated tubular adenocarcinoma (OR 28.2; 95% CI, 18.9-42.9) were an independent risk factor for a final diagnosis of MT.

CONCLUSIONS

MT poses a greater risk for noncurative resection regardless of the predominant histologic types, reflecting more aggressive malignant potential. Although a biopsy examination rarely shows MT, clinicians should consider the possibility of MT when a biopsy examination does not show well-differentiated tubular adenocarcinoma.

Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow-band imaging

BACKGROUND AND AIM

Magnifying endoscopy with narrow-band imaging (ME-NBI) has made a huge contribution to clinical practice. However, acquiring skill at ME-NBI diagnosis of early gastric cancer (EGC) requires considerable expertise and experience. Recently, artificial intelligence (AI), using deep learning and a convolutional neural network (CNN), has made remarkable progress in various medical fields. Here, we constructed an AI-assisted CNN computer-aided diagnosis (CAD) system, based on ME-NBI images, to diagnose EGC and evaluated the diagnostic accuracy of the AI-assisted CNN-CAD system.

METHODS

The AI-assisted CNN-CAD system (ResNet50) was trained and validated on a dataset of 5574 ME-NBI images (3797 EGCs, 1777 non-cancerous mucosa and lesions). To evaluate the diagnostic accuracy, a separate test dataset of 2300 ME-NBI images (1430 EGCs, 870 non-cancerous mucosa and lesions) was assessed using the AI-assisted CNN-CAD system.

RESULTS

The AI-assisted CNN-CAD system required 60 s to analyze 2300 test images. The overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 98.7%, 98%, 100%, 100%, and 96.8%, respectively. All misdiagnosed images of EGCs were of low-quality or of superficially depressed and intestinal-type intramucosal cancers that were difficult to distinguish from gastritis, even by experienced endoscopists.

CONCLUSIONS

The AI-assisted CNN-CAD system for ME-NBI diagnosis of EGC could process many stored ME-NBI images in a short period of time and had a high diagnostic ability. This system may have great potential for future application to real clinical settings, which could facilitate ME-NBI diagnosis of EGC in practice.

A rare case of Helicobacter pylori-uninfected intramucosal poorly differentiated adenocarcinoma that occurred in the gastric fornix

We report a rare case of undifferentiated-type intramucosal gastric cancer that occurred in the fornix of the stomach without Helicobacter pylori infection, which consisted mainly of poorly differentiated adenocarcinoma. A 49-year-old man visited our hospital for a follow-up endoscopic examination of a small depressed lesion of the gastric fornix detected by surveillance esophagogastroduodenoscopy. On magnifying endoscopy with blue laser imaging, the depressed lesion (approximately 10 mm in diameter) was regarded as undifferentiated-type early gastric cancer that proved to be a poorly differentiated adenocarcinoma by histological examination of biopsied specimens. The cancerous lesion was successfully treated with endoscopic submucosal dissection and microscopically showed an intramucosal cancer that invaded the whole mucosal layer with predominant growth of a poorly differentiated adenocarcinoma component. The patient status was verified as Helicobacter pylori-naïve according to the strict diagnostic criteria, thereby confirming this case as an undifferentiated-type Helicobacter pylori-uninfected gastric cancer. Helicobacter pylori-uninfected intramucosal poorly differentiated adenocarcinoma occurring in the gastric fornix has not been previously reported.

A study of evaluating specific tissue oxygen saturation values of gastrointestinal tumors by removing adherent substances in oxygen saturation imaging

OBJECTIVES

Oxygen saturation (OS) imaging is a new method of endoscopic imaging that has clinical applications in oncology which can directly measure tissue oxygen saturation (Sto2) of the surface of gastrointestinal tract without any additional drugs or devices. This imaging technology is expected to contribute to research into cancer biology which leads to clinical benefit such as prediction to efficacy of chemotherapy or radiotherapy. However, adherent substances on tumors such as blood and white coating, pose a challenge for accurate measurements of the StO2 values in tumors. The aim of this study was to develop algorithms for discriminating between the tumors and their adherent substances, and to investigate whether it is possible to evaluate the tumor specific StO2 values excluding adherent substances during OS imaging.

METHODS

We plotted areas of tumors and their adherent substances using white-light images of 50 upper digestive tumors: blood (68 plots); reddish tumor (83 plots); white coating (89 plots); and whitish tumor (79 plots). Scatter diagrams and discriminating algorithms using spectrum signal intensity values were constructed and verified using validation datasets. StO2 values were compared between the tumors and tumor adherent substances using OS images of gastrointestinal tumors.

RESULTS

The discriminating algorithms and their accuracy rates (AR) were as follows: blood vs. reddish tumor: Y> - 4.90X+7.13 (AR: 95.9%) and white coating vs. whitish tumor: Y< -0.52X+0.17 (AR: 96.0%). The StO2 values (median, [range]) were as follows: blood, 79.3% [37.8%-100.0%]; reddish tumor, 74.5% [62.0%-86.9%]; white coating, 73.8% [42.1%-100.0%]; and whitish tumor, 65.7% [53.0%-76.3%].

CONCLUSIONS

OS imaging is strongly influenced by adherent substances for evaluating the specific StO2 value of tumors; therefore, it is important to eliminate the information of adherent substances for clinical application of OS imaging.

A case of signet ring cell carcinoma and mucosa-associated lymphoid tissue lymphoma of the stomach diagnosed simultaneously via magnifying endoscopy with narrow-band imaging

We present the case of a 57-year-old woman who experienced 3 weeks of intermittent tarry stools and epigastric pain. She had a 25-year history of smoking and a 12-year history of heavy alcohol consumption but had discontinued both 12 years prior. Laboratory investigations revealed elevated anti-H. Pylori IgG antibody levels. Conventional upper gastrointestinal endoscopy revealed two lesions. Magnifying endoscopy with narrow-band imaging showed the characteristic appearance of a diffuse-type gastric cancer 0-IIc lesion with a demarcation line and abnormal vessels ("wavy micro-vessels" and a "cork-screw pattern"). There was also "ballooning" of the crypts and a "tree-like vessel appearance" in an "unstructured area" characteristic of gastric mucosa-associated lymphoid tissue lymphoma with ulceration. Accurate target biopsies were obtained. We performed a laparoscopic total gastrectomy with D1 lymphadenectomy. Pathological examination revealed poorly differentiated stage I adenocarcinoma of the stomach with features of signet ring cell carcinoma as well as stage I mucosa-associated lymphoid tissue lymphoma. In conclusion, we encountered a case of co-existing diffuse-type gastric cancer and gastric mucosa-associated lymphoid tissue lymphoma. Magnifying endoscopy with narrow-band imaging was effective for diagnosing these two co-existing tumors and resulted in the collection of adequate biopsy specimens allowing for an accurate pathological diagnosis and optimal treatment.

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.

Does previous biopsy lead to cancer overdiagnosis of superficial non-ampullary duodenal epithelial tumors?

Background and study aims  We aimed to evaluate the diagnostic performance of magnifying endoscopy with narrow-band imaging (M-NBI) in superficial non-ampullary duodenal epithelial tumors (SNADETs) regarding the absence or presence of biopsy before M-NBI diagnosis. Patients and methods  Clinicopathological data were retrospectively reviewed for 99 SNADETs from 99 patients who underwent endoscopic resection. The 99 tumors were divided into the non-biopsy group (32 lesions not undergoing biopsy before M-NBI examination) and the biopsy group (67 lesions undergoing biopsy before M-NBI examination). We investigated the correlation between the M-NBI diagnosis and the histopathological diagnosis of the SNADETs in both groups. Results  According to the modified revised Vienna classification, 31 tumors were classified as category 3 (C3) (low-grade adenoma) and 68 as category 4/5 (C4/5) (high-grade adenoma/cancer). The accuracy, sensitivity, and specificity of preoperative M-NBI diagnoses in the non-biopsy group vs the biopsy group were 88 % (95 % confidence interval: 71.0 - 96.5) vs 66 % (51.5 - 75.5), P  = 0.02; 95 % (77.2 - 99.9) vs 89 % (76.4 - 96.4), P  = 0.39; and 70 % (34.8 - 93.3) vs 14 % (3.0 - 36.3), P  < 0.01, respectively. Notably, in the biopsy group, the specificity of M-NBI in SNADETs was low at only 14 % because we over-diagnosed most C3 lesions as C4/5. M-NBI findings might have been compromised by the previous biopsy procedure itself. Conclusions  In the non-biopsy group, the accuracy of M-NBI in SNADETs was excellent in distinguishing C4/5 lesions from C3. The M-NBI findings in SNADETs should be evaluated while carefully considering the influence of a previous biopsy.

Clinicopathological and Endoscopic Features of Raspberry-Shaped Gastric Cancer in Helicobacter pylori-Uninfected Patients

BACKGROUND

Gastric adenocarcinoma of foveolar type (GA-FV) is a raspberry-shaped gastric cancer (RSGC) and garners much attention as H. pylori (Hp)-uninfected gastric cancer. However, the classification and clinicopathological and endoscopic features of RSGCs in Hp-uninfected patients are poorly defined. We designed a new histopathological classification of RSGC and compared them via endoscopic and clinicopathological characteristics.

SUMMARY

From 996 patients with early gastric cancers resected by endoscopy in our hospital, we studied 24 RSGC lesions from 21 (2.4%) Hp-uninfected patients. RSGCs were classified into 3 histological types as follows: GA-FV (n = 19), gastric adenocarcinoma of fundic gland type (GA-FG, n = 2), and gastric adenocarcinoma of fundic gland mucosa type (GA-FGM, n = 3). Most of the lesions were found at the greater curvature of the upper or middle third of the stomach. GA-FV lesions were homogeneously reddish and frequently accompanied with a whitish area around the tumor and an irregular microvascular (MV) pattern; these features were confirmed histopathologically by the presence of homogeneous neoplastic foveolar epithelium with foveolar hyperplasia around the tumors. GA-FG lesions might be heterogeneously reddish with a submucosal tumor shape and regular MV pattern; these were confirmed by the presence of covered or mixed nonneoplastic epithelium on deeper regions of tumors. GA-FGM lesions might be homogeneously reddish and occasionally had a submucosal tumor shape and irregular MV pattern; these were confirmed by the presence of homogeneous neoplastic foveolar epithelium on deeper regions of the tumors. Key Messages: RSGCs in Hp-uninfected patients are classified into 3 histopathological types. For accurate diagnosis of RSGCs, it may be necessary to fully understand endoscopic features of these lesions based on these histological characteristics and to take a precise biopsy.

Tapering body stiffness shortens upper gastrointestinal examination via transoral insertion with ultrathin endoscope

Background and study aims  Ultrathin endoscopes are commonly used for surveillance esophagogastroduodenoscopy (EGD) to reduce discomfort associated with scope insertion. However, the flexibility of an ultrathin endoscope is a trade-off between reducing discomfort and lengthening examination time. Patients and methods  The EG17-J10 (EG17) is a novel ultrathin endoscope characterized by its tapering body stiffness; however, the flexibility of its tip is comparable to that of the traditional ultrathin endoscope EG16-K10 (EG16). We compared EGD examination time between EG17 and EG16. A total of 319 examinees who underwent EGD from November 2019 to January 2020 at the Chiba-Nishi General Hospital were enrolled. Six examinees were excluded due to past history of surgical resection of the upper gastrointestinal tract or too much food residues; 313 examinees (EG17, 209; EG16,104) were retrospectively analyzed. The examination time was divided into three periods: esophageal insertion time (ET), gastroduodenal insertion time (GDT), and surveillance time of the stomach (ST). The total amount of ET, GDT, and ST was defined as total examination time (TT). Results  TT of EGD using EG17 was significantly shorter compared to EGD using EG16 (222.7 ± 68.9 vs. 245.7 ± 78.5 seconds) ( P  = 0.004). Among the three periods of examination time, ET (66.7 ± 24.1 vs. 76.0 ± 24.1 seconds) ( P  = 0.001) and GDT (47.9 ± 17.4 vs. 55.2 ± 35.2 seconds) ( P  = 0.007) of EGD using EG17 were significantly shorter compared to EGD using EG16, except for ST (108.1 ± 51.5.1 vs. 114.5 ± 50.1 seconds) ( P  = 0.148). Conclusion  An ultrathin endoscope with tapering body stiffness can shorten EGD examination time, mainly due to the shortening of insertion time.

Near-focus magnification and second-generation narrow-band imaging for early gastric cancer in a randomized trial

BACKGROUND

Magnifying endoscopy with narrow-band imaging (NBI) is effective for the diagnosis of early gastric cancer (EGC). However, magnifying endoscopy is not yet popular globally because of the required level of skill and lack of availability. To overcome these problems, dual-focus endoscopy (standard- and near-focus (NF) modes) has been developed. In this study, we evaluated the diagnostic performance of NF with second-generation (2G)-NBI (NF-NBI) for the diagnosis of EGC.

METHODS

This was a secondary analysis of a multicenter randomized controlled trial of 4523 high-risk patients who underwent gastroscopies at 13 institutions in Japan. Patients were randomly assigned to white-light imaging (WLI) followed by 2G-NBI or to 2G-NBI followed by WLI. Lesions suspicious for EGC, newly detected by non-magnifying WLI or 2G-NBI, were subsequently observed with NF-NBI. All detected lesions were biopsied or resected. The diagnostic performance of NF-NBI was compared with the final histology.

RESULTS

A total of 870 detected lesions (145 EGC, 725 non-EGC) were analyzed. Overall diagnostic performance for EGC using NF-NBI was accuracy 87.7%, sensitivity 60.7%, specificity 93.1%, positive predictive value 63.8%, and negative predictive value 92.2%. There were no significant differences in diagnostic performance between lesions detected by WLI or 2G-NBI. For lesions diagnosed with high (333 lesions) and low (537 lesions) confidences, accuracy was 92.2% and 84.9%, sensitivity was 64.7% and 58.5%, and specificity was 90.5% and 88.8%, respectively.

CONCLUSION

The diagnostic performance of NF-NBI is good and acceptable for diagnosis of EGC in combination with either WLI or 2G-NBI.

Image-enhanced endoscopy for gastric preneoplastic conditions and neoplastic lesions: a systematic review and meta-analysis

BACKGROUND : Image-enhanced endoscopy (IEE) improves the accuracy of endoscopic diagnosis. We aimed to assess the value of IEE for gastric preneoplastic conditions and neoplastic lesions. METHODS : Medline and Embase were searched until December 2018. Studies allowing calculation of diagnostic measures were included. Risk of bias and applicability were assessed using QUADAS-2. Subgroup analysis was performed to explore heterogeneity. RESULTS : 44 studies met the inclusion criteria. For gastric intestinal metaplasia (GIM), narrow-band imaging (NBI) obtained a pooled sensitivity and specificity of 0.79 (95 %CI 0.72-0.85) and 0.91 (95 %CI 0.88-0.94) on per-patient basis; on per-biopsy basis, it was 0.84 (95 %CI 0.81-0.86) and 0.95 (95 %CI 0.94-0.96), respectively. Tubulovillous pattern was the most accurate marker to detect GIM and it was effectively assessed without high magnification. For dysplasia, NBI showed a pooled sensitivity and specificity of 0.87 (95 %CI 0.84-0.89) and 0.97 (95 %CI 0.97-0.98) on per-biopsy basis. The use of magnification improved the performance of NBI to characterize early gastric cancer (EGC), especially when the vessel plus surface (VS) classification was applied. Regarding other technologies, trimodal imaging also obtained a high accuracy for dysplasia (sensitivity 0.93 [95 %CI 0.85-0.98], specificity 0.98 [95 %CI 0.92-1.00]). For atrophic gastritis, no specific pattern was noted and none of the technologies reached good diagnostic yield. CONCLUSION : NBI is highly accurate for GIM and dysplasia. The presence of tubulovillous pattern and the VS classification seem to be useful to detect GIM and characterize EGC, respectively. These features should be used in current practice and to standardize endoscopic criteria for other technologies.

Early gastric cancer and Artificial Intelligence: Is it time for population screening?

Gastric cancer is a common cause of death worldwide and its early detection is crucial to improve its prognosis. Its incidence varies throughout countries, and screening has been found to be cost-effective at least in high-incidence regions. Identification of individuals harbouring preneoplastic lesions and their surveillance or of those with early gastric cancer are extremely important processes and endoscopy play a key role for this purpose. Unfortunately, also quality and accuracy for endoscopic detection varies among centres and endoscopists. Recent studies about Artificial Intelligence applied to endoscopic imaging show that these technologies perform very well and could be extremely useful for endoscopists to achieve the accuracy needed for gastric cancer screening. Nonetheless, as its introduction in this field is very recent, most studies are carried out offline and its results in clinical practice need to be further validated namely by incorporating all the components/dimensions of endoscopy from pre to post-assessment.

Narrowband imaging with near-focus magnification for discriminating the gastric tumor margin before endoscopic resection: A prospective randomized multicenter trial

BACKGROUND AND AIM

This study investigated the usefulness of near-focus narrowband imaging (NF-NBI) for determining gastric tumor margins compared with indigo carmine chromoendoscopy (ICC) before endoscopic submucosal dissection (ESD).

METHODS

This prospective randomized controlled trial was conducted at seven teaching hospitals in Korea. Patients with gastric adenoma or differentiated adenocarcinoma undergoing ESD were enrolled and randomly assigned to the NF-NBI or ICC group. A marking dot was placed on the most proximal margin of the tumor before ESD. The primary endpoint was delineation accuracy, which was defined as presence of marking dots within 1 mm of the tumor margin under microscopic observation.

RESULTS

A total of 200 patients in the NF-NBI group and 195 patients in the ICC group were included. The delineation accuracy rate was 84.5% in the NF-NBI group and 81.0% in the ICC group (P = 0.44). However, the distance from the marking dot to the margin of the tumor was significantly shorter in the NF-NBI group than in the ICC group (0.8 ± 0.8 vs 1.2 ± 1.3 mm, P < 0.01). Even after adjustment of other clinicopathological factors that are associated with difficulty of tumor delineation, NF-NBI did not show significant association with accurate delineation (odds ratio of 0.86, P = 0.60).

CONCLUSIONS

This prospective multicenter study showed that NF-NBI is not superior to ICC in terms of accurately delineating gastric tumors (NCT02661945).

Three-dimensional flexible endoscopy enables more accurate endoscopic recognition and endoscopic submucosal dissection marking for superficial gastric neoplasia: a pilot study to compare two- and three-dimensional imaging

BACKGROUND

Three-dimensional (3D) visualization offers better depth recognition than two-dimensional (2D) imaging, thus helping to provide more useful information. We compared 3D and 2D endoscopy with regard to endoscopic recognition and endoscopic submucosal dissection (ESD) marking for superficial gastric neoplasia.

METHODS

ESD marking was performed on half of a neoplasia margin under 2D observation and the on other half under 3D observation for 28 gastric lesions (26 early gastric cancers and 2 adenomas). The accuracy of ESD marking was evaluated based on the distance between the pathological and endoscopic neoplasia margins measured on histology sections of ESD specimens. The technical ease of ESD marking and endoscopic lesion recognition (lesion morphology, lesion extent, and comprehensive endoscopic cognition) were assessed using visual analog scale (VAS) questionnaires.

RESULTS

The mean distance between the pathological and endoscopic margins under 3D observation (1.03 ± 0.80 mm) was significantly (p = 0.002) shorter than that under 2D observation (1.94 ± 1.96 mm). The VAS for technical ease of ESD marking under 3D observation was significantly better (p < 0.01) than that under 2D observation. The VAS for all aspects of endoscopic recognition under 3D observation was significantly better (p < 0.01) than under 2D observation.

CONCLUSIONS

3D flexible endoscopy achieved more accurate endoscopic recognition and ESD marking for superficial gastric neoplasia than a 2D approach in a clinical setting of ESD.

Diagnosis of early gastric cancer using image enhanced endoscopy: a systematic approach

This paper provides an overview of the principles of a vessel plus surface (VS) classification system to explain the diagnostic system of early gastric cancer using image-enhanced magnifying endoscopy. Furthermore, this paper introduces the magnifying endoscopy simple diagnostic algorithm for gastric cancer (MEADA-G) developed according to the VS classification system, with a description of the procedures performed for diagnosis. In addition to the diagnostic system, white opaque substance (WOS), light blue crest (LBC), white globe appearance (WGA), and vessels within epithelial circle (VEC) patterns, which are representative findings that can be observed in the gastric mucosa by image-enhanced magnifying endoscopy, are also described. Image-enhanced magnifying endoscopy is particularly useful in the diagnosis of differentiated-type early gastric cancer. It is important to use the appropriate clinical strategies based on a comprehensive understanding of the usefulness and limitations of the diagnostic system described in this paper.

Diagnostic limitations of magnifying endoscopy with narrow-band imaging in early gastric cancer

Background and study aims  Magnifying endoscopy with narrow band imaging (M-NBI) has made a huge contribution to endoscopic diagnosis of early gastric cancer (EGC). However, we sometimes encountered false-negative cases with M-NBI diagnosis (i. e., M-NBI diagnostic limitation lesion: M-NBI-DLL). However, clinicopathological features of M-NBI-DLLs have not been well elucidated. We aimed to clarify the clinicopathological features and histological reasons of M-NBI-DLLs. Patients and methods  In this single-center retrospective study, M-NBI-DLLs were extracted from 456 EGCs resected endoscopically at our hospital. We defined histological types of M-NBI-DLLs and analyzed clinicopathologically to clarify histological reasons of M-NBI-DLLs. Results  Of 456 EGCs, 48 lesions (10.5 %) of M-NBI-DLLs were enrolled. M-NBI-DLLs was classified into four histological types as follows: gastric adenocarcinoma of fundic-gland type (GA-FG, n = 25), gastric adenocarcinoma of fundic-gland mucosal type (GA-FGM, n = 1), differentiated adenocarcinoma (n = 14), and undifferentiated adenocarcinoma (n = 8). Thirty-nine lesions of M-NBI-DLLs were H. pylori -negative gastric cancers (39/47, 82.9 %). Histological reasons for M-NBI-DLLs were as follows: 1) completely covered with non-neoplastic mucosa (25/25 GA-FG, 8/8 undifferentiated adenocarcinoma); 2) well-differentiated adenocarcinoma with low-grade atypia (1/1 GA-FGM, 14/14 differentiated adenocarcinoma); 3) similarity of surface structure (10/14 differentiated adenocarcinoma); and 4) partially covered and/or mixed with a non-neoplastic mucosa (1/1 GA-FGM, 6/14 differentiated adenocarcinoma). Conclusions  Diagnostic limitations of M-NBI depend on four distinct histological characteristics. For accurate diagnosis of M-NBI-DLLs, it may be necessary to fully understand endoscopic features of these lesions using white light imaging and M-NBI based on these histological characteristics and to take a precise biopsy.

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.

Performance of a computer-aided diagnosis system in diagnosing early gastric cancer using magnifying endoscopy videos with narrow-band imaging (with videos)

BACKGROUND AND AIMS

The performance of magnifying endoscopy with narrow-band imaging (ME-NBI) using a computer-aided diagnosis (CAD) system in diagnosing early gastric cancer (EGC) is unclear. Here, we aimed to clarify the differences in the diagnostic performance between expert endoscopists and the CAD system using ME-NBI.

METHODS

The CAD system was pretrained using 1492 cancerous and 1078 noncancerous images obtained using ME-NBI. One hundred seventy-four videos (87 cancerous and 87 noncancerous videos) were used to evaluate the diagnostic performance of the CAD system using the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). For each item, comparisons were made between the CAD system and 11 experts who were skilled in diagnosing EGC using ME-NBI with clinical experience of more than 1 year at our hospital.

RESULTS

The CAD system demonstrated an AUC of 0.8684. The accuracy, sensitivity, specificity, PPV, and NPV were 85.1% (95% confidence interval [95% CI], 79.0-89.6), 87.4% (95% CI, 78.8-92.8), 82.8% (95% CI, 73.5-89.3), 83.5% (95% CI, 74.6-89.7), and 86.7% (95% CI, 77.8-92.4), respectively. The CAD system was significantly more accurate than 2 experts, significantly less accurate than 1 expert, and not significantly different from the remaining 8 experts.

CONCLUSIONS

The overall performance of the CAD system using ME-NBI videos in diagnosing EGC was considered good and was equivalent to or better than that of several experts. The CAD system may prove useful in the diagnosis of EGC in clinical practice.

Management following endoscopic resection in elderly patients with early-stage upper gastrointestinal neoplasia

With the ongoing increase in the aging population in Japan, the number of elderly patients among the total population with upper gastrointestinal (GI) neoplasia has also been increasing. As elderly patients present unique age-related variations in their physical condition, the therapeutic approach for upper GI neoplasia should be differentiated between elderly and nonelderly patients. According to the existing guidelines, additional treatment is the standard therapy in patients who undergo endoscopic resection (ER) with a possible risk of lymph node metastasis (LNM) for upper GI neoplasia. However, due to the relatively low rate of LNM, applying additional treatment in all elderly patients may be excessive. Although additional treatment has the advantage of reducing cancer-specific mortality, its disadvantages include deteriorated quality of life, complications, and mortality in surgery. In patients with early gastric cancer, we propose treatment decisions be made using a risk-scoring system for LNM and upon considering the physical condition of the patient after ER with curability C-2. In those with superficial esophageal squamous cell carcinoma with a possible risk of LNM after ER, selective chemoradiotherapy may be a less-invasive treatment option, although the present standard treatment is esophagectomy. When considering the treatment decision, achieving a "cure" of the tumor has been regarded as critical. However, as the main cause of mortality in elderly patients with ER for upper GI neoplasia is noncancer-related death, both achieving a "cure" and also a good level of "care" is important in the management of elderly patients.

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.

Value of endoscopy with narrow-band imaging and probe-based confocal laser endomicroscopy in the diagnosis of preneoplastic lesions of gastrointestinal tract

INTRODUCTION

Amongst all malignant tumors, cancers of the digestive tract rank first in terms of yearly deaths. Patients above 60 years of age are the most affected, as the diagnosis is frequently made in advanced stages of the disease when therapy is less effective. Our study aimed to evaluate the efficiency of narrow-band imaging (NBI) endoscopy and probe-based confocal laser endomicroscopy (pCLE) in the correct diagnosis of preneoplastic lesions in the upper and lower digestive tract.

PATIENTS, MATERIALS AND METHODS

We included 46 patients with digestive preneoplastic lesions, who underwent either upper or lower digestive endoscopy, followed by NBI and pCLE. We recorded 5-10 frames per each lesion, from different angles and distances during white-light endoscopy and selected frames from full recordings of NBI and pCLE. Usual preparation was used for the endoscopic procedures; pCLE required in vivo administration of 10% Sodium Fluorescein as a contrast agent. Pathology was performed in case of solid tumors. Three medical professionals with different levels of training, blinded to the results, interpreted the data.

RESULTS

The experienced physician correlated very well the NBI findings with pathology (0.93, p=0.05), while the resident physician and the experienced nurse obtain lower, albeit still statistically significant, values (0.73 and 0.62, respectively). For pCLE, the experienced physician obtained near-perfect correlation with pathology (0.96), followed closely by the resident physician (0.93). The nurse obtained a modest correlation (0.42). All examiners obtained approximately equal performances in discerning between malignant and benign lesions.

CONCLUSIONS

Digestive endoscopy in NBI mode proved its effectiveness. Even less experienced endoscopists can achieve good results, while an experienced nurse can positively influence the diagnosis. In the case of pCLE, when available, it can greatly reduce diagnostic times, while requiring higher expertise and specialty training.

Guidelines for endoscopic diagnosis of early gastric cancer

The Japan Gastroenterological Endoscopy Society developed the Guideline for Endoscopic Diagnosis of Early Gastric Cancer based on scientific methods. Endoscopy for the diagnosis of early gastric cancer has been acknowledged as a useful and highly precise examination, and its use has become increasingly more common in recent years. However, the level of evidence in this field is low, and it is often necessary to determine recommendations based on expert consensus only. This clinical practice guideline consists of the following sections to provide the current guideline: [I] Risk stratification of gastric cancer before endoscopic examination, [II] Detection of early gastric cancer, [III] Qualitative diagnosis of early gastric cancer, [IV] Diagnosis to choose the therapeutic strategy for gastric cancer, [V] Risk stratification after endoscopic examination, and [VI] Surveillance of early gastric cancer.

Convolutional Neural Network for Differentiating Gastric Cancer from Gastritis Using Magnified Endoscopy with Narrow Band Imaging

BACKGROUND

Early detection of early gastric cancer (EGC) allows for less invasive cancer treatment. However, differentiating EGC from gastritis remains challenging. Although magnifying endoscopy with narrow band imaging (ME-NBI) is useful for differentiating EGC from gastritis, this skill takes substantial effort. Since the development of the ability to convolve the image while maintaining the characteristics of the input image (convolution neural network: CNN), allowing the classification of the input image (CNN system), the image recognition ability of CNN has dramatically improved.

AIMS

To explore the diagnostic ability of the CNN system with ME-NBI for differentiating between EGC and gastritis.

METHODS

A 22-layer CNN system was pre-trained using 1492 EGC and 1078 gastritis images from ME-NBI. A separate test data set (151 EGC and 107 gastritis images based on ME-NBI) was used to evaluate the diagnostic ability [accuracy, sensitivity, positive predictive value (PPV), and negative predictive value (NPV)] of the CNN system.

RESULTS

The accuracy of the CNN system with ME-NBI images was 85.3%, with 220 of the 258 images being correctly diagnosed. The method's sensitivity, specificity, PPV, and NPV were 95.4%, 71.0%, 82.3%, and 91.7%, respectively. Seven of the 151 EGC images were recognized as gastritis, whereas 31 of the 107 gastritis images were recognized as EGC. The overall test speed was 51.83 images/s (0.02 s/image).

CONCLUSIONS

The CNN system with ME-NBI can differentiate between EGC and gastritis in a short time with high sensitivity and NPV. Thus, the CNN system may complement current clinical practice of diagnosis with ME-NBI.

Fluorescence detection of deep intramucosal cancer excited by green light for photodynamic diagnosis using protoporphyrin IX induced by 5-aminolevulinic acid: an ex vivo study

SIGNIFICANCE

The diagnostic depth of photodynamic diagnosis (PDD) for gastric cancer with protoporphyrin IX (PpIX) is limited, which leads to missing intramucosal cancers in screening and surgery.

AIM

The reason is that the excitation light, whose wavelength is determined by the highest absorption peak of PpIX (∼405  nm), is strongly attenuated by mucosal tissues. We investigated an excitation wavelength that can extend the diagnostic depth of PpIX fluorescence at the mucosal subsurface.

APPROACH

By calculating the depth-dependent intensity of the excitation light in porcine gastric mucosa for each wavelength, relationships among the wavelength, fluorophore depth, and fluorescence intensity were assessed and fluorescence images of PpIX pellets located at different fluorophore depths were compared experimentally by changing the excitation wavelength.

RESULTS

The numerical calculation showed that a 505-nm excitation light provided the highest fluorescence intensities at a fluorophore depth deeper than 1.1 mm. In the fluorescence observation, the fluorescence intensities at fluorophore depths of 0 and 1.0 mm at 405 nm were 5.4  ×  103 and 1.0  ×  103  arb. units, whereas those at 505 nm were 5.3  ×  101 and 1.9  ×  102  arb. units, respectively.

CONCLUSION

The experimental results suggest that the diagnosis depth of PDD with PpIX for intramucosal cancer can be extended by 505-nm excitation light.

Additive Effect of Magnifying Endoscopy with Narrow-Band Imaging for Diagnosing Mixed-Type Early Gastric Cancers

BACKGROUND

Pretreatment biopsy may not correctly diagnose mixed-type early gastric cancers. Despite reports on the usefulness of magnifying endoscopy with narrow-band imaging in diagnosing early gastric cancers, no reports exist on differences in magnifying endoscopy with narrow-band imaging findings between differentiated-type-predominant mixed-type and undifferentiated-type-predominant mixed-type early gastric cancers.

AIM

This study aimed to clarify differences in magnifying endoscopy with narrow-band imaging findings and investigate the additive effect of combining magnifying endoscopy with narrow-band imaging and biopsy findings for pretreatment histological-type diagnosis.

METHODS

Patients undergoing endoscopic submucosal dissection as initial treatment between April 2005 and March 2017 participated in this retrospective study. There were 156 differentiated-type-predominant mixed-type and 36 undifferentiated-type-predominant mixed-type lesions. We extracted the most significant magnifying endoscopy with narrow-band imaging findings of differentiated-type-predominant mixed-type and undifferentiated-type-predominant mixed-type lesions using multivariate analysis and compared the accuracy, sensitivity, and specificity between pretreatment biopsy alone and a combination of biopsy and magnifying endoscopy with narrow-band imaging findings.

RESULTS

Significant magnifying endoscopy with narrow-band imaging findings was fine network pattern in differentiated-type-predominant and corkscrew pattern in undifferentiated-type-predominant mixed-type lesions. Accuracy, sensitivity, and specificity were significantly higher with combined biopsy and magnifying endoscopy with narrow-band imaging findings than with pretreatment biopsy alone.

CONCLUSIONS

The study results demonstrated the additive effect of magnifying endoscopy with narrow-band imaging with biopsy for diagnosing mixed-type early gastric cancers. This study may be beneficial in routine practice because it indicates a possibility of reducing additional surgery after endoscopic submucosal resection because of incorrect diagnosis of histological type.

Recent advances in diagnostic upper endoscopy

BACKGROUND

Esophageo-gastro-duodenoscopy (EGD) is an important procedure used for detection and diagnosis of esophago-gastric lesions. There exists no consensus on the technique of examination.

AIM

To identify recent advances in diagnostic EGDs to improve diagnostic yield.

METHODS

We queried the PubMed database for relevant articles published between January 2001 and August 2019 as well as hand searched references from recently published endoscopy guidelines. Keywords used included free text and MeSH terms addressing quality indicators and technological innovations in EGDs. Factors affecting diagnostic yield and EGD quality were identified and divided into the follow segments: Pre endoscopy preparation, sedation, examination schema, examination time, routine biopsy, image enhanced endoscopy and future developments.

RESULTS

We identified 120 relevant abstracts of which we utilized 67 of these studies in our review. Adequate pre-endoscopy preparation with simethicone and pronase increases gastric visibility. Proper sedation, especially with propofol, increases patient satisfaction after procedure and may improve detection of superficial gastrointestinal lesions. There is a movement towards mandatory picture documentation during EGD as well as dedicating sufficient time for examination improves diagnostic yield. The use of image enhanced endoscopy and magnifying endoscopy improves detection of squamous cell carcinoma and gastric neoplasm. The magnifying endoscopy simple diagnostic algorithm is useful for diagnosis of early gastric cancer.

CONCLUSION

There is a steady momentum in the past decade towards improving diagnostic yield, quality and reporting in EGDs. Other interesting innovations, such as Raman spectroscopy, endocytoscopy and artificial intelligence may have widespread endoscopic applications in the near future.

Convolutional neural network for the diagnosis of early gastric cancer based on magnifying narrow band imaging

BACKGROUND

Magnifying endoscopy with narrow band imaging (M-NBI) has been applied to examine early gastric cancer by observing microvascular architecture and microsurface structure of gastric mucosal lesions. However, the diagnostic efficacy of non-experts in differentiating early gastric cancer from non-cancerous lesions by M-NBI remained far from satisfactory. In this study, we developed a new system based on convolutional neural network (CNN) to analyze gastric mucosal lesions observed by M-NBI.

METHODS

A total of 386 images of non-cancerous lesions and 1702 images of early gastric cancer were collected to train and establish a CNN model (Inception-v3). Then a total of 341 endoscopic images (171 non-cancerous lesions and 170 early gastric cancer) were selected to evaluate the diagnostic capabilities of CNN and endoscopists. Primary outcome measures included diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value.

RESULTS

The sensitivity, specificity, and accuracy of CNN system in the diagnosis of early gastric cancer were 91.18%, 90.64%, and 90.91%, respectively. No significant difference was spotted in the specificity and accuracy of diagnosis between CNN and experts. However, the diagnostic sensitivity of CNN was significantly higher than that of the experts. Furthermore, the diagnostic sensitivity, specificity and accuracy of CNN were significantly higher than those of the non-experts.

CONCLUSIONS

Our CNN system showed high accuracy, sensitivity and specificity in the diagnosis of early gastric cancer. It is anticipated that more progress will be made in optimization of the CNN diagnostic system and further development of artificial intelligence in the medical field.

Preoperative indicators of misdiagnosis in invasion depth staging of esophageal cancer: Pitfalls of magnifying endoscopy with narrow-band imaging

OBJECTIVES

The Japan Esophageal Society classification has been widely applied for predicting the invasion depth of superficial esophageal squamous cell carcinomas (SESCCs). Although Type B2 of the classification clinically corresponds to SESCCs with muscularis mucosa or slight submucosal invasion (MM/SM1), diagnostic yield based on Type B2 is insufficient. This study aimed to investigate risk factors for misdiagnosis in preoperative invasion depth staging.

METHODS

We included a total of 104 SESCCs in which Type B2 was observed by magnifying endoscopy. SESCCs were classified as either correct diagnosis (pMM/SM1, 39 lesions), overdiagnosis (epithelium or the lamina propria [pEP/LPM], 34 lesions), or underdiagnosis (deep invasion into the submucosa [pSM2-3], 31 lesions) based on pathological depth of invasion. The association between misdiagnosis and endoscopic features, including distinct features, was evaluated using logistic regression analysis. Distinct features were defined as nodular protrusion, thickness, and/or clearly depressed area. The diameter of type B2 area was endoscopically measured, and the cut-off value was determined using a receiver operating characteristic curve.

RESULTS

Type B2 area <6 mm (area under the curve, 0.776) and Type B2 vessels around erosion were significantly associated with overdiagnosis (odds ratio, 16.6 and 11.0, respectively), while distinct features were significantly associated with underdiagnosis (odds ratio, 8.7). Adjusted by these misdiagnosis factors, positive predictive value of Type B2 significantly improved from 38% to 65% (P < 0.01).

CONCLUSIONS

Lesions with a small Type B2 area (<6 mm) and/or Type B2 vessels around erosion should be diagnosed as EP/LPM and lesions with distinct features as SM2-3.

Risk stratification for lymph node metastasis using Epstein-Barr virus status in submucosal invasive (pT1) gastric cancer without lymphovascular invasion: a multicenter observational study

BACKGROUND

Lymphovascular invasion (LVI) is a strong predictive factor for lymph node metastasis (LNM) in early gastric cancer (GC). This study investigated the risk for LNM in pT1b GC without LVI based on Epstein-Barr virus (EBV) status in addition to conventional clinicopathological parameters.

METHODS

In total, 847 consecutive patients of pT1b GC without LVI who underwent surgery at three high-volume centers between 2005 and 2014 were retrospectively analyzed. Clinicopathological parameters and EBV status were evaluated, and univariate and multivariate analyses were performed to estimate LNM risk. With regard to the presence of those three parameters, risk stratification for LNM was performed and compared with a previously proposed risk classification that included low-risk (LNM < 3.0%), intermediate-risk (LNM ≥ 3.0 and < 19.6%), and high-risk (LNM ≥ 19.6%) groups.

RESULTS

EBV-positive GC (EBVGC) accounted for 11.3% (96 of 847) of cases; LNM was lower in EBVGC than in non-EBVGC (1 of 96, 1.0% vs. 71/751, 9.5%). In the multivariate analysis, non-EBVGC [odds ratio (OR) 10.8, 95% confidence interval (CI) 1.48-78.9], age < 65 years (OR 2.13, 95% CI 1.30-3.48), and tumor diameter > 3 cm (OR 2.26, 95% CI 1.36-3.74) were independent risk factors for LNM. Patients with EBVGC were at low risk for LNM whereas those with all of three independent risk factors were at high risk (36 of 168, 21.4%, 95% CI 15.5-28.4).

CONCLUSION

LNM risk stratification that includes EBV status is useful for clinical decision-making in pT1b GC cases without LVI.