Search

Background and Aims There are no agreed-on endoscopic signs for the diagnosis of villous atrophy (VA) in celiac disease (CD), necessitating biopsy sampling for diagnosis. Here we evaluated the role of near-focus narrow-band imaging (NF-NBI) for the assessment of villous architecture in suspected CD with the development and further validation of a novel NF-NBI classification. Methods Patients with a clinical indication for duodenal biopsy sampling were prospectively recruited. Six paired NF white-light endoscopy (NF-WLE) and NF-NBI images with matched duodenal biopsy sampling including the bulb were obtained from each patient. Histopathology grading used the Marsh-Oberhuber classification. A modified Delphi process was performed on 498 images and video recordings by 3 endoscopists to define NF-NBI classifiers, resulting in a 3-descriptor classification: villous shape, vascularity, and crypt phenotype. Thirteen blinded endoscopists (5 expert, 8 nonexpert) then undertook a short training module on the proposed classification and evaluated paired NF-WLE–NF-NBI images. Results One hundred consecutive patients were enrolled (97 completed the study; 66 women; mean age, 51.2 ± 17.3 years). Thirteen endoscopists evaluated 50 paired NF-WLE and NF-NBI images each (24 biopsy-proven VAs). Interobserver agreement among all validators for the diagnosis of villous morphology using the NF-NBI classification was substantial (κ = .71) and moderate (κ = .46) with NF-WLE. Substantial agreement was observed between all 3 NF-NBI classification descriptors and histology (weighted κ = 0.72-.75) compared with NF-WLE to histology (κ = .34). A higher degree of confidence using NF-NBI was observed when assessing the duodenal bulb. Conclusions We developed and validated a novel NF-NBI classification to reliably diagnose VA in suspected CD. There was utility for expert and nonexpert endoscopists alike, using readily available equipment and requiring minimal training. (Clinical trial registration number: NCT04349904.)

Introduction: Although endocytoscopy (EC) with narrow-band imaging (NBI) is effective in diagnosing gastric cancer, no diagnostic system has been validated. We explored a specific diagnostic system for gastric cancer using EC with NBI. Methods: Equal numbers of images from cancerous and noncancerous areas (114 images each) were assessed by endoscopists with (development group: 33) and without (validation group: 28) specific training in magnifying endoscopy with NBI. Microvascular and microsurface patterns (MS) in each image were evaluated. Lesions were diagnosed as cancerous when patterns were deemed “irregular.” The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of a diagnosis according to patterns on EC with NBI (microvascular pattern [MV] alone, MS alone, and both) were evaluated and compared between groups to determine the diagnostic performance. Results: In the development and validation groups, diagnoses based on the MV alone had significantly higher accuracy (91.7% vs. 76.3%, p < 0.0001 and 92.5% vs. 67.5%, p < 0.0001, respectively) and sensitivity (88.6% vs. 68.3%, p < 0.0001 and 89.5% vs. 38.6%, p < 0.0001, respectively) than those based on the MS alone. In both groups, there were no significant differences in diagnostic accuracy between using the MV alone and both patterns. Discussion/Conclusion: Evaluation of the MV alone is a simple and accurate diagnostic method for gastric cancer. This system could find widespread applications in clinical practice.

Objectives To assess a new application of artificial intelligence for real-time detection of laryngeal squamous cell carcinoma (LSCC) in both white light (WL) and narrow-band imaging (NBI) videolaryngoscopies based on the You-Only-Look-Once (YOLO) deep learning convolutional neural network (CNN). Study design Experimental study with retrospective data. Methods Recorded videos of LSCC were retrospectively collected from in-office transnasal videoendoscopies and intraoperative rigid endoscopies. LSCC videoframes were extracted for training, validation, and testing of various YOLO models. Different techniques were used to enhance the image analysis: contrast limited adaptive histogram equalization, data augmentation techniques, and test time augmentation (TTA). The best-performing model was used to assess the automatic detection of LSCC in six videolaryngoscopies. Results Two hundred and nineteen patients were retrospectively enrolled. A total of 624 LSCC videoframes were extracted. The YOLO models were trained after random distribution of images into a training set (82.6%), validation set (8.2%), and testing set (9.2%). Among the various models, the ensemble algorithm (YOLOv5s with YOLOv5m-TTA) achieved the best LSCC detection results, with performance metrics in par with the results reported by other state-of-the-art detection models: 0.66 Precision (positive predicted value), 0.62 Recall (sensitivity), and 0.63 mean Average Precision at 0.5 intersection over union. Tests on the six videolaryngoscopies demonstrated an average computation time per videoframe of 0.026 seconds. Three demonstration videos are provided. Conclusion This study identified a suitable CNN model for LSCC detection in WL and NBI videolaryngoscopies. Detection performances are highly promising. The limited complexity and quick computational times for LSCC detection make this model ideal for real-time processing. Level of evidence 3 Laryngoscope, 2021.

Background: With the development of new technologies such as magnifying endoscopy with narrow band imaging, endoscopists achieved better accuracy for diagnosis of gastric cancer (GC) in various aspects. However, to master such skill takes substantial effort and could be difficult for inexperienced doctors. Therefore, a novel diagnostic method based on artificial intelligence (AI) was developed and its effectiveness was confirmed in many studies. AI system using convolutional neural network has showed marvelous results in the ongoing trials of computer-aided detection of colorectal polyps. Summary: With AI’s efficient computational power and learning capacities, endoscopists could improve their diagnostic accuracy and avoid the overlooking or over-diagnosis of gastric neoplasm. Several systems have been reported to achieved decent accuracy. Thus, AI-assisted endoscopy showed great potential on more accurate and sensitive ways for early detection, differentiation, and invasion depth prediction of gastric lesions. However, the feasibility, effectiveness, and safety in daily practice remain to be tested. Key messages: This review summarizes the current status of different AI applications in early GC diagnosis. More randomized controlled trails will be needed before AI could be widely put into clinical practice.

OBJECTIVES Magnifying endoscopy with narrow-band imaging (M-NBI) is useful for the optical diagnosis of gastrointestinal neoplasms. However, the utility of M-NBI in screening esophagogastroduodenoscopy (EGD) is unclear. We aimed to evaluate the diagnostic ability of the magnification endoscope (ME) in screening EGD for a population with a low prevalence of upper gastrointestinal cancers. METHODS Overall, 4887 asymptomatic examinees without a history of laryngopharyngeal and/or upper gastrointestinal neoplasms who underwent opportunistic screening EGD between April 2011 and December 2017 were enrolled in this retrospective study. The examinees were categorized into two groups depending on whether screening EGD was performed using ME (ME group) or not (non-ME group). Using a propensity score-matched analysis, the diagnostic ability of EGD was compared between the two groups. RESULTS In total, 1482 examinees (30%) were allocated to the ME group and 3405 (70%) to the non-ME group. Thirty-five epithelial neoplasms were detected in 30 examinees (0.6%). The groups were matched for baseline characteristics (1481 pairs). Both groups showed no significant difference in the epithelial neoplasm detection rate (0.8% vs. 0.3%; P = 0.14). The biopsy rate was significantly lower in the ME group than in the non-ME group (12% vs. 15%; P = 0.003). The positive predictive value (PPV) for biopsy was significantly higher in the ME group than in the non-ME group (6.6% vs. 2.8%; P = 0.048). CONCLUSIONS Using an ME for screening EGD in an apparently healthy, asymptomatic population could reduce unnecessary biopsies by improving PPV for biopsy without decreasing the epithelial neoplasm detection rate.

OBJECTIVES/HYPOTHESIS To develop a deep-learning-based automatic diagnosis system for identifying nasopharyngeal carcinoma (NPC) from noncancer (inflammation and hyperplasia), using both white light imaging (WLI) and narrow-band imaging (NBI) nasopharyngoscopy images. STUDY DESIGN Retrospective study. METHODS A total of 4,783 nasopharyngoscopy images (2,898 WLI and 1,885 NBI) of 671 patients were collected and a novel deep convolutional neural network (DCNN) framework was developed named Siamese deep convolutional neural network (S-DCNN), which can simultaneously utilize WLI and NBI images to improve the classification performance. To verify the effectiveness of combining the above-mentioned two modal images for prediction, we compared the proposed S-DCNN with two baseline models, namely DCNN-1 (only considering WLI images) and DCNN-2 (only considering NBI images). RESULTS In the threefold cross-validation, an overall accuracy and area under the curve of the three DCNNs achieved 94.9% (95% confidence interval [CI] 93.3%-96.5%) and 0.986 (95% CI 0.982-0.992), 87.0% (95% CI 84.2%-89.7%) and 0.930 (95% CI 0.906-0.961), and 92.8% (95% CI 90.4%-95.3%) and 0.971 (95% CI 0.953-0.992), respectively. The accuracy of S-DCNN is significantly improved compared with DCNN-1 (P-value

Objectives With the advent of new optical technologies, early pharyngolaryngeal cancerous lesions can be better visualized. Although the conventional transnasal approach offers great views of the hypopharynx and larynx, the visualization of the oropharynx and palatine tonsils is limited. Through the transoral insertion of a flexible video-laryngoscope, direct views of the oropharynx and oral cavity can be obtained. Thus, transoral examination may contribute to primary detection of cancers of unknown primary (CUP). Methods Eighty-five CUP patients from Tokai University were included retrospectively in this study, from 2006 to 2017. Starting in 2010, we employed the transoral examination in addition to our conventional method. The primary detection rates were compared before and after 2010. Oropharyngeal primaries were further analyzed for tumor subsite and p16 status. Results The overall primary detection rate did not improve with the addition of transoral examination. However, greater numbers of oropharyngeal primaries were detected. The oropharyngeal lesions detected by transoral examination were mainly p16 positive, located on the palatine tonsil. Conclusion Transoral examination is a noninvasive, easy method to adopt in an outpatient setting, and a promising technique to improve tumor detection in this era of human papillomavirus-associated head and neck cancers. Level of evidence 3.

Introduction Traditional meta-analyses on the diagnostic accuracy of oral lesions have been conducted, but they were inherently limited to direct pairwise comparisons between a single method and a single alternative, while multiple diagnostic options and the ranking thereof were methodologically not possible. Objective To evaluate the diagnostic values of various methods in patients with oral potential malignant disease by performing a network meta-analysis. Methods Two authors independently searched the databases (MEDLINE, SCOPUS, the Cochrane Register of Controlled Trials, and Google scholar) up to June 2020 for studies comparing the diagnostic accuracy of various tools (autofluorescence, chemiluminescence, cytology, narrow band imaging, and toluidine blue) with visual examination or other tools. The outcomes of interest for this analysis were sensitivity, specificity, negative predictive value, positive predictive value and accuracy. Both a standard pairwise meta-analysis and network meta-analysis were conducted. Results Treatment networks consisting of six interventions were defined for the network meta-analysis. The results of traditional meta-analysis showed that, among six methods, narrow band imaging showed higher sensitivity, specificity, negative predictive value, positive predictive value, and accuracy compared to visual examination. The results of network meta-analysis showed that autofluorescence, chemiluminescence, and narrow band imaging had higher sensitivity compared with visual examination, and that chemiluminescence and narrow band imaging had higher negative predictive value compared with visual examination. However, autofluorescence and chemiluminescence had lower specificity compared with visual examination. There were no significant differences in positive predictive value and accuracy among the six interventions. Conclusion This study demonstrated that narrow banding imaging has superiority in terms of sensitivity and negative predictive value compared with the other five tested agents.

Background: White light imaging (WLI) cystoscopy, a “gold standard” for diagnosis of nonmuscle invasive bladder cancer (NMIBC), can miss ∼25% of bladder cancers. Spectra A (SA) and Spectra B (SB) a...

Treatment strategies for superficial esophageal squamous cell carcinoma (SESCC) are determined mainly on the basis of the invasion depth. The Japan Esophageal Society (JES) developed a simplified magnifying endoscopic classification for estimating the invasion depth of SESCC. We aimed to evaluate its accuracy. We prospectively applied the JES classification for estimating the invasion depth of SESCC to 204 consecutive lesions from 6 hospitals in Japan between April 2016 and October 2018. We analyzed the accuracy of the endoscopic diagnosis by adding the following two categories to the JES classification: ≥ 7 mm lesion in B2 vessels (defined as B2 ≥ 7 mm) and B2 vessels with inflammation (defined as B2i). After applying the exclusion criteria, 201 lesions remained in the analysis. The diagnostic value of type B1, B2, B3 vessels were as follows: sensitivity, 93.9%, 68.0%, 25.0%; specificity, 81.1%, 89.2%, 99.4%; positive predictive value (PPV), 95.6%, 47.2%, 75.0%; negative predictive value (NPV), 75.0%, 95.1%, 95.4%; and accuracy, 91.5%, 86.5%, 95.0%, respectively. A retrospective analysis showed that the diagnostic accuracy was higher in type B2 vessels (86.5% to 92.0%). An avascular area (AVA) was found in 55 (27%) of the 201 lesions, which tended to be associated with a deeper pathological diagnosis of each Type B vessel. In an additional analysis, B2 ≥ 7 mm and B2i improved the diagnostic accuracy of type B2 vessels from 86.5% to 92.0%. The JES classification is useful for estimating the invasion depth of SESCC. The diagnostic accuracy for type B2 vessels was low, which may be improved by using B2 ≥ 7 mm and B2i.

We compared the diagnostic accuracies of narrowband imaging and white-light endoscopy in the detection of nasopharyngeal cancer.Six databases (PubMed, Cochrane Database, Embase, Web of Science, SCOPUS, and Google Scholar).The 6 databases were thoroughly reviewed by 2 authors (working independently) from their dates of inception to December 2019. Nasopharyngeal mucosal or vascular changes detected by narrowband imaging were compared to those detected by white-light endoscopy. The authors extracted true-positive, true-negative, false-positive, and false-negative parameters for each study. Methodological quality was evaluated using the Quality Assessment of Diagnostic Accuracy Studies version 2 tool. The extent of interrater agreement was assessed.Eighteen prospective or retrospective studies were included. The diagnostic odds ratio of narrowband imaging was 77.560 (95% confidence interval [CI], 37.424-160.739). The area under the summary receiver operating characteristic curve was 0.926. The sensitivity, specificity, and negative predictive value were 0.871 (95% CI, 0.808-0.915), 0.905 (95% CI, 0.816-0.953), and 0.955 (95% CI, 0.906-0.979), respectively. The correlation between sensitivity and the false-positive rate was 0.284, indicating that heterogeneity was absent. Narrowband imaging exhibited moderate interrater reliability (0.7037; 95% CI, 0.6558-0.746). Subgroup analysis showed that vascular patterns revealed by endoscopy in a screened subgroup were significantly more diagnostically accurate than mucosal patterns used for surveillance of a recurrent cancer subgroup.Narrowband imaging exhibits high diagnostic accuracy and should be used in the diagnostic workup of nasopharyngeal cancer. However, further studies are necessary to confirm our results.

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. (Gut Liver 2021;15:492-499)

Background/Aims: A white substance that is opaque to endoscopic light is sometimes observed in the epithelium during narrowband imaging with magnifying endoscopy of gastric or colorectal epithelial neoplasms. This prospective observational study aimed to determine whether the morphology of the white opaque substance (WOS) allows differential diagnosis between colorectal adenoma and carcinoma.Methods: A consecutive series of patients with colorectal adenomas or early carcinomas who underwent endoscopic resection or surgical excision were studied. The morphology of the WOS was determined based on endoscopic images before the histopathological diagnosis was performed. The primary outcome was the diagnostic performance of an irregular WOS as a marker of colorectal carcinoma.Results: The study analyzed 125 lesions. A total of 33 lesions showed an irregular WOS, and 92 lesions showed a regular WOS. Among the 33 lesions found to show an irregular WOS, 30 were carcinomas. Among the 92 lesions showing a regular WOS, 79 were adenomas. With irregular WOS as a marker of carcinoma, the diagnostic accuracy was 87%, sensitivity was 91%, and specificity was 86%.Conclusions: This study demonstrated the potential usefulness of the morphology of the WOS as a marker for the differential diagnosis between adenoma and carcinoma in cases of colorectal epithelial neoplasms.

Recently, studies in many medical fields have reported that image analysis based on artificial intelligence (AI) can be used to analyze structures or features that are difficult to identify with human eyes. To diagnose early gastric cancer, related efforts such as narrow-band imaging technology are on-going. However, diagnosis is often difficult. Therefore, a diagnostic method based on AI for endoscopic imaging was developed and its effectiveness was confirmed in many studies. The gastric cancer diagnostic program based on AI showed relatively high diagnostic accuracy and could differentially diagnose non-neoplastic lesions including benign gastric ulcers and dysplasia. An AI system has also been developed that helps to predict the invasion depth of gastric cancer through endoscopic images and observe the stomach during endoscopy without blind spots. Therefore, if AI is used in the field of endoscopy, it is expected to aid in the diagnosis of gastric neoplasms and determine the application of endoscopic therapy by predicting the invasion depth.

Blue light imaging (BLI) has been shown to improve the characterization of colorectal polyps among the endoscopy experts. We aimed to determine if this technology could be taught to endoscopy trainees while maintaining high accuracy and interobserver agreement.Twenty-one gastroenterology trainees (fellows) from two academic institutions participated in this prospective study. Each trainee completed a web-based learning comprising four modules: pre-test, didactic videos explaining the BLI Adenoma Serrated International Classification (BASIC), interactive examples, and post-test assessment. The pre- and post-test modules consisted of reviewing video images of colon polyps in high definition white light imaging and BLI and then applying the BASIC classification to determine if the polyps were likely to be adenomatous. Confidence in adenoma identification (rated '1' to '5'), accuracy in polyp (adenoma vs. non-adenoma) identification, and agreement in characterization per BASIC criteria were derived.Trainee accuracy in the adenoma diagnosis improved from 74.7% (pre-test) to 85.4% (post-test) (P 0.01). There was a trend towards higher accuracy in polyp characterization with subsequent years of training (1st year fellows 77.4%, 2nd year 88.5%, and final year 94.0%) with consistent improvements after the e-learning across years of trainees. Overall, trainees were able to identify adenoma with a high sensitivity of 86.9%, specificity 83.9%, positive predictive value of 84.4%, and negative predictive value of 86.5%. However, their interobserver agreement in adenoma diagnosis was moderate (k = 0.52).The novel BLI classification can be easily taught to gastroenterology trainees using an online module and accuracy improves with years of training reaching90% for colorectal polyp characterization.

BACKGROUND AND AIMS Gastric intestinal metaplasia (GIM), a precursor of gastric adenocarcinoma, is challenging to diagnose with white light endoscopy (WLE) and can be missed by random gastric biopsies. Narrowband imaging (NBI) may potentially improve the detection of GIM. However, pooled estimates from prospective studies are lacking. METHODS Electronic databases were searched for studies comparing NBI and WLE alone for detection of GIM and synchronous dysplasia. Primary outcome was pooled detection rate of GIM by NBI compared with WLE in prospective studies. The secondary outcome was concurrent dysplasia detection. RESULTS Ten studies were found eligible from 306 articles screened. Eight prospective studies were found eligible for primary endpoint of GIM detection. Two other retrospective studies were included for dysplasia detection. A total of 1366 subjects (694 males, 54.4 ± 5.08 years) underwent upper endoscopy. GIM was detected in 482 (35.3%) subjects. NBI detected GIM in 32% additional subjects (70% vs 38%, RR 1.79; 95% CI 1.34-2.37; P

Perpendicular vascular changes (PVC) are markers of tumor-induced neoangiogenesis at the vocal folds. Contact endoscopy with narrow-band imaging (CE-NBI) allows a detailed analysis of such vascular changes.This work intends to evaluate the potential of CE-NBI for diagnosis of benign, dysplastic, and malignant lesions of the vocal folds. In addition, it should be determined whether CE-NBI offers an additional benefit in detecting PVC compared to white-light endoscopy (WLE) and NBI alone.Three examiners evaluated histologically verified cases of benign, dysplastic, and malignant lesions of the larynx in WLE, NBI, and CE-NBI (n = 60). In each mode, they examined the lesion for PVC and assessed the lesion's dignity. The proportion of lesions with detected PVC, the statistical measures of performance in detecting high-grade dysplasia and carcinoma, and the interrater variability for each mode were calculated.CE-NBI proved superior to the other investigated diagnostic methods in terms of detecting PVC and in terms of sensitivity and accuracy in the diagnosis of high-grade dysplasia and carcinoma. A clear association of such pathologies with PVC was seen.CE-NBI detects PVC more frequently and reliably than the other methods investigated. The association of these vascular patterns to high-grade dysplasia and vocal fold carcinomas could be confirmed. Compared to WLE and NBI endoscopy, the diagnostic quality for detecting high-grade dysplasia and carcinoma is increased. Thus, CE-NBI can improve endoscopic differentiation between benign and malignant lesions of the vocal folds by enhancing the detection of PVC.HINTERGRUND: Perpendikuläre Gefäßveränderungen (PGV) sind Marker der tumorinduzierten Neoangiogenese der Stimmlippen. Die Kontaktendoskopie mit Narrow Band Imaging (KE-NBI) ermöglicht eine detaillierte Analyse solcher Gefäßveränderungen.In dieser Arbeit wurde das Potenzial der KE-NBI bei der Diagnostik benigner, dysplastischer und maligner Veränderungen der Stimmlippen untersucht. Außerdem sollte bei der Detektion von PGV die Aussagekraft des KE-NBI im Vergleich zur Weißlichtendoskopie (WLE) und zur alleinigen Narrow-Band-Imaging-Endoskopie (NBI) bestimmt werden.Dazu befundeten 3 Untersucher histopathologisch verifizierte benigne, dysplastische oder maligne Läsionen der Stimmlippen (n = 60) jeweils im Modus WLE, NBI und KE-NBI. Die Läsionen wurden auf PGV hin untersucht und ihre Dignität beurteilt. Ermittelt wurden der Anteil der Läsionen mit detektierten PGV sowie die diagnostische Güte für jeden Modus und die Interratervariabilität bei der Erkennung von höhergradigen Dysplasien und Karzinomen.Die KE-NBI zeigte sich den anderen Modi bei der Detektion von PGV und hinsichtlich Sensitivität und Genauigkeit bei der Erkennung von höhergradigen Dysplasien und Karzinomen überlegen. Die Autoren sahen eine deutliche Assoziation dieser pathologischen Veränderungen mit PGV.Mittels KE-NBI werden PGV häufiger und zuverlässiger als mit den anderen Methoden erkannt. Die Assoziation dieser Gefäßveränderungen mit höhergradigen Dysplasien und Karzinomen der Stimmlippen wurde bestätigt. Im Vergleich zu WLE und NBI zeigte sich eine erhöhte diagnostische Güte. Somit kann die KE-NBI durch bessere Detektion der PGV die endoskopische Differenzierung zwischen benignen und malignen Läsionen der Stimmlippen verbessern.

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;15:329-337)

BACKGROUND: Proliferative abnormalities are believed to represent an early phase of colorectal carcinogenesis. Narrow band imaging (NBI) colonoscopy allows visual assessment of the mucosal vascular pattern (MVP) without dyeing. The aim of this study was to investigate the predictive value of MVP for mucosal proliferation in ulcerative colitis (UC). METHODS: A total of 119 colorectal lesions were analyzed from 42 patients with UC who underwent NBI colonoscopy. Both the MVP and the Mayo endoscopic score (MES) were assessed. The mucosal inflammation was histologically graded using a colitis score. The proliferation marker Ki-67 was assessed by immunohistochemical staining. RESULTS: The results showed that MVP correlated well with the MES (r = 0.796, P < .001). There was moderate correlation between the distribution of Ki-67 staining and MVP (r = 0.492, P < .001), and the Ki-67 labeling index increased with the orderly patterns of MVP (P < .001). An expansion of Ki-67 staining upward from the crypt base may be caused by active inflammation. CONCLUSION: MVP based on NBI colonoscopy can predict mucosal proliferation which is associated with inflammation in patients with UC.

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.

Background Intraoperative ultrasonography is the golden standard method for evaluation of liver tumors during hepatectomy. However, in laparoscopic surgery, accurate assessment of tumors may be difficult, particularly if the lesion is located nearby the liver surface because of the challenges in handling the intraoperative ultrasound and the lack of tactile sensation. In this study, we demonstrate the preliminary results of examining the microvascular architecture of subcapsular hepatic tumors using laparoscopic narrow-band imaging (NBI) to distinguish between malignant and benign tumors. Materials and Methods Thirty-five lesions were examined by NBI during laparoscopic hepatectomy for the presence of abnormal microvasculature on the liver surface in relation to hepatic tumors from January 2016 to August 2018. The microvascular findings were correlated with tumor localization and pathological diagnosis. Results The 35 examined nodules included 11 hepatocellular carcinoma, 18 colorectal liver metastasis, and six benign nodules. The mean tumor diameter was 26.3 (3-70) mm, and the distance from the liver surface to the tumor was 0.5 (0-5) mm. Microvessels on the liver surface were clearly visualized by NBI, consistent with malignant tumor localization. The tumors were thoroughly examined for the presence of three pathological microvascular features (enlargement, tortuosity, and heterogeneity). Abnormal microvascular patterns were found in 90.9% of hepatocellular carcinoma and 77.8% of colorectal liver metastasis, whereas neither normal sites nor benign lesions displayed microvascular abnormality. Conclusions This study suggests that observing the microvessel image on the liver surface by NBI could be useful in tumor localization and differentiation between benign and malignant lesions.

Introduction The novel optical techniques such as blue light cystoscopy (BLC) during transurethral resection of bladder tumor (TURBT) has been shown to improve the tumor detection rate and recurrence rate. Whether a single immediate intravesical chemotherapy (SIIC) still has an additive therapeutic effect in the setting of these novel optical techniques (e.g., photodynamic diagnosis (PDD) and narrow band imaging (NBI)) remains unclear. The main aim of this systematic review and network meta-analysis was to assess whether SIIC still adds value to bladder tumor management in combination with optical techniques- enhanced TURBT. Methods A systematic search was performed using PubMed and Web of Science databases in September 2020 according to the Preferred Reporting Items for Systematic Review and Meta-analysis (PRISMA) extension statement for network meta-analysis. Studies that compared recurrence rates between intervention groups (TURBT by PDD ± SIIC, NBI ± SIIC, or WLC + SIIC) and control group (TURBT by WLC alone) were included. We used the Bayesian approach in the network meta-analysis. Results Twenty-two studies (n= 4,519) met our eligibility criteria. Out of six different interventions including three different optical techniques, compared to WLC alone, BLC plus SIIC (odds ratio (OR): 0.349, 95% credible interval (CrI):0.196-0.601) and BLC alone (OR: 0.668, 95% CrI:0.459-0.931) were associated with a significantly lower likelihood of 12-month recurrence rate. In the sensitivity analysis, out of eight different interventions compared to WLC alone, PDD by 5-aminolevulinic plus SIIC (OR: 0.327, 95% CrI:0.159-0.646) and by hexaminolevulinic acid plus SIIC (OR: 0.376, 95% CrI:0.172-0.783) were both associated with a significantly lower likelihood of 12-month recurrence rate. NBI with and without SIIC were not associated with a significantly lower likelihood of 12-month recurrence rate (OR: 0.385, 95% CrI:0.105-1.29 and OR: 0.653, 95% CrI:0.343-1.15). Conclusion BLC during TURBT with concomitant SIIC seems to yieled superior recurrence outcomes in patients with non-muscle invasive bladder cancer. The Use of PDD was able to reduce the 12-month recurrence rate; moreover, a concomitant SIIC increased this risk benefit by 32% additional reduction of odds ratio. Although using PDD could reduce the recurrence rate, SIIC remains necessary. Moreover, the ranking analysis showed that both PDD and NBI, plus SIIC were better than these techniques alone.

Background Autoimmune and multifocal atrophic gastritis (AG) are at risk for gastric neoplastic lesions. European guidelines recommend surveillance with high-quality endoscopy every 3 years. Aim To prospectively investigate the occurrence of gastric neoplastic lesions at the 3-year follow-up in patients with autoimmune and multifocal AG. Methods Longitudinal cohort study conducted between 2011 and 2019: consecutive patients with histological diagnosis of autoimmune or multifocal AG underwent follow-up gastroscopy 3 years after diagnosis with high-resolution-narrow-band-imaging endoscopes. Results Overall, 160 patients were included(F117(73.0%);median age 66(35–87)years). Autoimmune and multifocal AG were present in 122(76.3%) and 38(23.7%) patients, respectively. At the 3-year follow-up, 16(10.0%) patients presented 16 gastric neoplastic lesions: 3(18.7%) gastric cancers, 4(25.0%) low-grade dysplasia, 2(12.5%) low-grade dysplasia adenomas, 7(43.7%) type-1 neuroendocrine tumours. In these patients, OLGA and OLGIM III/IV stages were present in 4(25.0)% and 1(6.3%), respectively; 11(69.0%) presented autoimmune AG, and all but one(93.7%) had parietal cells antibodies positivity (p = 0.026 vs patients without lesions). All lesions were endoscopically(87.5%) or surgically(12.5%) treated with favourable outcome. Age>70 years was associated with a 9-fold higher probability of developing gastric epithelial neoplastic lesions (OR 9.6,95CI% 1.2–79.4,p = 0.0359). Conclusions The first endoscopic surveillance 3 years after diagnosis seems safe for autoimmune and multifocal AG patients and should be offered to elderly patients who are at higher risk for gastric neoplasia.

Introduction: Narrow Band Imaging (NBI) is an endoscopic optical imaging enhancement technology that improves the contrast of mucosal surface texture and enhances visualization of mucosal and submucosal vasculature. Due to its properties, it can visualize suspected malignant or precancerous lesions earlier than conventional white light endoscopy. The aim of this study was to analyze the benefit of NBI in visualization of precancerous and malignant lesions in preoperative and intraoperative diagnostics and correlation with histopathologic results. Methods: A total of 589 patients with suspicious laryngeal or hypopharyngeal lesion were investigated using conventional white light endoscopy (WLE) and NBI endoscopy with high-definition TV (HDTV NBI) from 10/2013 to 12/2019. Patients were divided into two groups based on pre-operative NBI examination (group A, 345 patients) and intraoperative NBI examination (group B, 244 patients). All suspicious lesions were graded to 5 types of Ni classification and correlated with histopathologic results. The SPSS version 8.0.4 statistical software package was used for statistical analysis. In diagnosing premalignant and malignant lesions sensitivity, specificity, positive predictive value, and negative predictive value were calculated. Results: The agreement between NBI endoscopy and histopathological analysis in group A was statistically significant (Қ = 0.76, p < 0.001), with a sensitivity of 86.2% (95% IS: 65.4–95.2) and specificity of 90.9% (95% IS: 70.6–94.1). Moreover, in group B was proven almost perfect agreement between NBI and histopathological analysis (Қ = 0.8461, p < 0.001), with a sensitivity of 84.0% (95% IS: 60.2–92.4) and specificity of 96.0% (95% IS: 87.0–99.2). Conclusions: Based on our results, NBI using the Ni classification has great potential in improving diagnosis of precancerous and malignant lesions and correlates strongly with histopathologic results. It serves as a useful adjunct to white light endoscopy in the diagnosis of laryngeal and hypopharyngeal lesions, especially using HDTV NBI.

The main aims of the oncologic surgeon should be an early tumor diagnosis, complete surgical resection, and a careful post-treatment follow-up to ensure a prompt diagnosis of recurrence. Radiologic and endoscopic methods have been traditionally used for these purposes, but their accuracy might sometimes be suboptimal. Technological improvements could help the clinician during the diagnostic and therapeutic management of tumors. Narrow band imaging (NBI) belongs to optical image techniques, and uses light characteristics to enhance tissue vascularization. Because neoangiogenesis is a fundamental step during carcinogenesis, NBI could be useful in the diagnostic and therapeutic workup of tumors. Since its introduction in 2001, NBI use has rapidly spread in different oncologic specialties with clear advantages. There is an active interest in this topic as demonstrated by the thriving literature. It is unavoidable for clinicians to gain in-depth knowledge about the application of NBI to their specific field, losing the overall view on the topic. However, by looking at other fields of application, clinicians could find ideas to improve NBI use in their own specialty. The aim of this review is to summarize the existing literature on NBI use in oncology, with the aim of providing the state of the art: we present an overview on NBI fields of application, results, and possible future improvements in the different specialties.

Introduction The microarchitecture of the mucosal and submucosal vessels is crucial for diagnosis of vocal fold lesions. Neo-angiogenesis is a confirmed biological parameter that implicates progression and metastasis in laryngeal cancer. Objective This study investigates the correlation between vascular pattern classifications by narrow band imaging and immunohistological microvessel density in different types of intraepithelial vocal fold lesions. Methods Analysis of immunohistological microvessel density using CD31 and CD34 antibodies was performed in 77 lesions including: 20 non-dysplastic lesions, 20 with low-grade dysplasia, 17 with high-grade dysplasia and 20 invasive cancers. The evaluation of vascular patterns with narrow band imaging according to the Ni classification and European Laryngological Society guidelines was performed prior to surgical resection. Results The mean value of CD31 microvessel density was the highest for Ni Type IV lesions (20.55), whereas for the longitudinal and perpendicular patterns according to the European Laryngological Society classification it was 12.50 and 19.45 respectively. The highest mean value of microvessel density with CD 34 was identified in Ni Type Va (35.43) lesions and in the longitudinal and perpendicular patterns according to the European Laryngological Society classification was 15.12 and 30.40 respectively. Conclusions The microvascular morphological changes of intraepithelial laryngeal lesions observed under narrow band imaging endoscopy are positively correlated with angiogenesis indexes of immunohistological evaluation.

Introduction With the advancements in diagnostic and therapeutic upper gastrointestinal endoscopy (UGIE), clear mucosal visualization is essential to ensure optimal outcomes. Though routinely followed in Japan and Korea, pre-endoscopic preparation is seldom used in India. We evaluated the efficacy of a pre-endoscopic drink of N-acetylcysteine (NAC) and simethicone in improving mucosal visibility during UGIE. Patients and Methods This study was a retrospective, investigator blind study with a case–control study design. Cases included patients who received a pre-endoscopy drink of NAC and simethicone in 100 mL water administered 10 to 30 minutes prior to UGIE. Controls only had mandatory fasting for 6 to 8 hours prior to UGIE. Propensity score matching was done to ensure comparability between the groups. Digital images were taken at six standard landmarks during UGIE and stored. A blinded investigator subsequently analyzed the images and rated the mucosal visibility on a 3-point scale. The difference in the mean mucosal visibility between the cases and controls was compared. Results Mean mucosal visibility during UGIE was significantly better using NAC with simethicone as compared with no preparation at esophagus (1.14 [0.37] vs. 1.47 [0.62], p < 0.05), gastric fundus (1.10 [0.30] vs. 1.55 [0.64], p < 0.05), gastric body (1.22 [0.50] vs. 1.62 [0.73], p < 0.05), gastric antrum (1.13 [0.37] vs. 1.47 [0.62], p < 0.05), and duodenal bulb (1.13 [0.34] vs. 1.33 [0.56], p < 0.05). In distal duodenum, though visibility improved with NAC with simethicone, the difference was insignificant. There were no adverse events related to the pre-endoscopy drink. Conclusion A pre-endoscopy drink of NAC with simethicone can significantly improve mucosal visibility during UGIE. It is safe, cheap, easily available and maybe considered for routine utilization for ensuring optimal endoscopic outcomes.

Purpose Heterotopic gastric mucosa in the upper esophagus (cervical inlet patches - CIP) may be easily missed during esophagogastroduodenoscopy (EGD) due to low awareness of this usually, but not invariably, benign lesion. Narrow-band imaging (NBI) emphasizes contrast between normal esophageal mucosa and CIP. The purpose of this study was to investigate how NBI use and enhanced attention of operator during inspection of upper esophagus impacts cervical inlet patch detection rate (CIPDR). Materials and methods This is a prospective, randomized study in which we enrolled 1000 patients, qualified for diagnostic EGD. The trial was divided into two parts; the first, when 6 operators performed EGD with standard attention (SA), and the second, when the same operators were asked to step up with attention at CIP (enhanced attention - EA). In both parts of the study, patients were randomized to NBI and white light endoscopy (WLE) in 1:1 ratio. The study is registered in ClinicalTrials.gov (No. NCT03015571). Results Differences in CIPDR between WLE and NBI in SA and EA were not statistically different (5.6% vs 7.6%; p ​= ​0.3, and 7.6% vs 11.6%; p ​= ​0.1, respectively). In multivariate regression analysis, the only factors improving CIPDR were NBI with EA (NBIEA, OR 3.31; 95%CI 1.57–6.98; p ​= ​0.003) and sedation (OR 1.97; 95%CI 1.27–3.05; p ​= ​0.002). Conclusions The use of NBI combined with EA significantly improves CIPDR.

Background and Aims Artificial intelligence (AI)–based computer-aided diagnostic (CADx) algorithms are a promising approach for real-time histology (RTH) of colonic polyps. Our aim is to present a novel in situ CADx approach that seeks to increase transparency and interpretability of results by generating an intuitive augmented visualization of the model’s predicted histology over the polyp surface. Methods We developed a deep learning model using semantic segmentation to delineate polyp boundaries and a deep learning model to classify subregions within the segmented polyp. These subregions were classified independently and were subsequently aggregated to generate a histology map of the polyp’s surface. We used 740 high-magnification narrow-band images from 607 polyps in 286 patients and over 65,000 subregions to train and validate the model. Results The model achieved a sensitivity of .96, specificity of .84, negative predictive value (NPV) of .91, and high-confidence rate (HCR) of .88, distinguishing 171 neoplastic polyps from 83 non-neoplastic polyps of all sizes. Among 93 neoplastic and 75 non-neoplastic polyps ≤5 mm, the model achieved a sensitivity of .95, specificity of .84, NPV of .91, and HCR of .86. Conclusions The CADx model is capable of accurately distinguishing neoplastic from non-neoplastic polyps and provides a histology map of the spatial distribution of localized histologic predictions along the delineated polyp surface. This capability may improve interpretability and transparency of AI-based RTH and offer intuitive, accurate, and user-friendly guidance in real time for the clinical management and documentation of optical histology results.

Background An educational and training program is required for generalization of Japan NBI Expert Team (JNET) classification. However, there is no detailed report on the learning curve of the diagnostic accuracy of endoscopists using JNET classification. We examined the effect of an educational lecture on beginners and less experienced endoscopists for improving their diagnostic accuracy of colorectal lesions by JNET classification. Methods Seven beginners with no endoscopy experience (NEE group), 7 less experienced endoscopists (LEE group), and 3 highly experienced endoscopists (HEE group) performed diagnosis using JNET classification for randomized NBI images of colorectal lesions from 180 cases (Type 1: 22 cases, Type 2A: 105 cases, Type 2B: 33 cases, and Type 3: 20 cases). Next, the NEE and LEE groups received a lecture on JNET classification, and all 3 groups repeated the diagnostic process. We compared the correct diagnosis rate and interobserver agreement before and after the lecture comprehensively and for each JNET type. Results In the HEE group, the correct diagnosis rate was more than 90% with good interobserver agreements (kappa value: 0.78–0.85). In the NEE and LEE groups, the correct diagnosis rate (NEE: 60.2 → 68.0%, P P P P Conclusion After conducting an appropriate lecture, the diagnostic ability using JNET classification was improved in beginners or endoscopists with less experience in NBI magnifying endoscopy.

BACKGROUND Adenosquamous carcinoma (ASC), which is comprised of squamous cell carcinoma (SCC) and adenocarcinoma elements, is a rare histological type of esophageal carcinoma. Few reports have focused on the endoscopic findings and the effectiveness of the endoscopic treatment of early ASC. CASE SUMMARY A 77-year-old man underwent esophagogastroduodenoscopy for heartburn. A flat lesion with an uneven and slightly elevated central portion was found in the distal esophagus. Magnifying endoscopy with narrow-band imaging showed a well-demarcated brownish area with dendritically branched abnormal vessels and highly irregular intrapapillary capillary loops. A histopathological diagnosis of SCC was obtained by endoscopic biopsy. Endoscopic ultrasonography revealed a hypoechoic mass confined to the mucosa layer. The lesion was suspected to be SCC with invasion into the muscularis mucosa. The lesion was resected en bloc by endoscopic submucosal dissection and histologically diagnosed as esophageal ASC limited within the muscularis mucosa, which was completely resected without lymphovascular or neural invasion. The SCC element was the pre-dominant element. The adenocarcinoma element formed ductal and nested structures distributed in a focal pattern. The patient underwent only endoscopic submucosal dissection and has been under annual endoscopic and radiographic surveillance for 3 years without recurrence. CONCLUSION For early ASC confined within the mucosal layer, complete endoscopic resection might also be a curative treatment.

BACKGROUND It remains unclear whether the use of adjunctive diagnostic screening methods improves the diagnostic efficacies of oral premalignant and cancerous lesions. OBJECTIVE OF REVIEW We evaluated the diagnostic accuracy of narrow-band imaging used to detect oral cancer and precancerous lesions defined employing different narrow-band imaging criteria. TYPE OF REVIEW Systematic review and meta-analyses. SEARCH STRATEGY We searched PubMed, Scopus, the Web of Science, Embase, Google Scholar and the Cochrane Central Register of Controlled Trials to May 2020. EVALUATION METHODS Three different criteria for oral mucosal vascular changes using narrow-band imaging were compared: class I: well-demarcated brownish areas with thick dark spots and/or winding vessels; class II: intraepithelial papillary capillary looping of grades 2, 3 and 4; and class III: intraepithelial papillary capillary looping of grades 3 and 4. Methodological quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies (ver. 2) tool. We compared narrow-band imaging to conventional white-light imaging. RESULTS We included 10 prospective or retrospective studies (1374 patients). To detect all dysplastic and cancerous lesions, the class I criteria afforded the optimal specificity and sensitivity; the area under the summary receiver operating characteristic curve was 0.918. To detect highly dysplastic and advanced cancerous lesions, the class III criteria afforded appropriate specificity and sensitivity. The summary receiver operating characteristic curve was 0.905. When using the class III criteria, narrow-band imaging afforded better specificity (0.941 [range 0.920, 0.9572], P

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.

Background and Aim Magnifying endoscopy (ME) diagnostic algorithm for early gastric cancer (EGC) relies on qualitative features such as microvascular (MV) architecture and microsurface structure; however, it is a “static” diagnostic algorithm that uses still images. ME can visualize red blood cell flow within subepithelial microvessels in real time. Here, we evaluated the utility of using the MV blood flow rate in combination with ME for the diagnosis of EGC as a retrospective study. Methods Patients with differentiated‐type EGC (n = 10) or patchy redness (n = 10) underwent ME with blue laser imaging. The mean MV blood flow rates of EGC, patchy redness, and background mucosa were calculated by the mean movement distance of one tagging red blood cell using split images of ME with blue laser imaging videos. We compared the mean MV blood flow rate between EGC, patchy redness, and background mucosa and also calculated the MV blood flow imaging ratio (inside lesion/background mucosa) between EGC and patchy redness. Results Mean MV blood flow rate was significantly lower in EGC (1481 μm/s; range 1057–1762) than in patchy redness (3859 μm/s; 2435–5899) or background mucosa (4140.6 μm/s; 2820–6247) (P

Background and aims Endoscopic diagnosis of early esophageal squamous cell cancer (ESCC) is complicated and dependent on operators' experience. This study aimed to develop an artificial intelligence (AI) model for automatic diagnosis of early ESCC. Methods Non-magnifying and magnifying endoscopic images of normal/noncancerous lesions, early ESCC, and advanced esophageal cancer (AEC) were retrospectively obtained from Qilu Hospital of Shandong University. A total of 10,988 images from 5075 cases were chosen for training and validation. Another 2309 images from 1055 cases were collected for testing. One hundred and four real-time videos were also collected to evaluate the diagnostic performance of the AI model. The diagnostic performance of the AI model was compared with endoscopists by magnifying images and the assistant efficiency of the AI model for novices was evaluated. Results The AI diagnosis for non-magnifying images showed a per-patient accuracy, sensitivity, and specificity of 99.5%, 100%, 99.5% for white light imaging, and 97.0%, 97.2%, 96.4% for optical enhancement/iodine straining images. Regarding diagnosis for magnifying images, the per-patient accuracy, sensitivity, and specificity were 88.1%, 90.9%, and 85.0%. The diagnostic accuracy of the AI model was similar to experts (84.5%, P = 0.205) and superior to novices (68.5%, P = 0.005). The diagnostic performance of novices was significantly improved by AI assistance. When it comes to the diagnosis for real-time videos, the AI model showed acceptable performance as well. Conclusions The AI model could accurately recognize early ESCC among noncancerous mucosa and AEC. It could be a potential assistant for endoscopists, especially for novices.

Background Non-magnifying endoscopy with narrow-band imaging (NM-NBI) has been frequently used in routine screening of esophagus squamous cell carcinoma (ESCC). The performance of NBI for screening of early ESCC is, however, significantly affected by operator experience. Artificial intelligence may be a unique approach to compensate for the lack of operator experience. Aim To construct a computer-aided detection (CAD) system for application in NM-NBI to identify early ESCC and to compare it with our previously reported CAD system with endoscopic white-light imaging (WLI). Methods A total of 2167 abnormal NM-NBI images of early ESCC and 2568 normal images were collected from three institutions (Zhongshan Hospital of Fudan University, Xuhui Hospital, and Kiang Wu Hospital) as the training dataset, and 316 pairs of images, each pair including images obtained by WLI and NBI (same part), were collected for validation. Twenty endoscopists participated in this study to review the validation images with or without the assistance of the CAD systems. The diagnostic results of the two CAD systems and improvement in diagnostic efficacy of endoscopists were compared in terms of sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. Results The area under receiver operating characteristic curve for CAD-NBI was 0.9761. For the validation dataset, the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of CAD-NBI were 91.0%, 96.7%, 94.3%, 95.3%, and 93.6%, respectively, while those of CAD-WLI were 98.5%, 83.1%, 89.5%, 80.8%, and 98.7%, respectively. CAD-NBI showed superior accuracy and specificity than CAD-WLI (P = 0.028 and P ≤ 0.001, respectively), while CAD-WLI had higher sensitivity than CAD-NBI (P = 0.006). By using both CAD-WLI and CAD-NBI, the endoscopists could improve their diagnostic efficacy to the highest level, with accuracy, sensitivity, and specificity of 94.9%, 92.4%, and 96.7%, respectively. Conclusion The CAD-NBI system for screening early ESCC has higher accuracy and specificity than CAD-WLI. Endoscopists can achieve the best diagnostic efficacy using both CAD-WLI and CAD-NBI.

The aim of this study was to assess the performance of Narrow Band Imaging (NBI) added to White Light (WL) in the delineation of laryngopharyngeal superficial cancer spread during office-based transnasal flexible endoscopy. This bi-centric prospective study was conducted between October 2014 and December 2017. We included consecutive patients with laryngopharyngeal malignant tumors. Transnasal flexible endoscopy was performed by two endoscopists who were blinded to each other's assessments and who examined each patient independently. The first endoscopist only performed a WL examination, while the second endoscopist carried out both WL and NBI. The extent of tumor involvement was reported based on predefined anatomical sub-units. Biopsies in NBI + /WL− sub-units were subsequently performed during panendoscopy. Eighty-four patients were included in the study. A total of 72 NBI + /WL− sub-units were sampled in 38 patients, and 37 of the biopsies were positive (51.4%): 16 for invasive carcinoma, 17 for high-grade dysplasia/carcinoma in situ and 4 for low-grade dysplasia. Ultimately, 26.2% of patients had at least one positive biopsy in an NBI + /WL− sub-unit and, therefore, a better tumor delineation. The clinical T stage was upgraded in 4.8% of cases examined. Adding NBI to WL imaging during transnasal flexible endoscopy in patients presenting with laryngopharyngeal pre-malignant or malignant lesions improves the delineation of superficial cancer spread, thereby leading to better adapted treatments. Clinicaltrials.gov registration number: NCT02035735.

Condyloma acuminatum, in the form of genital warts, usually results from an infection by human papillomavirus, one of the most common causes of sexually transmitted diseases. It develops after an incubation period of 3 weeks to 8 months after infection; flat lesions are significantly rare. Condyloma acuminatum is prevalent in the genitals, particularly in the anus of immunodeficient patients. This also occurs in women during menstrual period and pregnancy. Although a common treatment option for rectal and anal lesions, surgical resection is highly invasive and results in a high rate of recurrence. Recently, endoscopic submucosal dissection has been performed for anorectal lesions, but data on its long-term follow-up are not available. We report the case of an immunocompromised patient due to pregnancy who remained recurrence-free 27 months after en-bloc resection by endoscopic submucosal dissection, with adequate visualisation of the flat lesion's safety margin, combined with magnifying narrow-band imaging.

Introduction: Curative rates of endoscopic treatment for undifferentiated-type early gastric cancer (EGC), particularly mixed poorly differentiated adenocarcinoma (MIXED-POR), are lower than those of endoscopic treatment for the differentiated type. Magnifying endoscopy with narrow-band imaging (ME-NBI) is useful for diagnoses of the histological type. This study aimed to investigate the detection rates of MIXED-POR among undifferentiated-type EGCs using biopsy and ME-NBI in order to improve curative rates through endoscopic treatment. Methods: We analyzed 267 lesions initially subjected to endoscopic submucosal resection (ESD) and histologically diagnosed as undifferentiated-type EGCs between July 2005 and December 2016 at our hospital. We obtained written informed consent from all participants. Biopsy and ME-NBI findings were compared to distinguish pure signet ring cell carcinoma (PURE-SIG) and MIXED-POR. ME-NBI findings were divided into 2 categories depending on the presence of irregular vessels. Results of biopsy and ME-NBI (combination method) were also analyzed, and detection rates of MIXED-POR and PURE-SIG were evaluated in terms of sensitivity, specificity, and accuracy. Results: Overall, 114 lesions were analyzed. Fifty-eight lesions (50.9%) were identified as MIXED-POR. With biopsy, the detection rate of MIXED-POR was significantly lower than that of PURE-SIG (p < 0.0001). ME-NBI detected significantly more MIXED-POR with irregular vessels than PURE-SIG (p < 0.0001). The combination method could detect significantly more MIXED-POR than PURE-SIG (p < 0.0001). The sensitivity and accuracy for MIXED-POR diagnosis were significantly higher with the combination method than with biopsy alone (p < 0.0001). Discussion/Conclusion: Combining biopsy and ME-NBI improved the accuracy of pretreatment diagnosis before ESD in undifferentiated-type cancer.

BACKGROUND AND AIMS: The endoscopic evaluation of narrow-band imaging (NBI) zoom imagery in Barrett's esophagus (BE) is associated with suboptimal diagnostic accuracy and poor interobserver agreement. Computer-aided diagnosis (CAD) systems may assist endoscopists in the characterization of Barrett's mucosa. Our aim was to demonstrate the feasibility of a deep-learning CAD system for tissue characterization of NBI zoom imagery in BE. METHODS: The CAD system was first trained using 494,364 endoscopic images of general endoscopic imagery. Next, 690 neoplastic BE and 557 nondysplastic BE (NDBE) white-light endoscopy overview images were used for refinement training. Subsequently, a third dataset of 112 neoplastic and 71 NDBE NBI zoom images with histologic correlation was used for training and internal validation. Finally, the CAD system was further trained and validated with a fourth, histologically confirmed dataset of 59 neoplastic and 98 NDBE NBI zoom videos. Performance was evaluated using fourfold cross-validation. The primary outcome was the diagnostic performance of the CAD system for classification of neoplasia in NBI zoom videos. RESULTS: The CAD system demonstrated accuracy, sensitivity, and specificity for detection of BE neoplasia using NBI zoom images of 84%, 88%, and 78%, respectively. In total, 30,021 individual video frames were analyzed by the CAD system. Accuracy, sensitivity, and specificity of the video-based CAD system were 83% (95% confidence interval [CI], 78%-89%), 85% (95% CI, 76%-94%), and 83% (95% CI, 76%-90%), respectively. The mean assessment speed was 38 frames per second. CONCLUSION: We have demonstrated promising diagnostic accuracy of predicting the presence/absence of Barrett's neoplasia on histologically confirmed unaltered NBI zoom videos with fast corresponding assessment time. ispartof: GASTROINTESTINAL ENDOSCOPY vol:93 issue:1 pages:89-98 ispartof: location:United States status: published

Background Linked color imaging (LCI) is a new image-enhanced endoscopy technique that allows users to recognize slight differences in mucosal color. Objective To compare the performance of LCI with white light imaging (WLI) in detecting neoplastic lesions in the upper gastrointestinal tract. Design A controlled, multicenter trial with randomization using minimization. (University Hospital Medical Information Network Clinical Trials Registry: UMIN000023863). Setting 16 university hospitals and 3 tertiary care hospitals in Japan. Patients 1502 patients with known previous or current cancer of the gastrointestinal tract and undergoing surveillance for gastrointestinal cancer. Intervention WLI followed by LCI examination (WLI group) or LCI followed by WLI examination (LCI group). Measurements Diagnosis of 1 or more neoplastic lesions in the pharynx, esophagus, or stomach in the first examination (primary outcome) and 1 or more neoplastic lesions overlooked in the first examination (secondary outcome). Results 752 patients were assigned to the WLI group and 750 to the LCI group. The percentage of patients with 1 or more neoplastic lesions diagnosed in the first examination was higher with LCI than with WLI (60 of 750 patients or 8.0% [95% CI, 6.2% to 10.2%] vs. 36 of 752 patients or 4.8% [CI, 3.4% to 6.6%]; risk ratio, 1.67 [CI, 1.12 to 2.50; P = 0.011]). The proportion with overlooked neoplasms was lower in the LCI group than in the WLI group (5 of 750 patients or 0.67% [CI, 0.2% to 1.6%] vs. 26 of 752 patients or 3.5% [CI, 2.3% to 5.0%]; risk ratio, 0.19 [CI, 0.07 to 0.50]). Limitation Endoscopists were not blinded. Conclusion LCI is more effective than WLI for detecting neoplastic lesions in the pharynx, esophagus, and stomach. Primary funding source Fujifilm Corporation.

This prospective study was aimed to evaluate the clinical value of narrow-band imaging (NBI), magnification endoscopy with narrow-band imaging (NBIME) and magnification endoscopy with acetic acid enhancement and narrow-band imaging (AA-NBIME) in the diagnosis of small colorectal polyps. We studied 261 small colorectal polyps from 122 patients with the use of above three techniques. Lesions were resected for histopathological analysis. The endoscopic images were independently reviewed by three experts and three non-experts and the diagnostic accuracy and image definition were compared among the modalities. The “experts-agreed” diagnostic accuracy was 87.7% for NBI versus 91.6% for NBIME versus 94.6% for AA-NBIME. The “non-experts-agreed” diagnostic accuracy was 80.1% for NBI versus 84.3% for NBIME versus 89.3% for AA-NBIME. All experts and non-experts diagnosed the small colorectal polyps statistically more accurately with AA-NBIME than NBI (P P

BACKGROUND: Disease recurrence and progression remain major challenges for the treatment of non‐muscle invasive bladder cancer. Narrow band imaging (NBI) is an optical enhancement technique that may improve resection of non‐muscle invasive bladder cancer and thereby lead to better outcomes for people undergoing the procedure. OBJECTIVES: To assess the effects of NBI‐ and white light cystoscopy (WLC)‐guided transurethral resection of bladder tumor (TURBT) compared to WLC‐guided TURBT in the treatment of non‐muscle invasive bladder cancer. SEARCH METHODS: We performed a comprehensive literature search of 10 databases, including the Cochrane Library, the Cochrane Database of Systematic Reviews, MEDLINE, Embase, several clinical trial registries, and grey literature for published and unpublished studies, irrespective of language. The search was performed per an a priori protocol on 3 December 2021. SELECTION CRITERIA: We included randomized controlled trials of participants with suspected or confirmed non‐muscle invasive bladder cancer. Participants in the control group must have received WLC‐guided TURBT alone (hereinafter simply referred to as 'WLC TURBT'). Participants in the intervention group had to have received NBI‐ and WLC‐guided TURBT (hereinafter simply referred to as 'NBI + WLC TURBT'). DATA COLLECTION AND ANALYSIS: Two review authors independently selected studies for inclusion/exclusion, performed data extraction, and assessed risk of bias. We conducted meta‐analysis on time‐to‐event and dichotomous data using a random‐effects model in RevMan, according to Cochrane methods. We rated the certainty of evidence for each outcome according to the GRADE approach. Primary outcomes were time to recurrence, time to progression, and the occurrence of a major adverse event, defined as a Clavien‐Dindo III, IV, or V complication. Secondary outcomes included time to death from bladder cancer and the occurrence of a minor adverse event, defined as a Clavien‐Dindo I or II complication. MAIN RESULTS: We included eight studies with a total of 2152 participants randomized to the standard WLC TURBT or to NBI + WLC TURBT. A total of 1847 participants were included for analysis. Based on limited confidence in the time‐to‐event data, we found that participants who underwent NBI + WLC TURBT had a lower risk of disease recurrence over time compared to participants who underwent WLC TURBT (hazard ratio 0.63, 95% CI 0.45 to 0.89; I(2) = 53%; 6 studies, 1244 participants; low certainty of evidence). No studies examined disease progression as a time‐to‐event outcome or a dichotomous outcome. There was likely no difference in the risk of a major adverse event between participants who underwent NBI + WLC TURBT and those who underwent WLC TURBT (risk ratio 1.77, 95% CI 0.79 to 3.96; 4 studies, 1385 participants; low certainty of evidence). No studies examined death from bladder cancer as a time‐to‐event outcome or a dichotomous outcome. There was likely no difference in the risk of a minor adverse event between participants who underwent NBI + WLC TURBT and those who underwent WLC TURBT (risk ratio 0.88, 95% CI 0.49 to 1.56; I(2) = 61%; 4 studies, 1385 participants; low certainty of evidence). AUTHORS' CONCLUSIONS: Compared to WLC TURBT alone, NBI + WLC TURBT may lower the risk of disease recurrence over time while having little or no effect on the risks of major or minor adverse events.

BACKGROUND AND AIMS The aim was to explore an effective training system for diagnosis of superficial esophageal squamous cell carcinoma (SESCC) and its staging with magnifying narrow-band imaging (M-NBI). PATIENTS AND METHODS Fifteen endoscopists with no or less M-NBI experience participated in this training, which consisted of four stages and five teaching methods (M-NBI classification criterion, case analysis, hands-on operation, error correction and SESCC pathological knowledge). M-NBI images were evaluated and diagnostic accuracy was analyzed. RESULTS After training, the accuracy of distinguishing neoplastic esophageal from non-neoplastic (0.58 ± 0.16 vs. 0.95 ± 0.05, P = 0.000) and diagnosing SESCC staging (0.25 ± 0.26 vs. 0.89 ± 0.08, P = 0.000) with M-NBI were significantly increased. Participants with no M-NBI experience achieve equivalent diagnostic accuracy with less experienced trainees after the training (0.91 ± 0.08 vs. 0.92 ± 0.04, P = 0.816). Besides, diagnosis of MM (muscularis mucosa)/SM1 (submucosal) staging tumors (Stage I, 0.47 ± 0.15; Stage II-III-IV, 0.76 ± 0.12) with M-NBI was difficult for trainees and should be the focus of this training. Every teaching method could improve the diagnostic accuracy for esophageal lesions, especially for case analysis (from 0.59 ± 0.10 to 0.85 ± 0.08, P = 0.000). In addition, the average operation score for trainees was significantly increased after hands-on teaching (60.40 ± 11.11 vs. 91.80 ± 4.28, P = 0.0001). CONCLUSIONS For novices, this training system showed efficient performance for diagnosing SESCC staging with M-NBI. Diagnosing MM/SM1 staging SESCC was difficult for beginners, and should be the focus of training.

Background Pit pattern classification using magnifying chromoendoscopy is the established method for diagnosing colorectal lesions. The Japan Narrow-band-imaging (NBI) Expert Team (JNET) classification is a novel NBI magnifying endoscopic classification that focuses on the vessel, and surface patterns. Aim To determine the diagnostic efficacy of each category of the JNET and Pit pattern classifications for colorectal lesions. Methods A systematic literature search was performed using PubMed, Embase, the Cochrane Library, and Web of Science databases. The pooled sensitivity, specificity, diagnostic odds ratio, and area under the summary receiver operating characteristic curve of each category of the JNET and Pit pattern classifications were calculated. Results A total of 19227 colorectal lesions in 31 studies were included. The diagnostic performance of the JNET classification was equivalent to the Pit pattern classification in each corresponding category. The pooled sensitivity, specificity, and area under the curve (AUC) for each category of the JNET classification were as follows: 0.73 (95%CI: 0.55-0.85), 0.99 (95%CI: 0.97-1.00), and 0.97 (95%CI: 0.95-0.98), respectively, for Type 1; 0.88 (95%CI: 0.78-0.94), 0.72 (95%CI: 0.64-0.79), and 0.84 (95%CI: 0.81-0.87), respectively, for Type 2A; 0.56 (95%CI: 0.47-0.64), 0.91 (95%CI: 0.79-0.96), and 0.72 (95%CI: 0.68-0.76), respectively, for Type 2B; 0.51 (95%CI: 0.42-0.61), 1.00 (95%CI: 1.00-1.00), and 0.90 (95%CI: 0.87-0.93), respectively, for Type 3. Conclusion This meta-analysis suggests that the diagnostic efficacy of the JNET classification may be equivalent to that of the Pit pattern classification. However, due to its simpler and clearer clinical application, the JNET classification should be promoted for the classification of colorectal lesions, and to guide the treatment strategy.

Background and Aims Endoscopy guidelines recommend adhering to policies such as resect and discard only if the optical biopsy is accurate. However, accuracy in predicting histology can vary greatly. Computer-aided diagnosis (CAD) for characterization of colorectal lesions may help with this issue. In this study, CAD software developed at the University of Adelaide (Australia) that includes serrated polyp differentiation was validated with Japanese images on narrow-band imaging (NBI) and blue-laser imaging (BLI). Methods CAD software developed using machine learning and densely connected convolutional neural networks was modeled with NBI colorectal lesion images (Olympus 190 series - Australia) and validated for NBI (Olympus 290 series) and BLI (Fujifilm 700 series) with Japanese datasets. All images were correlated with histology according to the modified Sano classification. The CAD software was trained with Australian NBI images and tested with separate sets of images from Australia (NBI) and Japan (NBI and BLI). Results An Australian dataset of 1235 polyp images was used as training, testing, and internal validation sets. A Japanese dataset of 20 polyp images on NBI and 49 polyp images on BLI was used as external validation sets. The CAD software had a mean area under the curve (AUC) of 94.3% for the internal set and 84.5% and 90.3% for the external sets (NBI and BLI, respectively). Conclusions The CAD achieved AUCs comparable with experts and similar results with NBI and BLI. Accurate CAD prediction was achievable, even when the predicted endoscopy imaging technology was not part of the training set.

Background and Aims Narrow-band imaging (NBI) is currently regarded as the standard modality for diagnosing esophageal squamous cell carcinoma (SCC). We developed a computerized image-analysis system for diagnosing esophageal SCC by NBI and estimated its performance with video images. Methods Altogether, 23,746 images from 1544 pathologically proven superficial esophageal SCCs and 4587 images from 458 noncancerous and normal tissue were used to construct an artificial intelligence (AI) system. Five- to 9-second video clips from 144 patients captured by NBI or blue-light imaging were used as the validation dataset. These video images were diagnosed by the AI system and 13 board-certified specialists (experts). Results The diagnostic process was divided into 2 parts: detection (identify suspicious lesions) and characterization (differentiate cancer from noncancer). The sensitivities, specificities, and accuracies for the detection of SCC were, respectively, 91%, 51%, and 63% for the AI system and 79%, 72%, and 75% for the experts. The sensitivity of the AI system was significantly higher than that of the experts, but its specificity was significantly lower. Sensitivities, specificities, and accuracy for the characterization of SCC were, respectively, 86%, 89%, and 88% for the AI system and 74%, 76%, and 75% for the experts. The receiver operating characteristic curve showed that the AI system had significantly better diagnostic performance than the experts. Conclusions Our AI system showed significantly higher sensitivity for detecting SCC and higher accuracy for characterizing SCC from noncancerous tissue than endoscopic experts.

A sessile-serrated adenoma (SSA) has a high risk for incomplete resection. Little is known regarding how to immediately detect remnant SSA tissue after endoscopic resection. We investigated the usefulness of narrow-band imaging (NBI) to detect remnant SSA tissue after endoscopic mucosal resection (EMR). We performed a prospective randomized study on 138 patients who had suspicious SSA on colonoscopy at five centers. After EMR on the suspected SSA determined on the endoscopic morphology, all lesions were randomized into two inspection methods, NBI and white light endoscopy (WLE), to detect remnant tissue on the resected margin. If remnant tissue was detected, an additional resection was performed. Finally, we obtained quadrant biopsies on the resection margin to evaluate the incomplete resection. The proportion of incomplete resection was calculated by combining the detection of remnant tissue and the positivity of SSA cells on the final quadrant biopsies. The primary outcome was the proportion of remnant tissue detection, and the secondary outcome was the proportion of incomplete resection of SSA. In all, 145 lesions from 138 patients were removed. The diagnostic rate of SSA was 87.6% (127/145). After randomization, NBI inspection was performed on 69 lesions, and WLE inspection was performed on 76 lesions. The histologic diagnostic rate of SSA was 89.9% (62/69) in the NBI group and 85.5% (65/76) in the WLE group (p > 0.05). There were no significant differences in the detection of remnant tissue (12.9% (8/62) vs. 15.4% (10/65), p > 0.05), the proportion of SSA in remnant tissue (11.3% (7/62) vs. 12.3% (8/65), p > 0.05), or the proportion of incomplete resection (6.5 (4/62) vs. 10.8 (7/65), p > 0.05) between the NBI and WLE inspection groups, respectively. NBI was not superior to WLE for detecting remnant SSA tissue after EMR and could not decrease the proportion of incomplete resection of SSA.

This systematic review and meta-analysis evaluates the validity of narrowband imaging (NBI) in differentiating between low-risk leukoplakia and high-risk leukoplakia. Medline, EMBASE, Scopus, Cochrane Database of Systematic Reviews and Database of Abstracts of Reviews of Effects were searched. Studies evaluating the diagnostic accuracy of NBI in the assessment of laryngeal leukoplakia were included. Pooled sensitivity, specificity and diagnostic odds ratio were calculated. Seven studies met the inclusion criteria assessing a total of 586 lesions with laryngeal leukoplakia. In differentiating between low-risk and high-risk leukoplakia, NBI had a pooled sensitivity and specificity of 85.4% (95% CI [76-99.9]) and 94.9% (95% CI [91.1-97.2]) respectively. Pooled diagnostic odds ratio was 99.2 (95% CI [38.28-257.18]). NBI is a useful imaging modality in differentiating between low-risk leukoplakia and high-risk laryngeal leukoplakia. The high sensitivity, specificity and diagnostic odds ratio make NBI a useful tool in the workup of laryngeal leukoplakia.

Sessile serrated lesion (SSL) is a colorectal polyp that has malignant potential. However, the dysplastic components within an SSL can be difficult to diagnose with conventional endoscopy, because most SSLs with dysplasia/carcinoma have subtle mucosal features. Many studies have indicated that narrow-band imaging (NBI) observations of colorectal polyps are very useful, accurate predictors of histology. We aimed to verify the usefulness of the Japan NBI Expert Team (JNET) classification system for the diagnosis of SSLs with dysplasia/carcinoma. We examined 709 endoscopically or surgically resected lesions that were pathologically diagnosed as SSL, including 647 with no dysplasia, 37 with low-grade dysplasia, 15 with high-grade dysplasia, and 10 with submucosal invasive carcinoma. We retrospectively evaluated their clinicopathologic characteristics and conventional endoscopic and magnifying NBI endoscopic findings using the JNET system. Cases in all groups were more frequently located in the proximal colon. Submucosal invasive carcinomas were significantly larger than no dysplasia and low-grade dysplasia lesions. Almost all studied lesions (96.3%) were covered with a mucus cap. Five hundred and eighty (81.8%) lesions exhibited dark spots inside the crypts, which are NBI findings’ characteristic of SSL. As for the JNET classification of magnifying NBI endoscopic findings, all 709 lesions showed Type 1. Six hundred and eighteen (95.5%) SSLs with no dysplasia lesions exhibited Type 1 only, whereas 52 (83.9%) SSLs with dysplasia/carcinoma had a combination of Type 1 and Type 2A, 2B, or 3, corresponding to SSL and dysplasia/carcinoma, respectively. The JNET classification had high sensitivity (83.9%), specificity (95.5%), and overall diagnostic accuracy (94.5%) for diagnosing SSLs with dysplasia/carcinoma. Use of magnifying NBI endoscopy with the JNET classification might be useful for diagnosing SSLs with dysplasia/carcinoma. This increased awareness may also improve the recognition of SSLs with dysplasia/carcinoma.