Magnifying Endoscopy Research Articles

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.

Real-time assessment of video images for esophageal squamous cell carcinoma invasion depth using artificial intelligence.

Although optimal treatment of superficial esophageal squamous cell carcinoma (SCC) requires accurate evaluation of cancer invasion depth, the current process is rather subjective and may vary by observer. We, therefore, aimed to develop an AI system to calculate cancer invasion depth. We gathered and selected 23,977 images (6857 WLI and 17,120 NBI/BLI images) of pathologically proven superficial esophageal SCC from endoscopic videos and still images of superficial esophageal SCC taken in our facility, to use as a learning dataset. We annotated the images with information [such as magnified endoscopy (ME) or non-ME, pEP-LPM, pMM, pSM1, and pSM2-3 cancers] based on pathologic diagnosis of the resected specimens. We created a model using a convolutional neural network. Performance of the AI system was compared with that of invited experts who used the same validation video set, independent of the learning dataset. Accuracy, sensitivity, and specificity with non-magnified endoscopy (ME) were 87%, 50%, and 99% for the AI system and 85%, 45%, 97% for the experts. Accuracy, sensitivity, and specificity with ME were 89%, 71%, and 95% for the AI system and 84%, 42%, 97% for the experts. Most diagnostic parameters were higher when done by the AI system than by the experts. These results suggest that our AI system could potentially provide useful support during endoscopies.

A Prospective Study of Factors Associated with Abdominal Pain in Patients during Unsedated Colonoscopy Using a Magnifying Endoscope.

Objective With the advent of endoscopic treatment, the detailed diagnosis of colorectal neoplasms made using magnifying colonoscopy has become increasingly important. However, insertion difficulty causes pain in unsedated colonoscopy. The aim of this prospective observational study was to clarify the factors associated with a patient's pain in unsedated colonoscopy using a magnifying endoscope. Methods Patient pain was assessed using a numerical rating scale (0-10) immediately after the procedure. We defined 5 as mild enough pain that patients would not be reluctant to undergo another colonoscopy. Acceptable pain was defined as 5 or less and severe pain was defined as 8 to 10. Univariate and multivariate linear regression analyses were performed using the pain scale score as a dependent variable. Results A total of consecutive 600 patients undergoing unsedated colonoscopies were evaluated to assess their abdominal pain. The completion rate was 99.5% (597/600). The mean pain scale score was 3.88±2.38. The rate of acceptable pain was 80.5% (483/600). The rate of severe pain was 6.7% (40/600) including the incomplete cases. A comparison of polyp-positive and polyp-negative cases revealed no marked difference in patient pain (3.82±2.24 vs. 3.94±2.49, respectively; p=0.590) or insertion time (6.62±3.98 vs. 6.29±4.21, p=0.090), while more observation time was needed in polyp-positive cases than in polyp-negative ones (16.30±4.95 vs. 13.08±4.69, p<0.01). Univariate and multivariate linear regression analyses revealed that an older age, colectomy, antispasmodic agent use, and a small-diameter endoscope were significant factors associated with less patient pain. In particular, a small-diameter endoscope induces significantly more acceptable pain than a non-small diameter endoscope [85.63% (274/320) vs. 73.93% (207/280), p=0.00003]. Conclusion Unsedated colonoscopy using a magnifying endoscope by an expert may result in acceptable pain levels. The use of an antispasmodic agent, particularly hyoscine N-butyl bromide, and a small-diameter endoscope are recommended for reducing abdominal pain during unsedated colonoscopy.

Efficacy and Feasibility of Magnifying Blue Laser Imaging without Biopsy Confirmation for the Diagnosis of the Demarcation of Gastric Tumors: A Randomized Controlled Study

Background: Accurate diagnosis of the demarcation line (DL) of gastric tumors is essential for curative complete resection by endoscopic submucosal dissection (ESD). It is controversial to perform only magnifying endoscopy for diagnosing the DL of gastric tumors prior to ESD. This study aimed to evaluate the diagnostic accuracy for the DL of gastric adenomas and well-differentiated adenocarcinomas using only magnifying blue laser imaging (M-BLI) compared with that using both M-BLI and biopsy confirmation. Methods: In this prospective, single-center study, 96 well-differentiated adenocarcinomas and 32 gastric adenomas were enrolled between July 2015 and December 2016. A total of 122 lesions with a clear DL on M-BLI were randomly allocated to undergo M-BLI only (the M-BLI group) or M-BLI with biopsy confirmation (the M-BLI-BC group), performed as biopsies in 4 directions from noncancerous tissues ≈ 5 mm outside the lesion before ESD. The primary end point was to clarify the noninferiority of M-BLI without biopsy confirmation compared with that with biopsy confirmation, in terms of the diagnostic accuracy and complete resection. Results: There were no significant differences in sex, median age, color, circumference, macroscopic type, biopsy-based diagnosis, and Helicobacter pylori infection between the 2 groups. The diagnostic accuracy for the DL was 100 and 95.0% and the complete resection was 100 and 100% in the M-BLI and M-BLI-BC groups, respectively. Conclusion: The diagnostic ability of M-BLI is excellent in diagnosing the demarcation of gastric adenoma and well-differentiated adenocarcinoma. Biopsy confirmation is not needed for these lesions with a clear DL by M-BLI.

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.

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 AimMagnifying 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.MethodsThe 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.ResultsThe 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.ConclusionsThe 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.

Esophageal anisakiasis observed using magnifying endoscopy with narrow-band imaging.

Esophageal anisakiasis observed using magnifying endoscopy with narrow-band imaging.

Recurrent laryngeal nerve management in transoral endoscopic thyroidectomy.

The mechanism of recurrent laryngeal nerve (RLN) injury was investigated during a TransOral Endoscopic Thyroidectomy Vestibular Approach (TOETVA). The function of 185 nerves at risk (NAR) was recorded with intermitted intraoperative neural monitoring (I-IONM). The RLN electromyography (EMG) was delineated during: (a) a pre-dissection vagal nerve stimulation; (b) a RLN stimulation at initial visualization; (c) at nerve dissection; and (d) at the final verification of the entire RLN route. The location, genesis, segmental or diffuse and the outcomes of RLN injuries were catalogued. Twelve nerves (6.4%) lost the EMG signal and the incidences of temporary and permanent RLN dysfunction were 5.9% and 0.5%. A disrupted point (type 1 injury) could be identified in 7/12 nerves (58%). Five (42%) nerve injuries were classified as global (type 2). Of the seven type 1 injuries, 3 lesions occurred at the RLN laryngeal entry point during the nerve identification. Four type 1 injuries were at the distal 1cm of the RLN course and during the early nerve dissection. No proximal (>2cm) injuries occurred. The mechanisms of the injuries were thermal (58%) during the energy-based device use at the ligament of Berry dissection or at the dividing small branches of the inferior thyroid artery. Two (16%) traction injuries occurred during the early nerve dissection. In 2 cases we could not elucidate the mechanism of RLN injury (16%) and 1 injury (8%) was caused by the connective tissue constricting band of. The thermal RLN lesions had longer recovery times. The RLN palsy occurs in TOETVA, even when combined with an endoscopic magnification, IONM, early nerve identification, cranial to caudal dissection and top-down view. The thermal RLN injury was the most frequent cause and all injuries occurred at the distal RLN course.

Tu1514 ANALYSIS OF METACHRONOUS GASTRIC CANCER AFTER ENDOSCOPIC SUBMUCOSAL DISSECTION FOR EARLY GASTRIC CANER

Progression of endoscopic diagnosis contributes improvement of detecting early gastric cancer (EGC). Endoscopic resection like endoscopic submucosal dissection (ESD) achieves surefire treatment of EGC. Now metachronous gastric cancer (MGC) after ESD becomes a problem. We analyzed the patients who had MGC after ESD to clarify the feature of MGC. We conducted retrospective analysis of EGC cases resected by ESD in our institution. From April 2014 through August 2019, 393 patients were performed ESD and 38 cases (9.7%) were MGC including 10 synchronous (within 1 year after ESD). We analyzed age, sex, interval of recurrence, location, macroscopic type, histological type, size of tumor, depth of invasion, history of eradication of Helicobacter Pylori (HP), detecting method and curative ratio by ESD. The study was approved by IRB. The outcomes were as follows: MGC including synchronous was 9.7% (38/393) during this surveillance. Sex: male/female ratio was 35/3. Average age: 74.0±4.7 years old (61-86, median 74). Average interval of recurrence: 45.7±41.6 months (2-168, median 33.5). 68% (26/38) of cases experienced a recurrence within 5 years after previous ESD. The maximum recurrence was 3 times. Location: Upper 19, Middle 4, Lower 15. 76% (29/38) of cases arose from different location from the previous one. Macroscopic type: 0-IIa 12, 0-IIb 4, 0-IIc 22. 42% of cases were same type as previous one. Histological type: 37 tubular adenocarcinoma and 1 poorly differentiated adenocarcinoma. Average size: 11.4±7.8 mm (1.5-37, median 10). Depth of invasion: M 36, SM 2. History of eradication of HP: 53% (20/38). In those cases, the longest interval of recurrence was 12 years and the shortest one was 2 years. Detecting method: white-light imaging 74%, indigo carmine dye 26%. Narrow-band imaging (NBI) or magnifying endoscopy with NBI was not used at the first detection of EGC. Curative ratio by ESD: 97% (37/38). Almost cases were less than 30mm tubular adenocarcinoma existed in mucosal layer, therefore, they were curative. Just one case (por, SM1) was not curative by ESD. In our analysis, MGC after ESD was 9.7%. The majority of cases were curative by ESD. 53% of cases had history of eradication of HP. They had severe atrophic gastritis and metaplasia. Even after eradication of HP, the patients performed ESD for EGC also still need continuous periodic endoscopic examination. To make sure effectivity of eradication of HP after ESD for EGC, additional prospective analysis is necessary.

Application of titanium clip marking in localization of 37 cases of rectal cancer before radiotherapy

AbstractObjectivesAt present, locating radiotherapy targets for rectal cancer is mostly assisted by computed tomography (CT) and/or magnetic resonance (MR) imaging. This article discusses the role of the upper and lower margins of rectal cancer lesions under colonoscopy in accurately delineating target areas of radiotherapy.MethodsA total of 37 patients with rectal cancer diagnosed by histopathology at the Shandong Provincial Cancer Hospital, affiliated with Shandong University, from 1 July 2017 to 1 August 2018 were selected before treatment. The upper and lower margins of the lesion were marked by titanium clips under the assistance of ultrasound and a magnifying endoscope in each patient, as well as the lower edge of the titanium clip from the anal margin. In the same position and in a thermal plastic membrane body fixation device, patients underwent CT and MR examinations to outline the gross tumor target area (GTV). The radiation therapy planning system calculated the length of the GTV under CT and MR (GTVCT, GTVMR), and the distance from the lower edge of the GTV to the anal margin. The application value of titanium clip labeling by colonoscopy in radiotherapy localization for rectal cancer was evaluated according to differences of GTV lengths by three methods.ResultsGTVs measured by endoscopic titanium clip labeling, CT localization, and MR localization were 5.84 ± 2.035 cm,6.97 ± 1.658 cm, and 5.45 ± 2.088 cm, respectively. The length of GTVtitanium clip was not significantly different from the length of GTVMR (P = 0.162). The marked lesion lengths by the endoscopic titanium clips and MR localization were significantly smaller than that measured by CT (GTV titanium clip &lt; GTVCT, GTVMR &lt; GTVCT, P &lt; 0.001). The distance between the lower margin of the titanium clip and the anal margin (4.19 ± 1.647 cm) was not significantly different from MR (4.41 ± 1.624 cm; P = 0.231). The distance from the inferior margin of the lesion to the anal margin was significantly greater in measurements from the endoscopic titanium clip and MR localization than CT localization (3.53 ± 1.394 cm; P &lt; 0.001). None of the patients had adverse reactions, such as bleeding or perforation.ConclusionsTumors labeled with titanium clips through colonoscopy contribute to the precise delineation of the target area before radiotherapy for rectal cancer. This technique is shown to have value in clinical application.

Magnifying endoscopy with narrow-band image for diagnosing diffuse type of gastric antral vascular ectasia in cirrhotic patients.

Gastric antral vascular ectasia (GAVE) and portal hypertensive gastropathy (PHG) can cause gastrointestinal bleeding in cirrhotic patients. Distinguishing diffuse-type GAVE and severe PHG is important but difficult by conventional endoscopy and endoscopic biopsy. The aim of this study is to evaluate the value of magnifying endoscopy with narrow-band image for diagnosing diffuse-type GAVE in cirrhotic patients. From January 2010 to December 2013, cirrhotic patients with diffuse red spots of stomach in suspicion of diffuse-type GAVE on conventional endoscopy in a tertiary medical center were included. The detection of diffuse red spots on magnifying endoscopy with narrow-band image (NBI) was classified into ring-pattern which suggested GAVE and mosaic-pattern which suggested non-GAVE. The golden diagnosis of GAVE was based on histological criteria of GAVE score ≥3 by any one of two endoscopic sessions. Total 27 cirrhotic patients were included. Twenty-two patients reached the diagnosis of GAVE and five patients were diagnosed of non-GAVE by histology. The diagnostic rate of conventional endoscopy was 81.5% (22/27). The positive rate of initial endoscopic biopsy was 77.2%. On magnifying endoscopy with NBI, the sensitivity, specificity, positive, negative predicted rate and accuracy of ring-pattern for the diagnosis of GAVE were 100, 90, 96.4, 100 and 97.3%. Kappa coefficient of inter-observer agreement for differentiating the ring and mosaic-pattern was 0.92. The efficacy and accuracy of magnifying endoscopy with NBI for diagnosing diffuse-type GAVE in cirrhotic patients have been demonstrated. It can avoid repeated endoscopy to confirm diagnosis and obviate the invasive biopsy in cirrhotic patients.

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

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. 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. 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. 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.

Barrett Esophagus - Update of clinical management and therapy options

Adenocarcinomas of the esophagus are very similar to those of the stomach and most likely develop in the gastric cardia, from where proliferating cells expand into the esophagus and form benign Barrett's mucosa. An additional genomic instability leads to the clonal evolution of certain cells, which can lead to the development of adenocarcinoma. A clear definition of factors is urgently needed for better risk stratification and the establishment of preventive strategies. Current prediction models, which include overweight, diet or tobacco consumption, have not yet been able to establish themselves in clinical application. Current guidelines exist for diagnostics and monitoring. The diagnosis of Barrett's esophagus is performed histopathologically from 4-quadrant biopsies. In addition, macroscopically conspicuous areas of the Barrett mucosa should be biopsies. The detection of neoplastic areas can be improved by using chromoendoscopy in combination with magnification endoscopy and staining techniques (methylene blue or acetic acid). The curatively intended endoscopic resection is the standard therapy for dysplastic Barrett's metaplasia, mucosal (T1a m) and superficial submucosal (T1a sm1) adenocarcinoma. Here, cap and ligature resection as well as endoscopic submucosal dissection (ESD) represent the recommended resection techniques and, in combination with radiofrequency ablation, the therapy according to guidelines.

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)

Magnification endoscopy in combination with acetic acid enhancement and narrow-band imaging for the accurate diagnosis of colonic neoplasms.

Background and study aims Magnification endoscopy with narrow-band imaging (NBIME) and NBIME with acetic acid enhancement (A-NBIME) enable visualization of the vascular and microstructural patterns of colorectal polyp. We compared the diagnostic accuracy and reproducibility of white light endoscopy (WLE), NBIME, and A-NBIME for predictive histologic diagnosis. Patients and methods Consecutive colorectal polyps (N = 628; 38 hyperplasias, 488 adenomas, 72 M-SM1 cancers, and 30 SM2 cancers) were photographed with WLE, NBIME, and A-NBIME. Endoscopic images were independently reviewed by three experts, according to the traditional criteria for WLE, the Japan NBI Expert Team classification for NBIME, and pit pattern classification for A-NBIME to compare diagnostic accuracy and interobserver diagnostic agreement among modalities. Results The specificity (95 % confidence interval) of hyperplasia and SM2 cancer with WLE were 98.2 % (96.8 %–99.1%) and 99.4 % (98.5 %–99.9 %), respectively, showing high accuracy for endoscopic resection without magnifying observation. Diagnostic accuracy of WLE, NBIME, and A-NBIME was 80.8 % (77.4 %–83.8 %), 79.3 % (75.9 %–82.4 %), and 86.1 % (83.2 %–88.7 %), respectively, showing the highest accuracy for A-NBIME among modalities ( P < .05). NBIME showed a lower PPV for M-SM1 cancer ( P < .05), as with WLE ( P = .08) compared to A-NBIME. Fleiss’s kappa values for WLE, NBIME, and A-NBIME diagnosis were 0.43 (0.39 – 0.46), 0.52 (0.49 – 0.56) and 0.65 (0.62 – 0.69), respectively, showing insufficient reproducibility of WLE and superiority of A-NBIME among modalities. Conclusion WLE showed high accuracy for endoscopic resection of colorectal polyps in expert diagnosis. NBIME demonstrated a higher diagnostic reproducibility than WLE. A-NBIME showed possible superiority among modalities in both diagnostic accuracy and reproducibility.

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

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

Irregularly branched microvessels as visualized by magnifying endoscopy: a reliable marker for predicting deep submucosal invasion of superficial esophageal squamous cell carcinoma.

Background and study aims Magnifying endoscopy with narrow-band imaging (M-NBI) is reported to be useful in diagnosing invasion depth of superficial esophageal squamous cell carcinoma (SCC), but accurate diagnosis of deep submucosal invasion (SM2) has remained difficult. However, we discovered that irregularly branched microvessels observed with M-NBI are detected in SM2 cancers with high prevalence. Thus, this retrospective study aimed to investigate the diagnostic performance of irregularly branched microvessels as visualized by M-NBI for predicting SM2 cancers. Patients and methods Patients with superficial esophageal SCC lesions that were endoscopically or surgically resected at our hospital between September 2005 and December 2014 were included. Endoscopic findings by M-NBI of these lesions were presented to an experienced endoscopist who was unaware of the histopathological diagnosis and who then judged whether irregularly branched microvessels were present. Using the invasion depth according to postoperative histopathological diagnosis as the gold standard, we determined the diagnostic performance of the presence of irregularly branched microvessels as an indicator for SM2 cancers. Results A total of 302 superficial esophageal SCC lesions (228 patients) were included in the analysis. When irregularly branched microvessels were used as an indicator of SM2 cancers, the diagnostic accuracy was 94.0 % (95 % confidence interval [CI]: 91.1–96.1 %), sensitivity was 79.4 % (95 % CI: 66.6–88.4 %), specificity was 95.9 % (95 % CI: 94.3–97.0 %), positive predictive value was 71.1 % (95 % CI: 59.6–79.1 %), and negative predictive value was 97.3 % (95% CI: 95.7–98.5 %). Conclusions Irregularly branched microvessels may be a reliable M-NBI indicator for the diagnosis of cancers with deep submucosal invasion.

Endoscopic acanthosis nigricans appearance: A novel specific marker for diagnosis of low-grade intraepithelial neoplasia.

At present, there is no recognized diagnostic criteria for gastric low-grade intraepithelial neoplasia (LGIN). The purpose of this study was to determine whether an "endoscopic acanthosis nigricans appearance (EANA)" could be a useful endoscopic marker for distinguishing LGIN lesions from peripheral non-neoplastic tissues. A retrospective study was conducted on 638 cases of suspected superficial lesions with endoscopic images from white light endoscopy and magnifying endoscopy combined with narrow band imaging. According to the pathological results of accurate biopsies, those lesions were divided into three groups: a control group, an LGIN group, and an early gastric cancer (EGC) group. According to the presence of EANAs, the sensitivity, specificity, positive predictive value, and negative predictive value for differentiating between the LGIN and control groups were 24.8%, 97.3%, 78.3%, and 76.6%, respectively. The sensitivity (84.1%) and negative predictive value (92.4%) were significantly improved by combining EANA with types IV-VI pit pattern. The intervening part and mean gray value of glands, representing microsurface features and microvascular variation, were significantly larger or higher in EANA lesions than in the surrounding non-neoplastic mucosa. LGIN with EANA was more likely to be present in lesions of type 0-IIa. In addition, the prevalence of EANAs in EGC was 16.7%. An EANA could be used as an auxiliary indicator for a diagnosis of LGIN in suspected lesions. It could also play a potential assistive role in the diagnosis of EGC lesions.

Recent advances in diagnostic upper endoscopy.

BACKGROUNDEsophageo-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.AIMTo identify recent advances in diagnostic EGDs to improve diagnostic yield.METHODSWe 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.RESULTSWe 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.CONCLUSIONThere 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.

Analysis of endoscopic submucosal dissection training system construction

Objective To investigate the prerequisites for endoscopists, who were chosen to receive endoscopic submucosal dissection (ESD) training. Methods A total of 41 trainees, who attended ESD training in the endoscopic center of Nanjing Drum Tower Hospital from January 2017 to June 2018 were enrolled in the study. The general information of the subjects were collected, including name, age, gender, the number of gastroscopy and colonoscopy independently performed before training, the independent usage of narrow band image (NBI), magnifying endoscopy (ME), endoscopic mucosal resection (EMR), ESD, endoscopic ultrasonography (EUS), and endoscopic retrograde cholangiopancreatography (ERCP) before training. And then every trainee independently finished four in vitro experiments of pig esophagus ESD. The specimen area and operating time were recorded, and the operating speed was calculated. Linear regression analysis was used to analyze the affecting factors of operating speed of ESD. Results Among the 41 trainees, 26 were male and 15 were female, with age of 36.07±4.44 years. The specimen area, operating time and operating speed of pig esophagus ESD was 4.67±1.61 cm2, 24.54±5.97 min, and 0.19±0.05 cm2/min, respectively. Univariate linear regression analysis showed that the number of gastroscopy (n>5 000, P=0.001 8) and colonoscopy (n>3 000, P=0.000 1), the detect number of early cancer in upper digestive tract (n>30, P=0.000 3) and lower digestive tract (n>10, P=0.019 7), and the usage of ME (P=0.047 8), EMR (P=0.019 6) and ESD (P=0.000 3) before training were statistically correlated with the operating speed of ESD. Carrying out NBI (P=0.532 9), ERCP (P=0.500 7) and EUS (P=0.766 8) before training were not statistically correlated with the operating speed of ESD. The operating speed of ESD was negatively correlated with the perforation rate of ESD (P<0.000 1). According to multivariable linear regression model, the usage of EMR (P=0.029) and ESD (P=0.034) were statistically correlated with the operating speed of ESD. Conclusion ESD trainees, who have the number of gastroscopy more than 5 000, the number of colonoscopy more than 3 000, the detect number of early cancer more than 30 in upper digestive tract and 10 in lower digestive tract, and the usage of ME, EMR and ESD before training, can get a better training effect. The study provides a theoretical basis for selecting appropriate ESD trainees. Key words: Animal models; In vitro; Endoscopic submucosal dissection; Operating training; Dissection time