White Light Imaging Endoscopy Research Articles

Enhanced multi-class pathology lesion detection in gastric neoplasms using deep learning-based approach and validation

This study developed a new convolutional neural network model to detect and classify gastric lesions as malignant, premalignant, and benign. We used 10,181 white-light endoscopy images from 2606 patients in an 8:1:1 ratio. Lesions were categorized as early gastric cancer (EGC), advanced gastric cancer (AGC), gastric dysplasia, benign gastric ulcer (BGU), benign polyp, and benign erosion. We assessed the lesion detection and classification model using six-class, cancer versus non-cancer, and neoplasm versus non-neoplasm categories, as well as T-stage estimation in cancer lesions (T1, T2-T4). The lesion detection rate was 95.22% (219/230 patients) on a per-patient basis: 100% for EGC, 97.22% for AGC, 96.49% for dysplasia, 75.00% for BGU, 97.22% for benign polyps, and 80.49% for benign erosion. The six-class category exhibited an accuracy of 73.43%, sensitivity of 80.90%, specificity of 83.32%, positive predictive value (PPV) of 73.68%, and negative predictive value (NPV) of 88.53%. The sensitivity and NPV were 78.62% and 88.57% for the cancer versus non-cancer category, and 83.26% and 89.80% for the neoplasm versus non-neoplasm category, respectively. The T stage estimation model achieved an accuracy of 85.17%, sensitivity of 88.68%, specificity of 79.81%, PPV of 87.04%, and NPV of 82.18%. The novel CNN-based model remarkably detected and classified malignant, premalignant, and benign gastric lesions and accurately estimated gastric cancer T-stages.

Diagnostic performance of deep-learning-based virtual chromoendoscopy in gastric neoplasms.

Cycle-consistent generative adversarial network (CycleGAN) is a deep neural network model that performs image-to-image translations. We generated virtual indigo carmine (IC) chromoendoscopy images of gastric neoplasms using CycleGAN and compared their diagnostic performance with that of white light endoscopy (WLE). WLE and IC images of 176 patients with gastric neoplasms who underwent endoscopic resection were obtained. We used 1,633 images (911 WLE and 722 IC) of 146 cases in the training dataset to develop virtual IC images using CycleGAN. The remaining 30 WLE images were translated into 30 virtual IC images using the trained CycleGAN and used for validation. The lesion borders were evaluated by 118 endoscopists from 22 institutions using the 60 paired virtual IC and WLE images. The lesion area concordance rate and successful whole-lesion diagnosis were compared. The lesion area concordance rate based on the pathological diagnosis in virtual IC was lower than in WLE (44.1% vs. 48.5%, p < 0.01). The successful whole-lesion diagnosis was higher in the virtual IC than in WLE images; however, the difference was insignificant (28.2% vs. 26.4%, p = 0.11). Conversely, subgroup analyses revealed a significantly higher diagnosis in virtual IC than in WLE for depressed morphology (41.9% vs. 36.9%, p = 0.02), differentiated histology (27.6% vs. 24.8%, p = 0.02), smaller lesion size (42.3% vs. 38.3%, p = 0.01), and assessed by expert endoscopists (27.3% vs. 23.6%, p = 0.03). The diagnostic ability of virtual IC was higher for some lesions, but not completely superior to that of WLE. Adjustments are required to improve the imaging system's performance.

The usefulness of image-enhanced endoscopy to distinguish gastric carcinoma in tumors initially diagnosed as adenomas by endoscopic biopsy: A retrospective study.

Superficial epithelial gastric neoplasms can be divided into adenomas and early carcinomas. Histological diagnosis by endoscopic forceps biopsy is crucial for the diagnosis and management of gastric neoplasms. It is difficult to distinguish features of gastric neoplasms in small biopsy specimens; hence, gastric carcinomas can be underdiagnosed as adenomas. Recent developments in image-enhanced endoscopy have improved the ability to differentiate between carcinomatous and non-carcinomatous lesions. To investigate the prevalence of gastric carcinoma in lesions initially diagnosed as adenomas by forceps biopsy and assess the usefulness of image-enhanced endoscopy in distinguishing carcinomas. A total of 142 lesions of gastric adenomas, diagnosed by biopsy and resected endoscopically between January 2010 and May 2020, were retrospectively evaluated. Images were captured by white-light endoscopy (WLE), magnifying endoscopy with narrow-band imaging (M-NBI), and magnifying endoscopy with acetic acid and narrow-band imaging (M-AANBI); they were analyzed and compared with histopathological results. The diagnostic performance of M-AANBI was compared with that of M-NBI. Of the 142 lesions, 58 (40.8%) were pathologically diagnosed as adenocarcinomas. On WLE images, a depressed macroscopic type and size ≥20 mm were significant predictors of carcinoma (P < .001); however, they displayed low sensitivities (32.8% and 41.4%, respectively). M-AANBI displayed significantly higher sensitivity, specificity, and accuracy for distinguishing carcinomas than M-NBI (94.8% vs 74.1%, 81.0% vs 72.6%, and 86.6% vs 73.2%, P < .05). In conclusion, carcinoma was prevalent in 40.8% of gastric lesions initially diagnosed as adenomas by forceps biopsy. M-AANBI may be more useful than M-NBI and WLE in distinguishing gastric carcinomas from adenomas.

A convolutional neural network-based system for detecting early gastric cancer in white-light endoscopy

Background White-light endoscopy (WLE) is a main and standard modality for detection of early gastric cancer (EGC). The detection rate of EGC is not satisfactory so far. In this single-center retrospective study we developed a convolutional neural network (CNN)-based system to automatically detect EGC in WLE images. Methods An EGC detecting system was constructed based on the CNN architecture EfficientDet. We trained our system with a data set including 4527 images from 130 cases (cancerous images, 1737; noncancerous images, 2790). Then we tested its performance with a data set including 1243 images from 64 cases (cancerous images, 445; noncancerous images, 798). Results For case-based analysis, our system successfully detected EGC in 63 of 64 cases and the sensitivity was 98.4%. For image-based analysis, the accuracy was 88.3%. The sensitivity, specificity, positive predictive value and negative predictive value were 84.5%, 90.5%, 83.2% and 91.3%, respectively. The most common cause for false positives was gastritis (57.9%). The most common cause for false negatives was that the lesion was too small with a diameter of 10 mm or less (44.9%). Conclusion Our CNN-based EGC detecting system was able to achieve satisfactory sensitivity for detecting EGC in WLE images and shows great potential in assisting endoscopists with the detection of EGC.

No-Code Platform-Based Deep-Learning Models for Prediction of Colorectal Polyp Histology from White-Light Endoscopy Images: Development and Performance Verification.

Background: The authors previously developed deep-learning models for the prediction of colorectal polyp histology (advanced colorectal cancer, early cancer/high-grade dysplasia, tubular adenoma with or without low-grade dysplasia, or non-neoplasm) from endoscopic images. While the model achieved 67.3% internal-test accuracy and 79.2% external-test accuracy, model development was labour-intensive and required specialised programming expertise. Moreover, the 240-image external-test dataset included only three advanced and eight early cancers, so it was difficult to generalise model performance. These limitations may be mitigated by deep-learning models developed using no-code platforms. Objective: To establish no-code platform-based deep-learning models for the prediction of colorectal polyp histology from white-light endoscopy images and compare their diagnostic performance with traditional models. Methods: The same 3828 endoscopic images used to establish previous models were used to establish new models based on no-code platforms Neuro-T, VLAD, and Create ML-Image Classifier. A prospective multicentre validation study was then conducted using 3818 novel images. The primary outcome was the accuracy of four-category prediction. Results: The model established using Neuro-T achieved the highest internal-test accuracy (75.3%, 95% confidence interval: 71.0–79.6%) and external-test accuracy (80.2%, 76.9–83.5%) but required the longest training time. In contrast, the model established using Create ML-Image Classifier required only 3 min for training and still achieved 72.7% (70.8–74.6%) external-test accuracy. Attention map analysis revealed that the imaging features used by the no-code deep-learning models were similar to those used by endoscopists during visual inspection. Conclusion: No-code deep-learning tools allow for the rapid development of models with high accuracy for predicting colorectal polyp histology.

Linked color imaging improves identification of early gastric cancer lesions by expert and non-expert endoscopists

Background and aimsEarly gastric cancer (EGC) lesions are often subtle and endoscopically poorly visible. The aim of this study is to evaluate the additive effect of linked color imaging (LCI) next to white-light endoscopy (WLE) for identification of EGC, when assessed by expert and non-expert endoscopists.MethodsForty EGC cases were visualized in corresponding WLE and LCI images. Endoscopists evaluated the cases in 3 assessment phases: Phase 1: WLE images only; Phase 2: LCI images only; Phase 3: WLE and LCI images side-to-side. First, 3 expert endoscopists delineated all cases. A high level of agreement between the expert delineations corresponded with a high AND/OR ratio. Subsequently, 62 non-experts indicated their preferred biopsy location. Outcomes of the study are as follows: (1) difference in expert AND/OR ratio; (2) accuracy of biopsy placement by non-expert endoscopists; and (3) preference of imaging modality by non-expert endoscopists.ResultsQuantitative agreement between experts increased significantly when LCI was available (0.58 vs. 0.46, p = 0.007). This increase was more apparent for the more challenging cases (0.21 vs. 0.47, p < 0.001). Non-experts placed the biopsy mark more accurately with LCI (82.3% vs. 87.2%, p < 0.001). Again this increase was more profound for the more challenging cases (70.4% vs. 83.4%, p < 0.001). Non-experts indicated to prefer LCI over WLE.ConclusionThe addition of LCI next to WLE improves visualization of EGC. Experts reach higher consensus on discrimination between neoplasia and inflammation when using LCI. Non-experts improve their targeted biopsy placement with the use of LCI. LCI therefore appears to be a useful tool for identification of EGC.Graphical abstract

Artificial Intelligence for Detecting and Delineating Margins of Early ESCC Under WLI Endoscopy.

INTRODUCTION:Conventional white light imaging (WLI) endoscopy is the most common screening technique used for detecting early esophageal squamous cell carcinoma (ESCC). Nevertheless, it is difficult to detect and delineate margins of early ESCC using WLI endoscopy. This study aimed to develop an artificial intelligence (AI) model to detect and delineate margins of early ESCC under WLI endoscopy.METHODS:A total of 13,083 WLI images from 1,239 patients were used to train and test the AI model. To evaluate the detection performance of the model, 1,479 images and 563 images were used as internal and external validation data sets, respectively. For assessing the delineation performance of the model, 1,114 images and 211 images were used as internal and external validation data sets, respectively. In addition, 216 images were used to compare the delineation performance between the model and endoscopists.RESULTS:The model showed an accuracy of 85.7% and 84.5% in detecting lesions in internal and external validation, respectively. For delineating margins, the model achieved an accuracy of 93.4% and 95.7% in the internal and external validation, respectively, under an overlap ratio of 0.60. The accuracy of the model, senior endoscopists, and expert endoscopists in delineating margins were 98.1%, 78.6%, and 95.3%, respectively. The proposed model achieved similar delineating performance compared with that of expert endoscopists but superior to senior endoscopists.DISCUSSION:We successfully developed an AI model, which can be used to accurately detect early ESCC and delineate the margins of the lesions under WLI endoscopy.

A Novel Deep Learning System for Diagnosing Early Esophageal Squamous Cell Carcinoma: A Multicenter Diagnostic Study.

This study aims to construct a real-time deep convolutional neural networks (DCNNs) system to diagnose early esophageal squamous cell carcinoma (ESCC) with white light imaging endoscopy. A total of 4,002 images from 1,078 patients were used to train and cross-validate the DCNN model for diagnosing early ESCC. The performance of the model was further tested with independent internal and external validation data sets containing 1,033 images from 243 patients. The performance of the model was then compared with endoscopists. The accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and Cohen kappa coefficient were measured to assess performance. The DCNN model had excellent performance in diagnosing early ESCC with a sensitivity of 0.979, a specificity of 0.886, a positive predictive value of 0.777, a negative predictive value of 0.991, and an area under curve of 0.954 in the internal validation data set. The model also depicted a tremendously generalized performance in 2 external data sets and exhibited superior performance compared with endoscopists. The performance of the endoscopists was markedly elevated after referring to the predictions of the DCNN model. An open-accessed website of the DCNN system was established to facilitate associated research. A real-time DCNN system, which was constructed to diagnose early ESCC, showed good performance in validation data sets. However, more prospective validation is needed to understand its true clinical significance in the real world.

Evaluation of Minimal Change Lesions Using Linked Color Imaging in Patients With Nonerosive Reflux Esophagitis.

High prevalence of minimal change lesion (MCL) in nonerosive reflux esophagitis (NERD) patients is commonly recognized by many endoscopists. However, it is difficult to detect MCL with conventional white-light imaging (WLI) endoscopy. Linked color imaging (LCI), a novel image-enhanced endoscopy technology with strong, unique color enhancement, is used for easy recognition of early gastric cancer and detection of Helicobacter pylori infection. The aim of the study was to compare the efficacy of LCI and WLI endoscopy in evaluating MCL in patients with NER. Forty-one patients with NERD and 38 subjects with nongastroesophageal reflux disease (non-GERD) were recruited in this study between August 2017 and July 2018. During upper gastrointestinal endoscopy, the distal 5 cm of the esophageal mucosal morphology at the squamocolumnar junction was visualized using WLI followed by LCI. MCL was defined as areas of erythema, blurring of the Z-line, friability, decreased vascularity, white turbid discoloration, and edema or accentuation of the mucosal folds. Three experienced endoscopists evaluated the color patterns for MCL on WLI images and on WLI combined with LCI images in both groups. A biopsy was taken 2 cm above the esophagogastric junction. Histologic slides were scored by a pathologist in a blinded manner. The proportion of MCL was higher in the patients with NERD (70.7%, 29/41) than in patients with non-GERD (39.5%, 15/38) using WLI combined with LCI. In 12 patients with NERD, both WLI and LCI showed normal mucosa. The MCL detection rate was significantly higher when using WLI combined with LCI than when using WLI (70.7% vs. 51.2%, P=0.039) in patients with NERD. The histopathologic score of MCL (+) was significantly higher than that of MCL (-) patients in both the NERD group (4.59±0.32 vs. 2.36±0.34, P<0.01) and the non-GERD group (3.47±0.50 vs. 2.00±0.28, P<0.01). The intraobserver reproducibility levels and interobserver agreement were better with LCI than with WLI alone. Frequency of MCL was higher in patients with NERD than in those with non-GERD. MCL can be identified by using WLI combined with LCI in patients with NERD. By enhancing endoscopic images, LCI is more sensitive in detecting MCL compared with WLI.

Magnifying endoscopy in detecting early gastric cancer: A network meta-analysis of prospective studies.

Background:Conventional white-light imaging endoscopy (C-WLI) had a significant number of misdiagnosis in early gastric cancer (EGC), and magnifying endoscopy (ME) combined with different optical imaging was more accurate in the diagnosis of EGC. This study aimed to evaluate the accuracy of ME and compare the accuracy of ME with different optical imaging in detecting EGC.Methods:A comprehensive literature search was conducted to identify all relevant studies. Pair-wise meta-analysis was conducted to evaluate the accuracy of ME, and Bayesian network meta-analysis was performed to combine direct and indirect evidence and estimate the relative effects.Results:Eight prospective studies were identified with a total of 5948 patients and 3 optical imaging in ME (ME with WLI (M-WLI), ME with narrow-band imaging (M-NBI), and ME with blue laser imaging (M-BLI)). Pair-wise meta-analysis showed a higher accuracy of ME than C-WLI (OR: 2.97, 95% CI: 1.68∼5.25). In network meta-analysis, both M-NBI and M-BLI were more accurate than M-WLI (OR: 2.56, 95% CI: 2.13∼3.13; OR: 3.13, 95% CI: 1.85∼5.71). There was no significant difference between M-NBI and M-BLI.Conclusion:ME was effective in improving the detecting rate of EGC, especially with NBI or BLI.

Separation of color channels from conventional colonoscopy images improves deep neural network detection of polyps.

.Significance: Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination.Aim: To advance detection and discrimination using currently available commercial colonoscopy systems, we developed a deep neural network (DNN) separating the color channels from images acquired under narrow-band imaging (NBI) and white-light endoscopy (WLE).Approach: Images of normal colon mucosa and polyps from colonoscopies were studied. Each color image was extracted based on the color channel: red/green/blue. A multilayer DNN was trained using one-channel, two-channel, and full-color images. The trained DNN was then tested for performance in detection of polyps.Results: The DNN performed better using full-colored NBI over WLE images in the detection of polyps. Furthermore, the DNN performed better using the two-channel red + green images when compared to full-color WLE images.Conclusions: The separation of color channels from full-color NBI and WLE images taken from commercially available colonoscopes may improve the ability of the DNN to detect and discriminate polyps. Further studies are needed to better determine the color channels and combination of channels to include and exclude in DNN development for clinical use.

Differential diagnosis for esophageal protruded lesions using a deep convolution neural network in endoscopic images

Recent advances in deep convolutional neural networks (CNNs) have led to remarkable results in digestive endoscopy. In this study, we aimed to develop CNN-based models for the differential diagnosis of benign esophageal protruded lesions using endoscopic images acquired during real clinical settings. We retrospectively reviewed the images from 1217 patients who underwent white-light endoscopy (WLE) and EUS between January 2015 and April 2020. Three deep CNN models were developed to accomplish the following tasks: (1) identification of esophageal benign lesions from healthy controls using WLE images; (2) differentiation of 3 subtypes of esophageal protruded lesions (including esophageal leiomyoma [EL], esophageal cyst (EC], and esophageal papilloma [EP]) using WLE images; and (3) discrimination between EL and EC using EUS images. Six endoscopists blinded to the patients' clinical status were enrolled to interpretall images independently. Their diagnostic performances were evaluated and compared with the CNN models using the area under the receiver operating characteristic curve (AUC). For task 1, the CNN model achieved an AUC of 0.751 (95% confidence interval [CI], 0.652-0.850) in identifying benign esophageal lesions. For task 2, the proposed model using WLE images for differentiation of esophageal protruded lesions achieved an AUC of 0.907 (95% CI, 0.835-0.979), 0.897 (95% CI, 0.841-0.953), and 0.868 (95% CI, 0.769-0.968) for EP, EL, and EC, respectively. The CNN model achieved equivalent or higher identification accuracy for EL and EC compared with skilled endoscopists. In the task of discriminating EL from EC (task 3), the proposed CNN model had AUC values of 0.739 (EL, 95% CI, 0.600-0.878) and 0.724 (EC, 95% CI, 0.567-0.881), which outperformed seniors and novices. Attempts to combine the CNN and endoscopist predictions led to significantly improved diagnostic accuracy compared with endoscopists interpretations alone. Our team established CNN-based methodologies to recognize benign esophageal protruded lesions using routinely obtained WLE and EUS images. Preliminary results combining the results from the models and the endoscopists underscored the potential of ensemble models for improved differentiation of lesions in real endoscopic settings.

Diagnostic Value and Pathological Correlation of Narrow Band Imaging Classification in Laryngeal Lesions.

To explore the diagnostic value and pathological correlation of narrow band imaging (NBI) classification in laryngeal lesions. A total of 112 patients (123 lesions) with laryngeal lesions from July 2018 to May 2019 were selected in this study. All patients were examined by NBI and white light imaging endoscopy. The NBI endoscopy was applied to classify the observed lesion sites according to intraepithelial papillary capillary loop pattern. The gold standard of diagnosis was pathological results. To evaluate the consistency of NBI classification and pathological results. The sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis for benign, precancerous, and malignant lesions under the NBI endoscopy were 90.91%, 81.19%, 74.07%, 85.42%; 41.67%, 92.93%, 58.82%, 86.79%; and 93.51%, 65.22%, 91.14%, 68.18%, respectively. There was a high consistency between NBI classification and pathological results (κ = 0.679, P < .001). The NBI classification can improve the accuracy of the diagnosis of laryngeal lesions. It is important for early diagnosis and treatment of vocal cord leukoplakia and laryngeal cancer.

A deep learning method for delineating early gastric cancer resection margin under chromoendoscopy and white light endoscopy.

Accurate delineation of cancer margins is critical for endoscopic curative resection. This study aimed to train and validate real-time fully convolutional networks for delineating the resection margin of early gastric cancer (EGC) under indigo carmine chromoendoscopy (CE) or white light endoscopy (WLE), and evaluated its performance and that of magnifying endoscopy with narrow-band imaging (ME-NBI). We collected CE and WLE images of EGC lesions to train fully convolutional networks ENDOANGEL. ENDOANGEL was tested both on stationary images and endoscopic submucosal dissection (ESD) videos. The accuracy and reliability of ENDOANGEL and NBI-dependent delineation were further evaluated by a novel endoscopy-pathology point-to-point marking. ENDOANGEL had an accuracy of 85.7% in the CE images and 88.9% in the WLE images under an overlap ratio threshold of 0.60 in comparison with the manual markers labeled by the experts. In the ESD videos, the resection margins predicted by ENDOANGEL covered all areas of high-grade intraepithelial neoplasia and cancers. The minimum distance between the margins predicted by ENDOANGEL and the histological cancer boundary was 3.44 ± 1.45mm which outperformed the resection margin based on ME-NBI. ENDOANGEL has the potential to assist endoscopists in delineating the resection extent of EGC under CE or WLE during ESD.

A Deep Learning Method for Delineating Early Gastric Cancer Resection Margins Under Chromoendoscopy or White Light Endoscopy

Background: Accurate delineation of cancer margins is critical for achieving endoscopic curative resection. This study aimed to train and validate real-time fully convolutional networks (FCNs) for delineating the resection margin of early gastric cancer (EGC) under indigo carmine chromoendoscopy (CE) or white light endoscopy (WLE) and evaluated its performance and that of magnifying endoscopy with narrow-band imaging (ME-NBI). Methods: We collected CE/WLE images of EGC lesions to train FCNs named ENDOANGEL. ENDOANGEL was tested both on still images and endoscopic submucosal dissection (ESD) videos and evaluated the performance of ME-NBI based on post-ESD pathology determined using endoscopy–pathology point-to-point marking. Findings: ENDOANGEL had an accuracy of 85·7% in the CE images and 88·9% in the WLE images under an overlap ratio threshold of 0·60 in comparison with the manual makers made by the expert. In the ESD videos, the resection margins predicted by ENDOANGEL covered all areas of high-grade intraepithelial neoplasia and cancer. The minimum distance between the margins predicted by ENDOANGEL and the cancerous boundary confirmed by pathology was 3·44±1·45 mm, outperforming the resection margin based on ME-NBI. Interpretation: ENDOANGEL has the potential to assist endoscopists in delineating the resection extent of EGCs under CE or WLE during ESD. Funding Statement: Project of Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision (grant no. 2018BCC337); Hubei Province Major Science and Technology Innovation Project (grant no. 2018-916-000-008); the National Natural Science Foundation of China [grant no. 81672387 (to Yu Honggang)]; the National Natural Science Foundation of China [grant no. 81302131(to Ping An)]. Declaration of Interests: The authors stated: None. Ethics Approval Statement: The study protocol was approved by the ethics committee of Renmin Hospital of Wuhan University.

Deep learning algorithm detection of Barrett’s neoplasia with high accuracy during live endoscopic procedures: a pilot study (with video)

We assessed the preliminary diagnostic accuracy of a recently developed computer-aided detection (CAD) system for detection of Barrett's neoplasia during live endoscopic procedures. The CAD system was tested during endoscopic procedures in 10 patients with nondysplastic Barrett's esophagus (NDBE) and 10 patients with confirmed Barrett's neoplasia. White-light endoscopy images were obtained at every 2-cm level of the Barrett's segment and immediately analyzed by the CAD system, providing instant feedback to the endoscopist. At every level, 3 images were evaluated by the CAD system. Outcome measures were diagnostic performance of the CAD system per level and per patient, defined as accuracy, sensitivity, and specificity (ground truth was established by expert assessment and corresponding histopathology), and concordance of 3 sequential CAD predictions per level. Accuracy, sensitivity, and specificity of the CAD system in a per-level analyses were 90%, 91%, and 89%, respectively. Nine of 10 neoplastic patients were correctly diagnosed. The single lesion not detected by CAD showed NDBE in the endoscopic resection specimen. In only 1 NDBE patient, the CAD system produced false-positive predictions. In 75% of all levels, the CAD system produced 3 concordant predictions. This is one of the first studies to evaluate a CAD system for Barrett's neoplasia during live endoscopic procedures. The system detected neoplasia with high accuracy, with only a small number of false-positive predictions and with a high concordance rate between separate predictions. The CAD system is thereby ready for testing in larger, multicenter trials. (Clinical trial registration number: NL7544.).

Blue-light imaging and linked-color imaging improve visualization of Barrett’s neoplasia by nonexpert endoscopists

Endoscopic recognition of early Barrett's neoplasia is challenging. Blue-light imaging (BLI) and linked-color imaging (LCI) may assist endoscopists in appreciation of neoplasia. Our aim was to evaluate BLI and LCI for visualization of Barrett's neoplasia in comparison with white-light endoscopy (WLE) alone, when assessed by nonexpert endoscopists. In this web-based assessment, corresponding WLE, BLI, and LCI images of 30 neoplastic Barrett's lesions were delineated by 3 expert endoscopists to establish ground truth. These images were then scored and delineated by 76 nonexpert endoscopists from 3 countries and with different levels of expertise, in 4 separate assessment phases with a washout period of 2 weeks. Assessments were as follows: assessment 1, WLE only; assessment 2, WLE+ BLI; assessment 3, WLE+ LCI; assessment 4, WLE+ BLI+ LCI. The outcomes were (1) appreciation of macroscopic appearance and ability to delineate lesions (visual analog scale [VAS] scores); (2) preferred technique (ordinal scores); and (3) assessors' delineation performance in terms of overlap with expert ground truth. Median VAS scores for phases 2 to 4 were significantly higher than in phase 1 (P< .001). Assessors preferred BLI and LCI over WLE for appreciation of macroscopic appearance (P< .001) and delineation (P<.001). Linear mixed-effect models showed that delineation performance increased significantly in phase4. The use of BLI and LCI has significant additional value for the visualization of Barrett's neoplasia when used by nonexpert endoscopists. Assessors appreciated the addition of BLI and LCI better than the use of WLE alone. Furthermore, this addition led to improved delineation performance, thereby allowing for better acquisition of targeted biopsy samples. (The Netherlands Trial Registry number: NL7541.).

Additional effect of magnifying narrow-band imaging on estimating the invasion depth of superficial esophageal cancer.

Background and AimTo investigate whether assessment by magnifying narrow‐band imaging (M‐NBI) based on the classification of the Japan Esophageal Society provides additional value to the estimation of the invasion depth of superficial esophageal squamous cell carcinoma (SCC) compared with assessment by white light endoscopy (WLE) alone.MethodsEndoscopic images of 211 consecutive superficial esophageal SCCs resected by endoscopic submucosal dissection were separated into WLE and M‐NBI images. Depth estimation was performed independently by five evaluators using the numerical depth estimation scale (0 = epithelium (EP)/lamina propria (LPM), 1 = EP/LPM > muscularis mucosa (MM)/shallow submucosa (SM1), 2 = MM/SM1 > EP/LPM, 3 = MM/SM1, 4 = MM/SM1 > deep submucosa (SM2), 5 = SM2 > MM/SM1, 6 = SM2), using primarily WLE images (step 1), and subsequently both WLE and M‐NBI images (step 2). The discordance scores, determined by the average of the five evaluators' difference between the estimated score (from 0 to 6) and pathological score (0 for histologically proven EP/LPM, 3 for MM/SM1, and 6 for SM2), were analyzed in steps 1 and 2.ResultsThe discordance scores significantly decreased in step 2 (0.53 ± 0.06) compared with those in step 1 (0.79 ± 0.07) (P < 0.001). When the discordance score < 1.5 was regarded as a clinically correct diagnosis, the rate of the clinically correct diagnosis significantly increased in step 2 compared with that in step 1 (81% to 91%, P < 0.001).ConclusionM‐NBI has an additive value for estimating the invasion depth of superficial esophageal SCCs.

The Argos project: The development of a computer-aided detection system to improve detection of Barrett's neoplasia on white light endoscopy.

BackgroundComputer-aided detection (CAD) systems might assist endoscopists in the recognition of Barrett's neoplasia.AimTo develop a CAD system using endoscopic images of Barrett's neoplasia.MethodsWhite light endoscopy (WLE) overview images of 40 neoplastic Barrett's lesions and 20 non-dysplastic Barret's oesophagus (NDBO) patients were prospectively collected. Experts delineated all neoplastic images.The overlap area of at least four delineations was labelled as the ‘sweet spot’. The area with at least one delineation was labelled as the ‘soft spot’. The CAD system was trained on colour and texture features. Positive features were taken from the sweet spot and negative features from NDBO images. Performance was evaluated using leave-one-out cross-validation. Outcome parameters were diagnostic accuracy of the CAD system per image, and localization of the expert soft spot by CAD delineation (localization score) and its indication of preferred biopsy location (red-flag indication score).ResultsAccuracy, sensitivity and specificity for detection were 92, 95 and 85%, respectively. The system localized and red-flagged the soft spot in 100 and 90%, respectively.ConclusionThis uniquely trained and validated CAD system detected and localized early Barrett's neoplasia on WLE images with high accuracy. This is an important step towards real-time automated detection of Barrett's neoplasia.

Effect of narrow-band imaging (NBI) combined with magnifying endoscopy in early diagnosis of gastric cancer

Objective To explore the effect of narrow-band imaging (NBI) combined with magnifying endoscopy (ME) in early diagnosis of gastric cancer, and to observe whether it is helpful for inexperienced endoscopists to diagnose. Methods From April 2015 to October 2017, a total of 480 lesions were selected as research objects which were detected in the normal white light endoscopy (WLE). Pathological examination was used as the gold standard for diagnosis. 3 experienced doctors were selected to read the endoscopy films. 40 intern endoscopy doctors were selected to read the endoscopy filins at the same time after simple training. 80 WLE images and narrowband imaging technology combined with magnifying endoscopy (ME-NBI) images were randomly selected to hold a film reading meeting. Real-time voting was used to judge the nature of lesions. Results The accuracy, sensitivity, specificity false positive rate and false negative rate of ME-NBI were 97.9%(470/480), 96.8%(120/124), 98.3%(350/356), 1.7%(6/356), 3.2%(4/124). And WLE values were 91.7%(440/480), 80.6%(100/124), 89.9%(320/356), 10.1%(36/356), 19.4%(24/124), respectively. The diagnostic accuracy, sensitivity and specificity of ME-NBI were significantly higher than those of WLE (χ2=18.989, 16.104, 15.859, P<0.05), and the false positive rate and false negative rate were significantly lower than those of WLE (χ2=22.772, 16.104, P<0.05). The diagnostic results of ME-NBI of 40 endoscopy interns were significantly better than those of WLE (t=11.467, 16.188, P<0.05). The diagnostic results of NBI by 40 interns were significantly better than that of WLE (t=11.467, 16.188, P<0.05). Conclusions The accuracy of ME-NBI in screening early gastric cancer is satisfactory, and it has certain diagnostic value for inexperienced doctors. Key words: Stomach neoplasms; Early detection of cancer; Gastroscopy