White-light Endoscopic Images Research Articles

An artificial intelligence system for comprehensive pathologic outcome prediction in early gastric cancer through endoscopic image analysis (with video)

BackgroundAccurate prediction of pathologic results for early gastric cancer (EGC) based on endoscopic findings is essential in deciding between endoscopic and surgical resection. This study aimed to develop an artificial intelligence (AI) model to assess comprehensive pathologic characteristics of EGC using white-light endoscopic images and videos.MethodsTo train the model, we retrospectively collected 4,336 images and prospectively included 153 videos from patients with EGC who underwent endoscopic or surgical resection. The performance of the model was tested and compared to that of 16 endoscopists (nine experts and seven novices) using a mutually exclusive set of 260 images and 10 videos. Finally, we conducted external validation using 436 images and 89 videos from another institution.ResultsAfter training, the model achieved predictive accuracies of 89.7% for undifferentiated histology, 88.0% for submucosal invasion, 87.9% for lymphovascular invasion (LVI), and 92.7% for lymph node metastasis (LNM), using endoscopic videos. The area under the curve values of the model were 0.992 for undifferentiated histology, 0.902 for submucosal invasion, 0.706 for LVI, and 0.680 for LNM in the test. In addition, the model showed significantly higher accuracy than the experts in predicting undifferentiated histology (92.7% vs. 71.6%), submucosal invasion (87.3% vs. 72.6%), and LNM (87.7% vs. 72.3%). The external validation showed accuracies of 75.6% and 71.9% for undifferentiated histology and submucosal invasion, respectively.ConclusionsAI may assist endoscopists with high predictive performance for differentiation status and invasion depth of EGC. Further research is needed to improve the detection of LVI and LNM.

Label-Free Optical Technologies to Enhance Noninvasive Endoscopic Imaging of Early-Stage Cancers.

White light endoscopic imaging allows for the examination of internal human organs and is essential in the detection and treatment of early-stage cancers. To facilitate diagnosis of precancerous changes and early-stage cancers, label-free optical technologies that provide enhanced malignancy-specific contrast and depth information have been extensively researched. The rapid development of technology in the past two decades has enabled integration of these optical technologies into clinical endoscopy. In recent years, the significant advantages of using these adjunct optical devices have been shown, suggesting readiness for clinical translation. In this review, we provide an overview of the working principles and miniaturization considerations and summarize the clinical and preclinical demonstrations of several such techniques for early-stage cancer detection. We also offer an outlook for the integration of multiple technologies and the use of computer-aided diagnosis in clinical endoscopy.

Few-shot learning for the classification of intestinal tuberculosis and Crohn's disease on endoscopic images: A novel learn-to-learn framework

Background and aimStandard deep learning methods have been found inadequate in distinguishing between intestinal tuberculosis (ITB) and Crohn's disease (CD), a shortcoming largely attributed to the scarcity of available samples. In light of this limitation, our objective is to develop an innovative few-shot learning (FSL) system, specifically tailored for the efficient categorization and differential diagnosis of CD and ITB, using endoscopic image data with minimal sample requirements. MethodsA total of 122 white-light endoscopic images (99 CD images and 23 ITB images) were collected (one ileum image from each patient). A 2-way, 3-shot FSL model that integrated dual transfer learning and metric learning strategies was devised. Xception architecture was selected as the foundation and then underwent a dual transfer process utilizing oesophagitis images sourced from HyperKvasir. Subsequently, the eigenvectors derived from the Xception for each query image were converted into predictive scores, which were calculated using the Euclidean distances to six reference images from the support sets. ResultsThe FSL model, which leverages dual transfer learning, exhibited enhanced performance metrics (AUC 0.81) compared to a model relying on single transfer learning (AUC 0.56) across three evaluation rounds. Additionally, its performance surpassed that of a less experienced endoscopist (AUC 0.56) and even a more seasoned specialist (AUC 0.61). ConclusionsThe FSL model we have developed demonstrates efficacy in distinguishing between CD and ITB using a limited dataset of endoscopic imagery. FSL holds value for enhancing the diagnostic capabilities of rare conditions.

D2polyp-Net: A cross-modal space-guided network for real-time colorectal polyp detection and diagnosis

Colorectal polyp screening and identification during endoscopy are crucial for reducing cancer morbidity and patient mortality. Although some deep neural networks for polyp detection and diagnosis have been proposed, there are still problems in small-size polyp localization, poor classification performance especially in white-light endoscopic imaging modality, as well as real-time performance. In this paper, we propose D2polyp-Net, employing a space-guided localization framework and a cross-modal pairwise training strategy, which performs real-time polyp detection and diagnosis simultaneously. The space-guided framework consisting of a dual-pyramid structure builds a fusion bridge between shallow-spatial and deep-semantic information, achieving more accurate localization and providing effective spatial information for polyp classification. The cross-modal pairwise training strategy constrains the output feature of white-light images to approach that of the corresponding narrow-band images, as the latter provide richer mucosal structure and blood flow information to classify polyps. The above modules are validated on publicly available datasets, and D2polyp-Net is demonstrated to surpass other compared state-of-the-art algorithms. It achieves an mAP@0.5 of 0.817 at a frame rate of 28 FPS, with precision and recall above 0.7 for both hyperplastic and adenomatous polyps. Cross-center tests on clinical data further demonstrate the generalization ability of D2polyp-Net, with the mAP@0.5 reaching 0.780. The experimental results show that D2polyp-Net can assist physicians in polyp detection and diagnosis during clinical colonoscopy, which is important for reducing the polyp miss rate and improving the diagnostic efficiency.

Gastrointestinal: Real-time observation of rectal malignant lymphoma using endocytoscopy for differentiation from adenocarcinoma.

A 25-year-old man was suspected of having advanced rectal cancer by his previous physician and was referred to our hospital for surgery. Colonoscopy was repeated in our hospital before surgery. White-light imaging revealed a semi-circumferential ulcerative lesion in the rectum (Fig. 1a). The lesion was stained with 1% methylene blue and 0.05% crystal violet solution and evaluated using endocytoscopy. Proliferation of swollen, irregular-shaped nuclei with the formation of glandular duct structures was observed (Fig. 1b). Tissue biopsies were taken for flow cytometry and histological assessment. Histopathological examination after hematoxylin and eosin staining revealed infiltration and proliferation of enlarged dysplastic cells, without formation of glandular ducts (Fig. 1c). Immunohistochemistry was performed in response to the flow cytometry results, and was positive for CD20, CD79a, bcl2, and bcl6, but negative for CD3, CD10, multiple myeloma oncogene 1, and Epstein–Barr-virus-encoded small RNA in situ hybridization. Ki-67 index was 90%. The lesion was diagnosed as diffuse large B-cell lymphoma (DLBCL), germinal center B-cell-like type. Malignant lymphomas of the colon account for 0.1%–0.7% of all colorectal malignancies. In the colon, DLBCL is the second most common tumor after mucosa-associated lymphoid tissue lymphoma. DLBCL is often ulcerated and resembles ulcerated colorectal cancer by white-light endoscopic imaging (Fig. 2a). However, differentiation is required for treatment decision-making. Tissue sampling for flow cytometry can be used to quantify expression of proteins associated with prognosis and to detect multidrug resistance, which makes it useful for measuring prognostic indicators in lymphoid neoplasia. Hence, it is important to make a diagnosis of lymphoma on-site to prevent multiple repeat colonoscopies. Endocytoscopy allows real-time, in vivo visualization of atypical cells on the tumor surface and tissue details, including nuclei and glandular lumens, resulting in high diagnostic accuracy for adenocarcinoma or adenomatous lesions. However, there are few reports of the endocytoscopic findings of lymphomas in the gastrointestinal tract. In this case, endocytoscopy (520×, H290ECI; Olympus, Tokyo, Japan) showed a significant difference between DLBCL and adenocarcinoma, with irregular and rough lumens and agglomeration of distorted nuclei strongly stained with methylene blue (Fig. 2b,c).

Role of endoscopic ultrasound and endoscopic resection in the diagnosis and treatment of esophageal granular cell tumors

Background and Aim Diagnosis and complete resection of esophageal granular cell tumors (GCTs) is an area of concern. However, articles on endoscopic ultrasound (EUS) and endoscopic resection of esophageal granular cell tumors are few. To evaluate the role of endoscopic ultrasound and endoscopic resection in the diagnosis and treatment of esophageal granular cell tumors. Methods A retrospective analysis of 15 patients with esophageal granular cell tumors who underwent endoscopic ultrasound examination and endoscopic resection in our hospital was conducted. The clinical data, endoscopic ultrasound images, endoscopic treatment, pathological characteristics, postoperative complications and follow-up status of all patients were evaluated. Ten board-certified endoscopists independently evaluated the white light endoscopic images of the 15 patients (Test 1) and the endoscopic ultrasound images together with white light endoscopic images of the same patient set (Test 2). Result Female patients accounted for 53.4% of the participants. The average age at the time of diagnosis was 49.13 ± 9.31 years old. Ten lesions (66.67%) showed hypoechoic signal, four lesions (26.67%) showed hyperechoic signal and one lesion showed medium signal. The diagnostic accuracy was significantly higher with Test 2(65.3% vs. 92.0%, p < .001). Complete endoscopic resection was performed in all the patients. No complications occurred in any of the patients. No esophageal stenosis, recurrence, or metastases was found in all patients during the follow-up period. Conclusion The endoscopic ultrasound images of esophageal granular cell tumors have certain characteristics that help diagnose esophageal granular cell tumors. Endoscopic resection of esophageal granular cell tumors is an effective, safe and feasible treatment method.

Computer-aided diagnosis of serrated colorectal lesions using non-magnified white-light endoscopic images

Computer-aided diagnosis systems for polyp characterization are commercially available but cannot recognize subtypes of sessile lesions. This study aimed to develop a computer-aided diagnosis system to characterize polyps using non-magnified white-light endoscopic images. A total of 2249 non-magnified white-light images from 1030 lesions including 534 tubular adenomas, 225 sessile serrated adenoma/polyps, and 271 hyperplastic polyps in the proximal colon were consecutively extracted from an image library and divided into training and testing datasets (4:1), based on the date of colonoscopy. Using ResNet-50 networks, we developed a classifier (1) to differentiate adenomas from serrated lesions, and another classifier (2) to differentiate sessile serrated adenoma/polyps from hyperplastic polyps. Diagnostic performance was assessed using the testing dataset. The computer-aided diagnosis system generated a probability score for each image, and a probability score for each lesion was calculated as the weighted mean with a log10-transformation. Two experts (E1, E2) read the identical testing dataset with a probability score. The area under the curve of classifier (1) for adenomas was equivalent to E1 and superior to E2 (classifier 86%, E1 86%, E2 69%; classifier vs. E2, p < 0.001). In contrast, the area under the curve of classifier (2) for sessile serrated adenoma/polyps was inferior to both experts (classifier 55%, E1 68%, E2 79%; classifier vs. E2, p < 0.001). The classifier (1) developed using white-light images alone compares favorably with experts in differentiating adenomas from serrated lesions. However, the classifier (2) to identify sessile serrated adenoma/polyps is inferior to experts.

Deep-Learning for the Diagnosis of Esophageal Cancers and Precursor Lesions in Endoscopic Images: A Model Establishment and Nationwide Multicenter Performance Verification Study.

Background: Suspicion of lesions and prediction of the histology of esophageal cancers or premalignant lesions in endoscopic images are not yet accurate. The local feature selection and optimization functions of the model enabled an accurate analysis of images in deep learning. Objectives: To establish a deep-learning model to diagnose esophageal cancers, precursor lesions, and non-neoplasms using endoscopic images. Additionally, a nationwide prospective multicenter performance verification was conducted to confirm the possibility of real-clinic application. Methods: A total of 5162 white-light endoscopic images were used for the training and internal test of the model classifying esophageal cancers, dysplasias, and non-neoplasms. A no-code deep-learning tool was used for the establishment of the deep-learning model. Prospective multicenter external tests using 836 novel images from five hospitals were conducted. The primary performance metric was the external-test accuracy. An attention map was generated and analyzed to gain the explainability. Results: The established model reached 95.6% (95% confidence interval: 94.2–97.0%) internal-test accuracy (precision: 78.0%, recall: 93.9%, F1 score: 85.2%). Regarding the external tests, the accuracy ranged from 90.0% to 95.8% (overall accuracy: 93.9%). There was no statistical difference in the number of correctly identified the region of interest for the external tests between the expert endoscopist and the established model using attention map analysis (P = 0.11). In terms of the dysplasia subgroup, the number of correctly identified regions of interest was higher in the deep-learning model than in the endoscopist group, although statistically insignificant (P = 0.48). Conclusions: We established a deep-learning model that accurately classifies esophageal cancers, precursor lesions, and non-neoplasms. This model confirmed the potential for generalizability through multicenter external tests and explainability through the attention map analysis.

Hyperspectral Imaging Combined with Artificial Intelligence in the Early Detection of Esophageal Cancer.

Simple SummaryDetection of early esophageal cancer is important to improve patient survival, however, early diagnosis of the cancer cells is difficult, even for experienced endoscopists. This article provides a new method by using hyperspectral imaging and a deep learning diagnosis model to classify and diagnose esophageal cancer using a single-shot multibox detector. The accuracy of the results when using an RGB image in WLI was 83% and while using the spectrum data the accuracy was increased to 88%. There was an increase of 5% in WLI. The accuracy of the results when using an RGB image in NBI was 86% and while using the spectrum data the accuracy was increased to 91%. There was an increase of 5% in NBI. This study proves that the accuracy of prediction when using the spectrum data has been significantly improved and the diagnosis of narrow-band endoscopy data is more sensitive than that of white-light endoscopy.This study uses hyperspectral imaging (HSI) and a deep learning diagnosis model that can identify the stage of esophageal cancer and mark the locations. This model simulates the spectrum data from the image using an algorithm developed in this study which is combined with deep learning for the classification and diagnosis of esophageal cancer using a single-shot multibox detector (SSD)-based identification system. Some 155 white-light endoscopic images and 153 narrow-band endoscopic images of esophageal cancer were used to evaluate the prediction model. The algorithm took 19 s to predict the results of 308 test images and the accuracy of the test results of the WLI and NBI esophageal cancer was 88 and 91%, respectively, when using the spectral data. Compared with RGB images, the accuracy of the WLI was 83% and the NBI was 86%. In this study, the accuracy of the WLI and NBI was increased by 5%, confirming that the prediction accuracy of the HSI detection method is significantly improved.

Simultaneous Recognition of Atrophic Gastritis and Intestinal Metaplasia on White Light Endoscopic Images Based on Convolutional Neural Networks: A Multicenter Study.

INTRODUCTION:Patients with atrophic gastritis (AG) or gastric intestinal metaplasia (GIM) have elevated risk of gastric adenocarcinoma. Endoscopic screening and surveillance have been implemented in high incidence countries. The study aimed to evaluate the accuracy of a deep convolutional neural network (CNN) for simultaneous recognition of AG and GIM.METHODS:Archived endoscopic white light images with corresponding gastric biopsies were collected from 14 hospitals located in different regions of China. Corresponding images by anatomic sites containing AG, GIM, and chronic non-AG were categorized using pathology reports. The participants were randomly assigned (8:1:1) to the training cohort for developing the CNN model (TResNet), the validation cohort for fine-tuning, and the test cohort for evaluating the diagnostic accuracy. The area under the curve (AUC), sensitivity, specificity, and accuracy with 95% confidence interval (CI) were calculated.RESULTS:A total of 7,037 endoscopic images from 2,741 participants were used to develop the CNN for recognition of AG and/or GIM. The AUC for recognizing AG was 0.98 (95% CI 0.97–0.99) with sensitivity, specificity, and accuracy of 96.2% (95% CI 94.2%–97.6%), 96.4% (95% CI 94.8%–97.9%), and 96.4% (95% CI 94.4%–97.8%), respectively. The AUC for recognizing GIM was 0.99 (95% CI 0.98–1.00) with sensitivity, specificity, and accuracy of 97.9% (95% CI 96.2%–98.9%), 97.5% (95% CI 95.8%–98.6%), and 97.6% (95% CI 95.8%–98.6%), respectively.DISCUSSION:CNN using endoscopic white light images achieved high diagnostic accuracy in recognizing AG and GIM.

A narrative review of fluorescence imaging in robotic-assisted surgery.

Objective:In this review, we provide examples of applications of fluorescence imaging in urologic, gynecologic, general, and endocrine surgeries.Background:While robotic-assisted surgery has helped increase the availability of minimally invasive procedures across surgical specialties, there remains an opportunity to reduce adverse events associated with open, laparoscopic, and robotic-assisted methods. In 2011, fluorescence imaging was introduced as an option to the da Vinci Surgical System, and has been standard equipment since 2014. Without interfering with surgical workflow, this fluorescence technology named Firefly® allows for acquisition and display of near-infrared fluorescent signals that are co-registered with white light endoscopic images. As a result, robotic surgeons of all specialties have been able to explore the clinical utility of fluorescence guided surgery.Methods:Literature searches were performed using the PubMed and MEDLINE databases using the keywords “robotic-assisted fluorescence surgery”, “ICG robotic surgery”, and “fluorescence guided surgery” covering the years 2011–2020.Conclusions:Real-time intraoperative fluorescence guidance has shown great potential in helping guide surgeons in both simple and complex surgical interventions. Indocyanine green is one of the most widely-used imaging agents in fluorescence guided surgery, and other targeted, near-infrared imaging agents are in various stages of development. Fluorescence is becoming a reliable tool that can help surgeons in their decision-making process in some specialties, while explorations continue in others.

Diagnostic Performance of Artificial Intelligence-Based Models for the Detection of Early Esophageal Cancers in Barret's Esophagus: A Meta-Analysis of Patient-Based Studies.

IntroductionBarret’s esophagus (BE) is a precursor of adenocarcinoma of the esophagus. The detection of high-grade dysplasia and adenocarcinoma at an early stage can improve survival but is very challenging. Artificial intelligence (AI)-based models have been claimed to improve diagnostic accuracy. The aim of the current study was to carry out a meta-analysis of papers reporting the results of artificial intelligence-based models used in real-time white light endoscopy of patients with BE to detect early esophageal adenocarcinoma (EEAC).MethodsThis meta-analysis was registered with the International Prospective Register of Systematic Reviews (PROSPERO; Reg No. CRD42021246148) and its conduction and reporting followed the Preferred Reporting Items for Systematic Review and Meta-Analysis of Diagnostic Test Accuracy (PRISMA-DTA) statement guidelines. All peer-reviewed and preprint original articles that reported the sensitivity and specificity of AI-based models on white light endoscopic imaging as an index test against the standard criterion of histologically proven early oesophageal cancer on the background of Barret's esophagus reported as per-patient analysis were considered for inclusion. There was no restriction on type and year of publication, however, articles published in the English language were searched. The search engines used included Medline, PubMed, EMBASE, EMCARE, AMED, BNI, and HMIC. The search strategy included the following keywords for all search engines: ("Esophageal Cancer" OR "Esophageal Neoplasms" OR " Oesophageal Cancer" OR "Oesophageal Neoplasms” OR "Barrett's Esophagus" OR "Barrett's Oesophagus") And ("Artificial Intelligence" OR "Deep Learning" OR "Machine Learning" OR "Convolutional Network"). This search was conducted on November 30, 2020. Duplicate studies were excluded. Studies that reported more than one dataset per patient for the diagnostic accuracy of the AI-based model were included twice. Quantitative and qualitative data, including first author, year of publication, true positives (TP), false negatives (FN), false positives (FP), true negatives (TN), the threshold of the index test, and country where the study was conducted, were extracted using a data extraction sheet. The Quality Appraisal for Diverse Studies 2 (QUADS-2) tool was used to assess the quality of each study. Data were analyzed using MetaDTA, interactive online software for meta-analysis of diagnostic studies. The diagnostic performance of the meta-analysis was assessed by a summary receiver operating characteristics (sROC) plot. A meta-analysis tree was constructed using MetaDTA software to determine the effect of cumulative sensitivity and specificity on surveillance of patients with BE in terms of miss rate and overdiagnosis.ResultsThe literature search revealed 171 relevant records. After removing duplicates, 117 records were screened. Full-text articles of 28 studies were assessed for eligibility. Only three studies reporting four datasets met the inclusion criteria. The summary sensitivity and specificity of AI-based models were 0.90 (95% CI, 0.83- 0.944) and 0.86 (95% CI, 0.781-0.91), respectively. The area under the curve for all the available evidence was 0.88.ConclusionCollective evidence for the routine usage of AI-based models in the detection of EEAC is encouraging but is limited by the low number of studies. Further prospective studies reporting the patient-based diagnostic accuracy of such models are required.

ID: 3523068 COMPUTER-AIDED DIAGNOSIS OF COLORECTAL CANCER WITH DEEP SUBMUCOSAL INVASION USING NON-MAGNIFIED WHITE LIGHT ENDOSCOPIC IMAGES COMPARED WITH ENDOSCOPISTS

Colorectal cancers (CRCs) with deep (≥1mm) submucosal invasion (T1b) are endoscopically (e-) untreatable while CRCs limited to the mucosa (Tis) and CRCs with superficial submucosal invasion (T1a) are e-treatable. The endoscopic appearance of e-untreatable CRCs resembles that of e-treatable CRCs. This study aimed to develop a computer-aided diagnosis (CADx) system to identify e-untreatable CRC using non-magnified unenhanced white light endoscopic images.

Endoscopic prediction of submucosal invasion in Barrett's cancer with the use of artificial intelligence: a pilot study.

The accurate differentiation between T1a and T1b Barrett's-related cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an artificial intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett's cancer on white-light images. Endoscopic images from three tertiary care centers in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) were evaluated using the AI system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett's cancer. The sensitivity, specificity, F1 score, and accuracy of the AI system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.74, and 0.71, respectively. There was no statistically significant difference between the performance of the AI system and that of experts, who showed sensitivity, specificity, F1, and accuracy of 0.63, 0.78, 0.67, and 0.70, respectively. This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett's cancer. AI scored equally to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and real-life settings. Nevertheless, the correct prediction of submucosal invasion in Barrett's cancer remains challenging for both experts and AI.

ELNet:Automatic classification and segmentation for esophageal lesions using convolutional neural network.

Automatic and accurate esophageal lesion classification and segmentation is of great significance to clinically estimate the lesion statuses of the esophageal diseases and make suitable diagnostic schemes. Due to individual variations and visual similarities of lesions in shapes, colors, and textures, current clinical methods remain subject to potential high-risk and time-consumption issues. In this paper, we propose an Esophageal Lesion Network (ELNet) for automatic esophageal lesion classification and segmentation using deep convolutional neural networks (DCNNs). The underlying method automatically integrates dual-view contextual lesion information to extract global features and local features for esophageal lesion classification and lesion-specific segmentation network is proposed for automatic esophageal lesion annotation at pixel level. For the established clinical large-scale database of 1051 white-light endoscopic images, ten-fold cross-validation is used in method validation. Experiment results show that the proposed framework achieves classification with sensitivity of 0.9034, specificity of 0.9718, and accuracy of 0.9628, and the segmentation with sensitivity of 0.8018, specificity of 0.9655, and accuracy of 0.9462. All of these indicate that our method enables an efficient, accurate, and reliable esophageal lesion diagnosis in clinics.

Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning.

Endoscopic resection is recommended for gastric neoplasms confined to mucosa or superficial submucosa. The determination of invasion depth is based on gross morphology assessed in endoscopic images, or on endoscopic ultrasound. These methods have limited accuracy and pose an inter-observer variability. Several studies developed deep-learning (DL) algorithms classifying invasion depth of gastric cancers. Nevertheless, these algorithms are intended to be used after definite diagnosis of gastric cancers, which is not always feasible in various gastric neoplasms. This study aimed to establish a DL algorithm for accurately predicting submucosal invasion in endoscopic images of gastric neoplasms. Pre-trained convolutional neural network models were fine-tuned with 2899 white-light endoscopic images. The prediction models were subsequently validated with an external dataset of 206 images. In the internal test, the mean area under the curve discriminating submucosal invasion was 0.887 (95% confidence interval: 0.849–0.924) by DenseNet−161 network. In the external test, the mean area under the curve reached 0.887 (0.863–0.910). Clinical simulation showed that 6.7% of patients who underwent gastrectomy in the external test were accurately qualified by the established algorithm for potential endoscopic resection, avoiding unnecessary operation. The established DL algorithm proves useful for the prediction of submucosal invasion in endoscopic images of gastric neoplasms.

Poor inter-observer agreement on the endoscopic diagnosis of eosinophilic esophagitis among Japanese endoscopists

A variety of endoscopic findings are considered useful for the diagnosis of eosinophilic esophagitis (EoE). However, the diagnostic consistency among Japanese endoscopists for those findings has not been fully examined. The aim of this study was to investigate the inter- and intra-observer agreement for endoscopic findings suggesting EoE. Forty endoscopists, including 20 with board certification from the Japan Gastroenterological Endoscopy Society (JGES), participated in this study. Initially, they examined 50 randomized white-light endoscopic images from 30 patients with EoE and 20 without EoE. Four weeks later, the same 50 endoscopic images were re-examined in a different random order. Inter- and intra-observer agreement was calculated using kappa statistics for multiple observers. The kappa coefficient of reliability [95% confidence interval (CI)] for all 40 endoscopists for diagnosis of EoE was 0.34 (0.33–0.35), indicating poor level of inter-observer agreement, while intra-observer agreement showed a moderate value of 0.52 (0.47–0.57). Among 4 possible endoscopic findings (linear furrows, concentric rings, edema, white exudates) for EoE, acceptable levels (kappa value >0.4) of inter- and intra-observer agreement were seen only for linear furrows. When the JGES board-certified and non-certified endoscopists were compared for successful diagnosis of EoE, the value was significantly higher for the board-certified group. However, the level of inter-observer agreement remained poor level. We concluded that inter-observer agreement on the endoscopic diagnosis of EoE among Japanese endoscopists did not reach a clinically acceptable level.

AGA White Paper: Training and Implementation of Endoscopic Image Enhancement Technologies.

Endoscopic image-enhancement technologies provide opportunities to visualize normal and abnormal tissues within the gastrointestinal (GI) tract in a manner that complements conventional white light endoscopic imaging. The additional information that is obtained enables the endoscopist to better identify, delineate, and characterize lesions and can facilitate targeted biopsies or, in some cases, eliminate the need to send samples for histologic analysis. Some of these technologies have been available for more than a decade, but despite this fact, there is limited use of these technologies by endoscopists. Lack of formalized training in their use and a scarcity of guidelines on implementation of these technologies into clinical practice are contributing factors. In November 2014, the American Gastroenterological Association's Center for GI Innovation and Technology conducted a 2-day workshop to discuss endoscopic image-enhancement technologies. This article represents the third of 3 separate documents generated from the workshop and discusses the published literature pertaining to training and outlines a proposed framework for the implementation of endoscopic image-enhancement technologies in clinical practice. There was general agreement among participants in the workshop on several key considerations. Training and competency assessment for endoscopic image-enhancement technologies should incorporate competency-based education paradigms. To facilitate successful training, multiple different educational models that can cater to variations in learning styles need to be developed, including classroom-style and self-directed programs, in-person and web-based options, image and video atlases, and endoscopic simulator programs. To ensure safe and appropriate use of these technologies over time, refresher courses, skill maintenance programs, and options for competency reassessment should be established. Participants also generally agreed that although early adopters of novel endoscopic image-enhancement modalities can successfully implement these technologies by pursuing training and ensuring self-competency, widespread implementation is likely to require support from GI societies and buy-in from other key stakeholders including payors/purchasers and patients. Continued work by manufacturers and the GI societies in providing training programs and patient education, working with payors and purchasers, and creating environments and policies that motivate endoscopists to adopt new practices is essential in creating widespread implementation.

Is virtual chromoendoscopy useful in the evaluation of subtle ulcerative small-bowel lesions detected by video capsule endoscopy?

Background: The identification of subtle small-bowel mucosal lesions by video capsule endoscopy (VCE) can be challenging. Virtual chromoendoscopy techniques, based on narrowing the bandwidth of conventional white light endoscopic imaging (WLI), were developed to improve the analysis of mucosal patterns. However, data on the already-implemented Flexible spectral Imaging (or Fujinon Intelligent) Color Enhancement (FICE) software application in VCE are limited. Materials and methods: An evaluation of 250 difficult-to-interpret small-bowel ulcerative and 50 artifact lesions selected from 64 VCE recordings was conducted by four experienced VCE readers in two steps: initially as WLI, then with the addition of all available virtual chromoendoscopy pre-sets (FICE 1, 2, and 3 and Blue mode). The readers labeled them as real or false ulcerative lesions and rated the usefulness of each of the pre-sets. Results: Between the first (WLI-only) and second (virtual chromoendoscopy-aided) readings, in terms of accuracy there was a global 16.5 % (95 % confidence interval [95 %CI] 13.6 – 19.4 %) improvement (P < 0.001), derived from a 22 % [95 %CI 18.9 – 25.1 %] improvement in the evaluation of true ulcerative images (P < 0.001) and an 11 % (95 %CI 4.1 – 17.7 %) decrease in the evaluation of false ulcerative ones (P = 0.003). The FICE 1 and 2 pre-sets were rated as most useful. Conclusion: The application of virtual chromoendoscopy for VCE is useful to better categorize difficult-to-interpret small-bowel mucosal ulcerative lesions. However, care must be taken, and individual images should be evaluated only as part of a sequence in a recording because the technology can also mistakenly guide to the incorrect interpretation of artifacts as ulcerative lesions.

Novel computer-aided diagnostic system for colorectal lesions by using endocytoscopy (with videos)

Endocytoscopy enables invivo observation of nuclei at 450× magnification during GI endoscopy, thus allowing precise prediction of lesion pathology. However, because it requires training and experience, it may be beneficial only when performed by expert endoscopists. To develop and evaluate a novel computer-aided diagnosis system for endocytoscopic imaging (EC-CAD) of colorectal lesions. Pilot study. University hospital. One hundred fifty-two patients with small colorectal polyps (≤10mm) who had undergone endocytoscopy. Test sets of white-light endoscopic images and endocytoscopic images from 176 small colorectal polyps (137 neoplastic and 39 non-neoplastic polyps) were assessed by EC-CAD, 2 expert endoscopists, and 2trainee endoscopists. Sensitivity, specificity, and accuracy in predicting neoplastic change by EC-CAD comparing expert and trainee endoscopists. EC-CAD had a sensitivity of 92.0% and an accuracy of 89.2%; these were comparable to those achieved by expert endoscopists (92.7% and 92.3%; P= .868 and .256, respectively) and significantly higher than those achieved by trainee endoscopists (81.8% and 80.4%; P< .001 and .002, respectively). EC-CAD achieved a specificity of 79.5%; this did not differ significantly from that achieved by the experts and trainees. EC-CAD also enabled instant diagnosis, taking only 0.3 seconds for each lesion with perfect reproducibility. No sample size calculation. EC-CAD provides fully automated instant classification of colorectal polyps with excellent sensitivity, accuracy, and objectivity. Thus, it can be a powerful tool for facilitating decision making during routine colonoscopy.