The role of linked color imaging in endoscopic diagnosis of Helicobacter pylori associated gastritis

The Diagnostic Performance of Linked Color Imaging Compared to White Light Imaging in Endoscopic Diagnosis of Helicobacter pylori Infection: A Systematic Review and Meta-Analysis

Background/Aims

Recognizing Helicobacter pylori infection during endoscopy is important because it can lead to the performance of confirmatory testing. Linked color imaging (LCI) is an image enhancement technique that can improve the detection of gastrointestinal lesions. The purpose of this study was to compare LCI to conventional white light imaging (WLI) in the endoscopic diagnosis of H. pylori infection.

Methods

We conducted a comprehensive literature search using PubMed, Embase, and the Cochrane Library. All studies evaluating the diagnostic performance of LCI or WLI in the endoscopic diagnosis of H. pylori were eligible. Studies on magnifying endoscopy, chromoendoscopy, and artificial intelligence were excluded.

Results

Thirty-four studies were included in this meta-analysis, of which 32 reported the performance of WLI and eight reported the performance of LCI in diagnosing H. pylori infection. The pooled sensitivity and specificity of WLI in the diagnosis of H. pylori infection were 0.528 (95% confidence interval [CI], 0.517 to 0.540) and 0.821 (95% CI, 0.811 to 0.830), respectively. The pooled sensitivity and specificity of LCI in the diagnosis of H. pylori were 0.816 (95% CI, 0.790 to 0.841) and 0.868 (95% CI, 0.850 to 0.884), respectively. The pooled diagnostic odds ratios of WLI and LCI were 15.447 (95% CI, 8.225 to 29.013) and 31.838 (95% CI, 15.576 to 65.078), respectively. The areas under the summary receiver operating characteristic curves of WLI and LCI were 0.870 and 0.911, respectively.

Conclusions

LCI showed higher sensitivity in the endoscopic diagnosis of H. pylori infection than standard WLI.

Clinical usefulness of linked color imaging in identifying Helicobacter pylori infection: A systematic review and meta-analysis

BACKGROUND

Accurate diagnosis of Helicobacter pylori (H. pylori) infection status is a crucial premise for eradication therapy, as well as evaluation of risk for gastric cancer. Recent progress on imaging enhancement endoscopy (IEE) made it possible to not only detect precancerous lesions and early gastrointestinal cancers but also to predict H. pylori infection in real time. As a novel IEE modality, linked color imaging (LCI) has exhibited its value on diagnosis of lesions of gastric mucosa through emphasizing minor differences of color tone.

AIM

To compare the efficacy of LCI for H. pylori active infection vs conventional white light imaging (WLI).

METHODS

PubMed, Embase, Embase and Cochrane Library were searched up to the end of April 11, 2022. The random-effects model was adopted to calculate the diagnostic efficacy of LCI and WLI. The calculation of sensitivity, specificity, and likelihood ratios were performed; symmetric receiver operator characteristic (SROC) curves and the areas under the SROC curves were computed. Quality of the included studies was chosen to assess using the quality assessment of diagnostic accuracy studies-2 tool.

RESULTS

Seven original studies were included in this study. The pooled sensitivity, specificity, positive likelihood rate, and negative likelihood rate of LCI for the diagnosis of H. pylori infection of gastric mucosa were 0.85 [95% confidence interval (CI): 0.76-0.92], 0.82 (95%CI: 0.78-0.85), 4.71 (95%CI: 3.7-5.9), and 0.18 (95%CI: 0.10-0.31) respectively, with diagnostic odds ratio = 26 (95%CI: 13-52), SROC = 0.87 (95%CI: 0.84-0.90), which showed superiority of diagnostic efficacy compared to WLI.

CONCLUSION

Our results showed LCI can improve efficacy of diagnosis on H. pylori infection, which represents a useful endoscopic evaluation modality for clinical practice.

Role of linked color imaging for upper gastrointestinal disease: present and future

Techniques for upper gastrointestinal endoscopy are advancing to facilitate lesion detection and improve prognosis. However, most early tumors in the upper gastrointestinal tract exhibit subtle color changes or morphological features that are difficult to detect using white light imaging. Linked color imaging (LCI) has been developed to overcome these shortcomings; it expands or reduces color information to clarify color differences, thereby facilitating the detection and observation of lesions. This article summarizes the characteristics of LCI and advances in LCI-related research in the upper gastrointestinal tract field.

Linked Color Imaging for Stomach

Image-enhanced endoscopy (IEE) plays an important role in the detection and further examination of gastritis and early gastric cancer (EGC). Linked color imaging (LCI) is also useful for detecting and evaluating gastritis, gastric intestinal metaplasia as a pre-cancerous lesion, and EGC. LCI provides a clear excellent endoscopic view of the atrophic border and the demarcation line under various conditions of gastritis. We could recognize gastritis as the lesions of the diffuse redness to purple color area with LCI. On the other hand, EGCs are recognized as the lesions of the orange-red, orange, or orange-white color area in the lesion of the purple color area, which is the surround atrophic mucosa with LCI. With further prospective randomized studies, we will be able to evaluate the diagnosis ability for EGC by IEE, and it will be necessary to evaluate the role of WLI/IEE and the additional effects of the diagnostic ability by adding IEE to WLI in future.

An explainable artificial intelligence system for diagnosing Helicobacter Pylori infection under endoscopy: a case-control study

Background

Changes in gastric mucosa caused by Helicobacter pylori (H. pylori) infection affect the observation of early gastric cancer under endoscopy. Although previous researches reported that computer-aided diagnosis (CAD) systems have great potential in the diagnosis of H. pylori infection, their explainability remains a challenge.

Objective

We aim to develop an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) and giving diagnostic basis under endoscopy.

Design

A case-control study.

Methods

We retrospectively obtained 47,239 images from 1826 patients between 1 June 2020 and 31 July 2021 at Renmin Hospital of Wuhan University for the development of EADHI. EADHI was developed based on feature extraction combining ResNet-50 and long short-term memory networks. Nine endoscopic features were used for H. pylori infection. EADHI's performance was evaluated and compared to that of endoscopists. An external test was conducted in Wenzhou Central Hospital to evaluate its robustness. A gradient-boosting decision tree model was used to examine the contributions of different mucosal features for diagnosing H. pylori infection.

Results

The system extracted mucosal features for diagnosing H. pylori infection with an overall accuracy of 78.3% [95% confidence interval (CI): 76.2-80.3]. The accuracy of EADHI for diagnosing H. pylori infection (91.1%, 95% CI: 85.7-94.6) was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3) in internal test. And it showed a good accuracy of 91.9% (95% CI: 85.6-95.7) in external test. Mucosal edema was the most important diagnostic feature for H. pylori positive, while regular arrangement of collecting venules was the most important H. pylori negative feature.

Conclusion

The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs.

Plain language summary

An explainable AI system for Helicobacter pylori with good diagnostic performance Helicobacter pylori (H. pylori) is the main risk factor for gastric cancer (GC), and changes in gastric mucosa caused by H. pylori infection affect the observation of early GC under endoscopy. Therefore, it is necessary to identify H. pylori infection under endoscopy. Although previous research showed that computer-aided diagnosis (CAD) systems have great potential in H. pylori infection diagnosis, their generalization and explainability are still a challenge. Herein, we constructed an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) using images by case. In this study, we integrated ResNet-50 and long short-term memory (LSTM) networks into the system. Among them, ResNet50 is used for feature extraction, LSTM is used to classify H. pylori infection status based on these features. Furthermore, we added the information of mucosal features in each case when training the system so that EADHI could identify and output which mucosal features are contained in a case. In our study, EADHI achieved good diagnostic performance with an accuracy of 91.1% [95% confidence interval (CI): 85.7-94.6], which was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3%) in internal test. In addition, it showed a good diagnostic accuracy of 91.9% (95% CI: 85.6-95.7) in external tests. The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs. However, we only used data from a single center to develop EADHI, and it was not effective in identifying past H. pylori infection. Future, multicenter, prospective studies are needed to demonstrate the clinical applicability of CADs.

The role of advanced endoscopy in the management of inflammatory digestive diseases (upper gastrointestinal tract)

The Japan Gastroenterological Endoscopy Society held four serial symposia between 2019 and 2020 on the state-of-the-art of issues related to upper GI inflammatory diseases. This review discusses some of the topics addressed in these symposia. The papers regarding nonerosive reflux disease, recent improvements in intraesophageal pH-impedance monitoring and endoscopic diagnosis using image-enhanced endoscopy have been published. Many publications have addressed its usefulness in endoscopic treatment of gastroesophageal reflux disease such as anti-reflux mucosectomy. In the management of eosinophilic esophagitis, since the symptoms are subjective, objective indicators have been sought, and ultrasonography and high-resolution manometry may be useful tools for evaluation. The natural course of this condition, especially of asymptomatic cases, is not well clarified. Some newly developed anti-acid or anti-inflammatory medicines are now under investigation. With regard to autoimmune gastritis, because of widespread medical examinations, diagnosis of asymptomatic cases has been increasing. Recently, its endoscopic characteristics have become clear and the natural history of these conditions is being elucidated. The Kyoto Classification of Gastritis has been reported to be useful not only for Helicobacter pylori diagnosis but also for identification of risks of gastric cancer. Its usefulness is now recognized in Asia and Europe.

Diagnostic value of linked color imaging based on endoscopy for gastric intestinal metaplasia: a systematic review and meta-analysis

Background

The diagnostic value of linked color imaging based on endoscopy for gastric intestinal metaplasia has shown variable results. Therefore, this meta-analysis sought to systematically evaluate the value of linked color imaging (LCI) based on the blue laser endoscopy system for the diagnosis of gastric intestinal metaplasia (GIM).

Methods

Literature searches were conducted of electronic databases including PubMed, Embase, the Cochrane Library, and Web of Science to screen diagnostic tests of LCI. The random-effects model was adopted to calculate the diagnostic efficacy of LCI for GIM. Meta-DiSc 1.40 software was applied for the calculation of sensitivity, specificity, and likelihood ratios; symmetric receiver operator characteristic (SROC) curves were drawn, and the areas under the SROC curves (AUCs) were computed. Quality of the included studies was chosen to assess using the quality assessment of diagnostic accuracy studies-2 (QUADAS-2) tool.

Results

Six original studies involving 700 participants were included in the meta-analysis. The pooled sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of LCI for diagnosing GIM were 0.87 (0.83–0.91), 0.86 (0.82–0.89), 5.72 (3.63–8.99), and 0.17 (0.08–0.36), respectively. SROC curve analysis showed that the AUC value was 0.9283.

Discussion

Our study shows that LCI can be used for the accurate diagnosis of GIM. Considering weaknesses of available studies in terms of design, further studies with rigorous design are in need for further validating the findings of this meta-analysis.