Narrow band imaging and serology in the assessment of premalignant gastric pathology

Assessment of Narrow Band Imaging Algorithm for Video Capsule Endoscopy Based on Decorrelated Color Space for Esophageal Cancer

Video capsule endoscopy (VCE) is increasingly used to decrease discomfort among patients owing to its small size. However, VCE has a major drawback of not having narrow band imaging (NBI) functionality. The current VCE has the traditional white light imaging (WLI) only, which has poor performance in the computer-aided detection (CAD) of different types of cancer compared to NBI. Specific cancers, such as esophageal cancer (EC), do not exhibit any early biomarkers, making their early detection difficult. In most cases, the symptoms are unnoticeable, and EC is diagnosed only in later stages, making its 5-year survival rate below 20% on average. NBI filters provide particular wavelengths that increase the contrast and enhance certain features of the mucosa, thereby enabling early identification of EC. However, VCE does not have a slot for NBI functionality because its size cannot be increased. Hence, NBI image conversion from WLI can presently only be achieved in post-processing. In this study, a complete arithmetic assessment of the decorrelated color space was conducted to generate NBI images from WLI images for VCE of the esophagus. Three parameters, structural similarity index metric (SSIM), entropy, and peak-signal-to-noise ratio (PSNR), were used to assess the simulated NBI images. Results show the good performance of the NBI image reproduction method with SSIM, entropy difference, and PSNR values of 93.215%, 4.360, and 28.064 dB, respectively.

Helicobacter pylori Infection: Current Status and Future Prospects on Diagnostic, Therapeutic and Control Challenges

Helicobacter pylori (H. pylori) infection, which affects approximately half of the world's population, remains a serious public health problem. As H. pylori infection leads to a number of gastric pathologies, including inflammation, gastroduodenal ulcers, and malignancies, early detection and treatment are crucial to preventing the spread of the infection. Multiple extragastric complications, such as iron deficiency anaemia, immune thrombocytopenic purpura, vitamin B12 deficiency, diabetes mellitus, cardiovascular diseases, and certain neurological disorders, have also been linked to H. pylori infection. An awareness of H. pylori and associated health hazards is necessary to minimize or even eradicate the infection. Therefore, there is an urgent need to raise the standards for the currently employed diagnostic, eradication, alternative treatment strategies. In addition, a brief overview of traditional and cutting-edge approaches that have proven effective in identifying and managing H. pylori is needed. Based on the test and laboratory equipment available and patient clinical characteristics, the optimal diagnostic approach requires weighing several factors. The pathophysiology and pathogenic mechanisms of H. pylori should also be studied, focusing more on the infection-causing virulence factors of this bacterium. Accordingly, this review aims to demonstrate the various diagnostic, pathophysiological, therapeutic, and eradication tactics available for H. pylori, emphasizing both their advantages and disadvantages. Invasive methods (such as quick urease testing, biopsy, or culture) or noninvasive methods (such as breath tests, stool investigations, or serological tests) can be used. We also present the most recent worldwide recommendations along with scientific evidence for treating H. pylori. In addition to the current antibiotic regimens, alternative therapies may also be considered. It is imperative to eradicate the infections caused by H. pylori as soon as possible to prevent problems and the development of stomach cancer. In conclusion, significant advances have been made in identifying and treating H. pylori. To improve eradication rates, peptide mass fingerprinting can be used as a diagnostic tool, and vaccines can also eliminate the infection.

Value of serum pepsinogen, gastrin, and cadherin-17 detection combined with narrowband imaging magnifying endoscopy in distinguishing early gastric cancer and precancerous lesions

BACKGROUND

The early screening of cancer has always been the focus of cancer research. As a common cancer in the world, gastric cancer has had a high incidence rate and mortality for many years, and canceration is difficult to detect. Current detection methods are not ideal for early detection of gastric cancer and precancerous lesions.

AIM

To assess the value of detection of serum pepsinogen (PG), gastrin (G-17), and hepato-intestinal cadherin-17 (CDH-17) combined with narrowband imaging magnifying endoscopy in the identification of early gastric cancer and precancerous lesions.

METHODS

The clinical data of patients with early gastric cancer (106 cases) and precancerous lesions (134 cases) at our hospital from January 2018 to January 2021 were retrospectively analyzed. All patients underwent narrow-band imaging magnifying endoscopy and detection of serum PG (including PGⅠ and PGⅡ), G-17, and CDH-17 levels. The sensitivity, specificity, and accuracy of PG, G-17, CDH-17, and narrow-band imaging magnifying endoscopy, alone and in combination, in the diagnosis of early gastric cancer and precancerous lesions were calculated.

RESULTS

In the early gastric cancer group, the incidence of lesions with border limits, mucosal microvascular irregularities, irregular surface ducts, and increased glandular spacing as detected by narrow-band imaging magnifying endoscopy was higher than that in the precancerous lesion group (P < 0.05). The diagnostic coincidence rates of magnifying endoscopy for early gastric cancer and precancerous lesions were 83.02% and 85.07%, respectively, and the difference was not statistically significant (P > 0.05). Serum PGⅠ level in the early gastric cancer group was lower than that of the precancerous lesion group, but there was no significant difference in serum PGⅡ between the two groups (P > 0.05); serum G-17 and CDH-17 levels were higher than those of the precancerous lesion group (P < 0.05). There was no statistically significant difference in the diagnostic coincidence rates of serum PGI, G-17, and CDH-17 alone (P > 0.05). The sensitivity, specificity and accuracy of serum PGⅠ, G-17, and CDH-17 combined with narrow-band imaging magnifying endoscopy in the diagnosis of early gastric cancer and precancerous lesions were higher than those of any serum index alone (PGⅠ/G-17/CDH-17) or narrowband imaging magnifying endoscopy alone (P < 0.05).

CONCLUSION

The detection of serum PG, G-17, and CDH-17 combined with narrow-band imaging magnifying endoscopy has high sensitivity, specificity, and accuracy in the differential diagnosis of early gastric cancer and precancerous lesions.

Current and Future Perspectives in the Diagnosis and Management of Helicobacter pylori Infection

Helicobacter pylori (Hp) is a prevalent organism infecting almost half the global population. It is a significant concern, given its associated risk of gastric cancer, which is the third leading cause of cancer death globally. Infection can be asymptomatic or present with dyspeptic symptoms. It may also present with alarm symptoms in the case of progression to cancer. Diagnosis can be achieved non-invasively (breath tests, stool studies, or serology) or invasively (rapid urease test, biopsy, or culture). Treatment involves acid suppression and regimens containing several antibiotics and is guided by resistance rates. Eradication is essential, as it lowers the risk of complications and progression to cancer. Follow-up after eradication is similarly important, as the risk of cancer progression remains. There have been many recent advances in both diagnosis and treatment of Hp. In particular, biosensors may be effective diagnostic tools, and nanotechnology, vaccines, and potassium-competitive acid blockers may prove effective in enhancing eradication rates.

Traditional and Modern Diagnostic Approaches in Diagnosing Pediatric Helicobacter pylori Infection

Helicobacter pylori (H. pylori) is the most common bacterial infection worldwide, is usually acquired during childhood and is related to gastric carcinogenesis during adulthood. Therefore, its early proper diagnosis and subsequent successful eradication represent the cornerstones of gastric cancer prevention. The aim of this narrative review was to assess traditional and modern diagnostic methods in terms of H. pylori diagnosis. Several invasive and non-invasive methods were described, each with its pros and cons. The invasive diagnostic methods comprise endoscopy with biopsy, rapid urease tests, histopathological exams, cultures and biopsy-based molecular tests. Among these, probably the most available, accurate and cost-effective test remains histology, albeit molecular tests definitely remain the most accurate despite their high costs. The non-invasive tests consist of urea breath tests, serology, stool antigens and non-invasive molecular tests. Urea breath tests and stool antigens are the most useful in clinical practice both for the diagnosis of H. pylori infection and for monitoring the eradication of this infection after therapy. The challenges related to accurate diagnosis lead to a choice that must be based on H. pylori virulence, environmental factors and host peculiarities.

Low serum pepsinogen II levels are closely linked with a risk of metabolic syndrome among healthy individuals with asymptomatic Helicobacter pylori infection: a cross-sectional study

Aim: Helicobacter pylori (Hp) infection has a connection with metabolic syndrome (MetS). Pepsinogen II (PGII) is a marker for gastric epithelial function. The present research was aimed at determining the associations among serum PGII levels, Hp infection and MetS in healthy subjects. Methods: This cross-sectional study enrolled 1242 healthy people, including 545 subjects with asymptomatic Hp infection and 697 subjects without Hp infection. Based on the number of MetS components present, subjects with Hp infection were assigned to the following groups: group 1, no component (126 subjects); group 2, one or two components (260 subjects); and group 3, three or more components (159 subjects). Physical measurements and biochemical indices were recorded. Serum PGII levels were recorded using ELISA. SPSS and GraphPad Prism were used for statistical analyses. Results: Among subjects with Hp infection, serum PGII was evidently downregulated in group 3 compared with group 1 (14.95 ± 8.24 vs 17.97 ± 9.08 μg/l; p = 0.015). Serum PGII levels were correlated with an increased risk of MetS (odds ratio: 0.867; 95% CI: 0.772-0.974; p = 0.016), as indicated by the multivariate logistic regression analysis. Grouping subjects with Hp infection according to quartiles of serum PGII levels identified an evident difference in MetS prevalence among the four quartile-based groups (p = 0.047). Conclusions: Among healthy subjects with asymptomatic Hp infection, serum PGII levels were lower in those with MetS than in those without MetS. Serum PGII levels showed an independent and negative correlation with the risk of MetS in healthy subjects with Hp infection.

A deep learning-based model improves diagnosis of early gastric cancer under narrow band imaging endoscopy

BACKGROUND

Diagnosis of early gastric cancer (EGC) under narrow band imaging endoscopy (NBI) is dependent on expertise and skills. We aimed to elucidate whether artificial intelligence (AI) could diagnose EGC under NBI and evaluate the diagnostic assistance of the AI system.

METHODS

In this retrospective diagnostic study, 21,785 NBI images and 20 videos from five centers were divided into a training dataset (13,151 images, 810 patients), an internal validation dataset (7057 images, 283 patients), four external validation datasets (1577 images, 147 patients), and a video validation dataset (20 videos, 20 patients). All the images were labeled manually and used to train an AI system using You look only once v3 (YOLOv3). Next, the diagnostic performance of the AI system and endoscopists were compared and the diagnostic assistance of the AI system was assessed. The accuracy, sensitivity, specificity, and AUC were primary outcomes.

RESULTS

The AI system diagnosed EGCs on validation datasets with AUCs of 0.888-0.951 and diagnosed all the EGCs (100.0%) in video dataset. The AI system achieved better diagnostic performance (accuracy, 93.2%, 95% CI, 90.0-94.9%) than senior (85.9%, 95% CI, 84.2-87.4%) and junior (79.5%, 95% CI, 77.8-81.0%) endoscopists. The AI system significantly enhanced the performance of endoscopists in senior (89.4%, 95% CI, 87.9-90.7%) and junior (84.9%, 95% CI, 83.4-86.3%) endoscopists.

CONCLUSION

The NBI AI system outperformed the endoscopists and exerted potential assistant impact in EGC identification. Prospective validations are needed to evaluate the clinical reinforce of the system in real clinical practice.

Evolution of Diagnostic Methods for Helicobacter pylori Infections: From Traditional Tests to High Technology, Advanced Sensitivity and Discrimination Tools

Rapid diagnosis and treatment application in the early stages of H. pylori infection plays an important part in inhibiting the transmission of this infection as this bacterium is involved in various gastric pathologies such as gastritis, gastro-duodenal ulcer, and even gastric neoplasia. This review is devoted to a quick overview of conventional and advanced detection techniques successfully applied to the detection of H. pylori in the context of a compelling need to upgrade the standards of the diagnostic methods which are currently being used. Selecting the best diagnostic method implies evaluating different features, the use of one or another test depending on accessibility, laboratories equipment, and the clinical conditions of patients. This paper aims to expose the diagnosis methods for H. pylori that are currently available, highlighting their assets and limitations. The perspectives and the advantages of nanotechnology along with the concept of nano(bio)sensors and the development of lab-on-chip devices as advanced tools for H. pylori detection, differentiation, and discrimination is also presented, by emphasizing multiple advantages: simple, fast, cost-effective, portable, miniaturized, small volume of samples required, highly sensitive, and selective. It is generally accepted that the development of intelligent sensors will completely revolutionize the acquisition procedure and medical decision in the framework of smart healthcare monitoring systems.

Identifying the pre-malignant stomach: from guidelines to practice

Gastric adenocarcinoma develops after stepwise progression from normal mucosa through to adenocarcinoma most commonly after being triggered by Helicobacter pylori (H. pylori) infection. As disease is often diagnosed late, the prognosis for gastric adenocarcinoma is poor. Identifying pre-malignant mucosal lesions such as atrophic gastritis, intestinal metaplasia and dysplasia is one strategy adopted by clinicians to reduce cancer related mortality. Surveillance of high-risk individuals and endoscopic resection of dysplastic lesions is recommended by international and UK guidelines. The early detection and endoscopic management reduce the need for invasive surgery. The advancement of image enhanced endoscopy technology, endoscopic training, risk stratification and histological assessment has proven pivotal to the management of pre-malignant lesions. In this review we outline the development of a high-risk stomach, endoscopic assessment and review practical guidelines on identifying pre-malignant gastric mucosa.

Artificial intelligence in gastroenterology: A state-of-the-art review

The development of artificial intelligence (AI) has increased dramatically in the last 20 years, with clinical applications progressively being explored for most of the medical specialties. The field of gastroenterology and hepatology, substantially reliant on vast amounts of imaging studies, is not an exception. The clinical applications of AI systems in this field include the identification of premalignant or malignant lesions (e.g., identification of dysplasia or esophageal adenocarcinoma in Barrett’s esophagus, pancreatic malignancies), detection of lesions (e.g., polyp identification and classification, small-bowel bleeding lesion on capsule endoscopy, pancreatic cystic lesions), development of objective scoring systems for risk stratification, predicting disease prognosis or treatment response [e.g., determining survival in patients post-resection of hepatocellular carcinoma), determining which patients with inflammatory bowel disease (IBD) will benefit from biologic therapy], or evaluation of metrics such as bowel preparation score or quality of endoscopic examination. The objective of this comprehensive review is to analyze the available AI-related studies pertaining to the entirety of the gastrointestinal tract, including the upper, middle and lower tracts; IBD; the hepatobiliary system; and the pancreas, discussing the findings and clinical applications, as well as outlining the current limitations and future directions in this field.

What Is New in Helicobacter pylori Diagnosis. An Overview

Helicobacter pylori infection remains one of the most prevalent infections worldwide, especially in low-resource countries, and the major risk factor for peptic ulcer and gastric cancer. The “test-and-treat” strategy is recommended by several guidelines and consensus. The choice of testing method is based on patient age, presence of alarm signs and/or symptoms, use of non-steroidal anti-inflammatory drugs, as well as local availability, test reliability, and cost. Culture is the gold standard to detect H. pylori and, possibly, to perform susceptibility testing, however, it requires upper endoscopy and dedicated labs. Recent advances in molecular biology have provided new strategies in detecting infection and antimicrobial resistance without invasive tests. In this review we attempt to offer a comprehensive panorama on the new diagnostic tools and their potential use in clinical settings, in order to accomplish specific recommendations.

Chronic atrophic gastritis: an update on diagnosis

Background and aim

Atrophic gastritis is a precancerous gastric lesion, therefore its early detection is a priority in preventing gastric cancer. The aim of the present paper is to develop a narrative synthesis of the present knowledge on diagnostic methods of chronic atrophic gastritis.

Methods

A literature search was carried out on main databases: PubMed, Hinari, SpringerLink and Scopus (Elsevier) for the period 2000–2020. The searched keywords were: chronic atrophic gastritis, intestinal metaplasia and dysplasia + diagnosis. Inclusion criteria were focused on the articles about the invasive and non-invasive diagnosis of chronic atrophic gastritis and of precancerous gastric lesions, intestinal metaplasia and dysplasia; exclusion criteria were articles published before 2000 and those that did not include the proposed theme.

Results

The search returned 575 papers addressing the topic of precancerous lesions. From these, 60 articles were qualified representative for the materials published on the topic of this synthesis article, being those that met the inclusion criteria. The data emphasize the need to use upper digestive endoscopy with biopsies for the diagnosis of chronic atrophic gastritis. However serological diagnosis is available as alternative mainly recommended in follow up.

Conclusions

There are two main methodological approaches for the evaluation of chronic atrophic gastritis as a precancerous gastric lesions: invasive examination, which requires histological analysis of biopsy samples taken during upper digestive endoscopy, being the “gold standard” for diagnosis, and non-invasive serological examination using markers of gastric function.

Application of Artificial Intelligence in Gastrointestinal Endoscopy

Artificial intelligence (AI), also known as computer-aided diagnosis, is a technology that enables machines to process information and functions at or above human level and has great potential in gastrointestinal endoscopy applications. At present, the research on medical image recognition usually adopts the deep-learning algorithm based on the convolutional neural network. AI has been used in gastrointestinal endoscopy including esophagogastroduodenoscopy, capsule endoscopy, colonoscopy, etc. AI can help endoscopic physicians improve the diagnosis rate of various lesions, reduce the rate of missed diagnosis, improve the quality of endoscopy, assess the severity of the disease, and improve the efficiency of endoscopy. The diversity, susceptibility, and imaging specificity of gastrointestinal endoscopic images are all difficulties and challenges on the road to intelligence. We need more large-scale, high-quality, multicenter prospective studies to explore the clinical applicability of AI, and ethical issues need to be taken into account.

The endoscopic predictors of Helicobacter pylori status: a meta-analysis of diagnostic performance

Objective:

The endoscopic findings associated with Helicobacter pylori–naïve status, current infection or past infection are an area of ongoing interest. Previous studies have investigated parameters with a potential diagnostic value. The aim of this study was to perform meta-analysis of the available literature to validate the diagnostic accuracy of mucosal features proposed in the Kyoto classification.

Data sources:

The databases of MEDLINE and Embase, clinicalTrials.gov and the Cochrane Library were systematically searched for relevant studies from October 1999 to October 2019.

Methods:

A bivariate random effects model was used to produce pooled diagnostic accuracy calculations for each of the studied endoscopic findings. Diagnostic odds ratios and sensitivity and specificity characteristics were calculated to identify significant predictors of H pylori status.

Results:

Meta-analysis included 4380 patients in 15 studies. The most significant predictor of an H pylori-naïve status was a regular arrangement of collecting venules (diagnostic odds ratio 55.0, sensitivity 78.3%, specificity 93.8%). Predictors of active H pylori infection were mucosal oedema (18.1, 63.7%, 91.1%) and diffuse redness (14.4, 66.5%, 89.0%). Map-like redness had high specificity for previous H pylori eradication (99.0%), but poor specificity (13.0%).

Conclusion:

The regular arrangement of collecting venules, mucosal oedema, diffuse redness and map-like redness are important endoscopic findings for determining H pylori status. This meta-analysis provides a tentative basis for developing future endoscopic classification systems.

Convolutional neural network for the diagnosis of early gastric cancer based on magnifying narrow band imaging

BACKGROUND

Magnifying endoscopy with narrow band imaging (M-NBI) has been applied to examine early gastric cancer by observing microvascular architecture and microsurface structure of gastric mucosal lesions. However, the diagnostic efficacy of non-experts in differentiating early gastric cancer from non-cancerous lesions by M-NBI remained far from satisfactory. In this study, we developed a new system based on convolutional neural network (CNN) to analyze gastric mucosal lesions observed by M-NBI.

METHODS

A total of 386 images of non-cancerous lesions and 1702 images of early gastric cancer were collected to train and establish a CNN model (Inception-v3). Then a total of 341 endoscopic images (171 non-cancerous lesions and 170 early gastric cancer) were selected to evaluate the diagnostic capabilities of CNN and endoscopists. Primary outcome measures included diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value.

RESULTS

The sensitivity, specificity, and accuracy of CNN system in the diagnosis of early gastric cancer were 91.18%, 90.64%, and 90.91%, respectively. No significant difference was spotted in the specificity and accuracy of diagnosis between CNN and experts. However, the diagnostic sensitivity of CNN was significantly higher than that of the experts. Furthermore, the diagnostic sensitivity, specificity and accuracy of CNN were significantly higher than those of the non-experts.

CONCLUSIONS

Our CNN system showed high accuracy, sensitivity and specificity in the diagnosis of early gastric cancer. It is anticipated that more progress will be made in optimization of the CNN diagnostic system and further development of artificial intelligence in the medical field.

Diagnosis: gastric intestinal metaplasia - what to do next?

PURPOSE OF REVIEW

One of the most vexing problems for gastroenterologists is what actions to take after receiving a histological diagnosis of gastric intestinal metaplasia. We approach the problem by starting with suggesting a biopsy protocol that ensures obtaining the biopsies required for diagnosis, assessing the status of the gastric mucosa, and effective communication with the pathologist and patient.

RECENT FINDINGS

The rediscovery and integration of the long history of gastric damage and repair resulting in pseudopyloric metaplasia (called SPEM) into the thinking of investigators working with animal models of gastric cancer has resulted in improved ability to separate changes associated with benign repair from those associated with inflammation-associated gastric carcinogenesis.

SUMMARY

Gastric intestinal metaplasia is a potential reversible product of injury and repair and not directly connected with carcinogenesis. Intestinal metaplasia is a biomarker for prior gastric injury and repair. The risk of gastric cancer is best assessed in relation to the severity, extent, and, most importantly, the cause of the atrophic changes.

Review: Diagnosis of Helicobacter pylori infection

Endoscopic imaging of the stomach is improving. In addition to narrow band imaging, other methods, for example, blue light imaging and linked color imaging, are now available and can be combined with artificial intelligence systems to obtain information on the gastric mucosa and detect early gastric cancer. Immunohistochemistry is only recommended as an ancillary stain in case of chronic active gastritis without Helicobacter pylori detection by standard staining, and recommendations to exclude false negative H. pylori results have been made. Molecular methods using real-time PCR, droplet digital PCR, or amplification refractory mutation system PCR have shown a high accuracy, both for detecting H. pylori and for clarithromycin susceptibility testing, and can now be used in clinical practice for targeted therapy. The most reliable non-invasive test remains the ¹³ C-urea breath test. Large data sets show that DOB values are higher in women and that the cut-off for positivity could be decreased to 2.74 DOB. Stool antigen tests using monoclonal antibodies are widely used and may be a good alternative to UBT, particularly in countries with a high prevalence of H. pylori infection. Attempts to improve serology by looking at specific immunodominant antigens to distinguish current and past infection have been made. The interest of Gastropanel^® which also tests pepsinogen levels was confirmed.