Assessing the severity of atrophic gastritis

Algorithm improvement of neural network in endoscopic image recognition of upper digestive tract system

The development of effective gastrointestinal diseases computer‐aided diagnosis tools and automatic image quality assessment algorithms is very important to improve the effectiveness of diagnosis and treatment. In order to further study the application of neural network algorithm in the endoscopic image of upper digestive tract, improve the efficiency of neural network algorithm in the field of endoscopic image. In this study, neural network algorithms were used to identify endoscopic images of the upper digestive tract. 1335 cases with upper gastrointestinal endoscopic images were collected. After the data was enlarged, it was randomly divided into training set and test set according to the proportion, and the obtained training set was input. After convolutional neural network training, an algorithm model was established in the institute. 1653 test set data samples were input into the neural network to verify the accuracy. Finally, the accuracy of the neural root network model constructed in this study reached 0.0942. Through horizontal comparison, it can be concluded that the neural network model proposed in this study not only has a higher accuracy rate, but also is better than the current existing related neural network algorithms. Based on the above experimental verification, it can be concluded that the upper gastrointestinal endoscopic image recognition algorithm based on neural network proposed in this study can more accurately and effectively identify the lesions in the upper gastrointestinal endoscopic images.

No higher risk for colorectal cancer in atrophic gastritis-related hypergastrinemia

BACKGROUND

Atrophic gastritis of the corporal mucosa is a frequent cause of hypergastrinemia. Hypergastrinemia is implicated in colorectal cancer development.

AIM

To assess whether hypergastrinemic atrophic gastritis is associated with a higher risk of neoplastic colorectal lesions.

METHODS

Among 441 hypergastrinemic atrophic gastritis patients, 160 who were aged >40 and underwent colonoscopy for anaemia, diarrhoea or colorectal cancer-screening were retrospectively selected. Each patient was age- and gender-matched with a normogastrinemic control with healthy stomach. Controls had colonoscopy, gastroscopy with biopsies and gastrin assessment.

RESULTS

160 hypergastrinemic atrophic gastritis patients and 160 controls were included. 28 atrophic gastritis patients and 36 controls had neoplastic colorectal lesions (p=0.33). Patients and controls did not differ for frequency of colorectal adenomas (10.6% vs. 13.1%, p=0.60) or cancer (6.9% vs. 9.4%, p=0.54). Hypergastrinemic atrophic gastritis was not associated with a higher probability of developing colorectal cancer (OR 1.03, 95% CI 0.34-3.16). Age >50 years (OR 3.86) but not hypergastrinemia (OR 0.61) was associated with colorectal cancer.

CONCLUSIONS

Hypergastrinemic atrophic gastritis is not associated with higher risk for colorectal cancer. Atrophic gastritis-related hypergastrinemia is not associated with an increased risk of neoplastic colorectal lesions. Closer surveillance of colonic neoplasia in atrophic gastritis patients seems not appropriate.

HLA-DRB1*03 and DRB1*04 are associated with atrophic gastritis in an Italian population

BACKGROUND

Atrophic gastritis (AG) is often considered an autoimmune disorder and is associated with other autoimmune diseases. HLA-DRB1 alleles are often associated with autoimmune diseases, however HLA-DRB1 genotyping data in AG patients are lacking. The objective of the study was to evaluate the prevalence of HLA-DRB1 in AG patients.

METHODS

The occurrence of HLA-DRB1 alleles was assessed in 89 Italian AG patients (69.1% female) and 313 controls (47.3% females). Genomic DNA was extracted from peripheral venous blood, PCR-coamplified for HLA-DRB1 and typed using a reverse line-blot assay.

RESULTS

Compared to controls, prevalence of HLA-DRB1*03 (28.1% vs. 15.9%, p=0.01) and HLA-DRB1*04 (25.8% vs. 14.4%, p=0.01) was greater in AG patients, conferring an OR of 2.05 and 2.07, respectively. HLA-DRB1*01 occurred more frequently in controls than in AG patients (11.5% vs. 3.4%, p=0.01) conferring an OR of 0.27. AG patients carrying the HLA-DRB1*03 or *04 alleles were characterised by having more frequently autoimmune thyroid disease (70.4% vs. 42.2%, p=0.01) and intestinal metaplasia (86.4% vs. 62.2%, p=0.01).

CONCLUSIONS

In our population, over 50% of AG patients carry the HLA-DRB1*03 or *04 alleles associated with autoimmune diseases, suggesting that this subset of AG patients has a genetic predisposition to autoimmunity.

Is it possible to clinically differentiate erosive from nonerosive reflux disease patients? A study using an artificial neural networks-assisted algorithm

BACKGROUND

The use of either symptom questionnaires or artificial neural networks (ANNs) has proven to improve the accuracy in diagnosing gastroesophageal reflux disease (GERD). However, the differentiation between the erosive and nonerosive reflux disease based upon symptoms at presentation still remains inconclusive.

AIM

To assess the capability of a combined approach, that is, the use of a novel GERD questionnaire - the QUestionario Italiano Diagnostico (QUID) questionnaire - and of an ANNs-assisted algorithm, to discriminate between nonerosive gastroesophageal reflux disease (NERD) and erosive esophagitis (EE) patients.

METHODS

Five hundred and fifty-seven adult outpatients with typical GERD symptoms and 94 asymptomatic adult patients, were submitted to the QUID questionnaire. GERD patients were then submitted to upper gastrointestinal endoscopy to differentiate them between EE and NERD patients.

RESULTS

The QUID score resulted significantly (P<0.001) higher in GERD patients versus controls, but it was not statistically significantly different between EE and NERD patients. ANNs assisted diagnosis had greater specificity, sensitivity and accuracy compared with the linear discriminant analysis only to differentiate GERD patients from controls. However, no single technique was able to satisfactorily discriminate between EE and NERD patients.

CONCLUSION

Our study suggests that the combination between QUID questionnaire and an ANNs-assisted algorithm is useful only to differentiate GERD patients from healthy individuals but fails to further discriminate erosive from nonerosive patients.

Helicobacter pylori immunoproteomics in gastric cancer and gastritis of the carcinoma phenotype

Helicobacter pylori infection is linked to the development of gastric cancer. Atrophic body gastritis is considered the first important step in the histogenesis of such neoplasia. H. pylori infection is involved in the induction of atrophic body gastritis, but documentation of H. pylori infection is difficult because of the progressive disappearance of the bacterium. Host-pathogen interactions may be investigated by means of immunoproteomics, which provides global information regarding the host humoral response to H. pylori infection and allows the identification of relevant specific and nonspecific antigens, and can be used for diagnostic or prognostic purposes. In the present review, we describe how several research groups used H. pylori immunoproteomics to investigate highly immunoreactive bacterial antigens related to the development of gastric cancer.