Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection.

Automated detection and classification of gastric infections (i.e., ulcer, polyp, esophagitis, and bleeding) through wireless capsule endoscopy (WCE) is still a key challenge. Doctors can identify these endoscopic diseases by using the computer-aided diagnostic (CAD) systems. In this article, a new fully automated system is proposed for the recognition of gastric infections through multi-type features extraction, fusion, and robust features selection. Five key steps are performed-database creation, handcrafted and convolutional neural network (CNN) deep features extraction, a fusion of extracted features, selection of best features using a genetic algorithm (GA), and recognition. In the features extraction step, discrete cosine transform, discrete wavelet transform strong color feature, and VGG16-based CNN features are extracted. Later, these features are fused by simple array concatenation and GA is performed through which best features are selected based on K-Nearest Neighbor fitness function. In the last, best selected features are provided to Ensemble classifier for recognition of gastric diseases. A database is prepared using four datasets-Kvasir, CVC-ClinicDB, Private, and ETIS-LaribPolypDB with four types of gastric infections such as ulcer, polyp, esophagitis, and bleeding. Using this database, proposed technique performs better as compared to existing methods and achieves an accuracy of 96.5%.

Co-infection with Helicobacter pylori and Epstein-Barr virus in benign upper digestive diseases: An endoscopic and serologic pilot study.

BACKGROUND: Some gastric cancers are Epstein-Barr virus associated. AIM: To assess the prevalence of Helicobacter pylori and viral co-infection in benign upper digestive diseases. METHODS: One hundred and four outpatients were included in a prospective endoscopic-serologic study. Epstein-Barr virus immunoglobulin G (IgG), immunoglobulin M and viral capsid antigen titres were assayed with an ELISA test. Helicobacter pylori was determined by the modified Giemsa stain and by IgG-chemiluminescence. RESULTS: The overall prevalence of Helicobacter pylori was 56.7%. Duodenal ulcer patients were infected in 72.5 % of the cases, with the prevalence being 33.3% in functional dyspepsia (p = 0.0008) and 25.8% in reflux patients (p = 0.0001). Epstein-Barr virus IgG was detected in 70.1% of the whole group, 75% of duodenal ulcer patients, 51.2% of functional dyspepsia patients (p = 0.04) and 51.6% of the reflux disease cases (p = 0.04). Co-infection with both agents was detected in 60% of duodenal ulcer patients, 18.1% of functional dyspepsia (p = 0.00014) and 12.9% of reflux disease patients (p = 0.00012). Anti-viral IgG titre displayed a 31.7 ± 3.0 cut-off index in duodenal ulcer, 20.5 ± 3.5 in functional dyspepsia (p = 0.01) and 21.4 ± 3.6 in reflux cases (p = 0.03). CONCLUSIONS: Both Helicobacter pylori and Epstein-Barr virus, and co-infection with these agents, were significantly more prevalent in duodenal ulcer patients than in dyspeptic/reflux patients.