Multi-modal information fusion system for esophageal functional diseases diagnosis system

Abstract

The invention discloses a multi-modal information fusion system for an esophageal functional diseases diagnosis system. The system is configured in a computer. The multi-modal information fusion system includes a single-modal information input layer, a single-modal information conditional probability calculation layer, a multi-modal information fusion probability calculation layer and a classification decision layer which are connected with one another in a step-by-step manner; a corresponding Bayesian reasoning model is configured in each single-modal information conditional probability calculation unit; m kinds of esophagus functional diseases are defined in the Bayesian reasoning model; m conditional probability tables are configured in the i-th Bayesian reasoning model, wherein the conditional probability table Eij stores the conditional probability that the j-th esophagus functional disease is expressed as the i-th kind of single-mode information; the multimodal information fusionprobability calculation layer is used to calculate multimodal information fusion probabilities; and the classification decision layer is used to determine the final categories of esophageal functional diseases. With the system of the invention adopted, multi-modal information fusion can be realized for the diagnosis of the esophageal functional diseases, and the accuracy of the diagnosis can be improved.

Description

technical field [0001] The invention relates to the technical field of medical devices, in particular to a multimodal information fusion system used in a diagnosis system for esophageal functional diseases. Background technique [0002] Functional esophageal disease refers to a type of esophageal disease whose clinical manifestations are symptoms in the esophagus or adjacent areas, and no organic lesions are found by biochemical, imaging, and endoscopic examinations, or the clinical symptoms cannot be explained by organic diseases . According to epidemiological statistics, the annual average incidence rate of esophageal functional diseases worldwide is 25%. In China, at least 200 million people have symptoms related to esophageal functional diseases, and the number of patients is increasing year by year. 50-60% of these patients need to receive accurate diagnosis and symptomatic treatment. The most typical esophageal functional diseases mainly include: (1) non-erosive gast...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the above-mentioned prior art, the present invention provides a multimodal information fusion system for esophageal functional disease diagnosis system, which solves the problem of low diagnostic accuracy in diagnosing esophageal functional disease based on single-modal features in the prior art. High technical problems, can achieve multi-modal information fusion to diagnose esophageal functional diseases, and can improve diagnostic accuracy

Images