Chest surgery examination data arrangement method

Abstract

The invention relates to the field of medical data, in particular to a thoracic surgery examination data arrangement method, which comprises the following steps of: performing K-SVD (K-Singular Value Decomposition) decomposition on a preset number of chest radiograph images without diseases and diseased chest radiograph images to obtain a normal dictionary, a normal sparse image set, an abnormal dictionary and an abnormal sparse image set, obtaining a normal dictionary vector set and an abnormal dictionary vector set according to the heat values of the normal dictionary, the abnormal dictionary and the dictionary vectors, and carrying out K-SVD decomposition on all chest radiograph images to obtain a normal dictionary vector set and an abnormal dictionary vector set; and obtaining a final dictionary and a final sparse image set according to the normal dictionary vector set, the abnormal dictionary vector set and the heat value of each dictionary vector, and storing and classifying the final dictionary and the final sparse image set. According to the invention, the chest radiograph images are convenient to read, write and store after being arranged, and related data features are convenient to query, so that doctors can quickly analyze illness conditions, and the reception efficiency of hospitals is improved.

Description

technical field [0001] The invention relates to the field of medical data, in particular to a method for sorting out thoracic surgery examination data. Background technique [0002] When a hospital conducts a physical examination on a patient or a doctor detects a patient's chest disease or respiratory disease, it usually obtains the patient's chest X-ray. With the long-term reception of the hospital, there will be a large number of chest X-ray images in the hospital database. These chest radiographs are of great significance for patients' follow-up visits and big data analysis and mining of medical data. Usually, it is necessary to query, read and store a large number of chest radiograph images to obtain the desired chest radiograph data features. However, due to the large amount of chest radiograph data and the lack of data collation and analysis, the efficiency of query, reading and storage Low, especially when it is necessary to obtain and analyze certain data features ...

AI Technical Summary

Problems solved by technology

Usually, it is necessary to query, read and store a large number of chest radiograph images to obtain the desired chest radiograph data features. However, due to the large amount of chest radiograph data and the lack of data collation and analysis, the efficiency of query, reading and storage Low, especially when it is necessary to obtain and analyze certain data features in a large number of chest radiographs, such as analyzing the situation of different periods of pulmonary effusion, the acquisition efficiency of these data features will be lower, so that doctors can obtain the desired data Features are like looking for a needle in a haystack

Images