Chronic obstructive pulmonary disease prediction method based on reconstructed airway tree images

Abstract

The invention provides a chronic obstructive pulmonary disease prediction method based on reconstructed airway tree images and relates to the medical image processing technology field. The method comprises steps that firstly, multi-layer CT image files of COPD patients and healthy people from the same hospital are collected, reconstructed airway tree images of the healthy people and the COPD patients are generated, different perspectives are changed to take a screenshot of the reconstructed airway tree images of the healthy person and COPD patients, the redundant background information of theairway tree images after screenshot taking is then removed, based on the convolutional neural network, training and classification are performed, and whether a test set has some COPD patients is predicted; and lastly, cross validation of an image set after reconstructed airway tree screenshot is performed, and accuracy of the prediction result is guaranteed. The method is advantaged in that the method is taken as a technical means to initially screen the disease, the method is accurate and efficient, misdiagnosis and missed diagnosis are effectively avoided, the complex process of lung function tests is further omitted, and the workload of the hospital is greatly reduced.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for predicting chronic obstructive pulmonary disease based on reconstructed airway tree images. Background technique [0002] Chronic Obstructive Pulmonary Disease (COPD) is a common respiratory disease that seriously endangers the physical and mental health of patients and has become an important problem that global public health must face. Therefore, effective diagnostic methods are also extremely important. [0003] In traditional clinical testing, pulmonary function tests (Pulmonary Function Tests, PFTs) are often used, and the ratio of forced expiratory volume in one second (FEV1) to forced vital capacity (FVC) after bronchodilation is less than 70% is used as the standard for diagnosis , PFTs measure the macroscopic functional parameters of the whole lung, and cannot provide structural information of the COPD lung airway tree. In addition, the ra...

AI Technical Summary

Problems solved by technology

[0003] In traditional clinical testing, pulmonary function tests (Pulmonary Function Tests, PFTs) are often used, and the ratio of forced expiratory volume in one second (FEV1) to forced vital capacity (FVC) after bronchodilation is less than 70% is used as the standard for diagnosis , PFTs measure the macroscopic functional parameters of the whole lung, and cannot provide structural information on the airway tree of the COPD lung

In addition, the ratio of FEV1 to FVC in healthy people decreases with age, so this method is also prone to misdiagnosis and missed diagnosis

[0004] At the same time, the pulmonary function examination process in the hospital is also very cumbersome, and the steps are lengthy, generally including ventilation function, respiratory regulation and pulmonary circulation function.

The testing standards are also often different. The clinical diagnosis of COPD with pulmonary function tests requires a comprehensive assessment based on the patient’s symptoms and health status. Some severe patients cannot tolerate it, and it is difficult to distinguish it from airflow limitation caused by other diseases.

At the same time, medical staff and workers have limited understanding of relevant knowledge, which greatly limits clinical application

[0005] In summary, the current diagnostic methods for COPD have many defects, which increase the workload of doctors and the suffering of patients, and the diagnostic results are not satisfactory

Images