Pulmonary nodule analysis method and device based on ternary capsule network algorithm, and storage medium

Abstract

The invention relates to a pulmonary nodule analysis method and device based on a ternary capsule network algorithm, and a storage medium. The method comprises the following steps: constructing a pulmonary nodule analysis model based on the ternary capsule network algorithm; acquiring a to-be-analyzed image; carrying out single capsule network module learning, and training a capsule network intelligent agent; performing ternary capsule network module learning, and optimizing a capsule network agent based on ternary capsule network loss; based on the learned and optimized capsule network agent, analyzing the CT image, and giving a classification result of the pulmonary nodules, namely obtaining signs of the pulmonary nodules of the patient; determining a data analysis result of the to-be-analyzed image according to the classification result, and outputting the data analysis result through a result determination module. Compared with the prior art, the method has the advantages of improving the analysis accuracy of the pulmonary nodules and the like.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a pulmonary nodule analysis method, device and storage medium based on a ternary capsule network algorithm. Background technique [0002] With the development of computer-aided technology, more and more computer-aided equipment is used in the medical field to reduce the work intensity of doctors. Doctors observe and analyze patients' body images manually. With the enhancement of people's health awareness, the demand for lung imaging examination and diagnosis is increasing year by year. In the field of medical image analysis, the main difficulties at present include the following: (1) The sample labeling is complex, the signs of lesions in medical images are complex and diverse, and it is difficult to distinguish different types of nodules. Identification and labeling require professional knowledge and rich experience. Experience; this complex labeling process ma...

AI Technical Summary

Problems solved by technology

In the field of medical image analysis, the main difficulties at present include the following: (1) The sample labeling is complex, the signs of lesions in medical images are complex and diverse, and it is difficult to distinguish different types of nodules. Identification and labeling require professional knowledge and rich experience. Experience; this complex labeling process makes the reader prone to fatigue, resulting in unstable diagnostic results, so each lesion requires multiple experts to compare with different time periods, resulting in high costs

(2) There are not enough radiologists in the hospital. The doctors have a heavy task of reading films every day, and they cannot spare time for sample labeling, resulting in insufficient samples in the field of medical image analysis and research.

However, imaging experts cannot spare a lot of time for sample labeling, resulting in insufficient samples and low accuracy in the field of medical image analysis research

Images