System and method for realizing risk classification of pulmonary nodules in computer software system

Abstract

The present invention relates to a system and method for realizing the classification of pulmonary nodules risk degree in a computer software system, including an image CT value density distribution calculation module, which is used to calculate CT value density distribution characteristics according to unsupervised clustering; classification of pulmonary nodule risk degree The module is used to implement the training and classification of the risk degree of pulmonary nodules using the CT value density distribution feature of the pulmonary nodules according to the supervised machine learning model, and also includes a system for implementing the above method. Using the system and method for judging the degree of risk of pulmonary nodules in the computer software system, to a certain extent, before invasive pathological biopsy, it can be used to assist in judging the benign and malignant of pulmonary nodules from a clinical perspective, thereby improving the accuracy of pathological biopsy; Unnecessary invasive biopsy of patients, avoiding unnecessary CT follow-up of patients, and providing more effective information processing methods for improving the accuracy of lung cancer screening, detection, and diagnosis have a wide range of references.

Description

technical field [0001] The invention relates to the field of identification, in particular to the classification of the risk degree of pulmonary nodules, in particular to a system and method for realizing the classification of the risk degree of pulmonary nodules in a computer software system. Background technique [0002] In recent years, lung CT images have become more and more widely used in the clinical diagnosis of pulmonary nodules. It is of great significance to analyze the risk of pulmonary nodules through lung CT images, especially for the study of early pulmonary nodules. A high-accuracy, clinically meaningful, and robust classification system for the risk of pulmonary nodules has become increasingly important. Due to the complexity of pulmonary nodules, the current pulmonary nodule classification technology based on lung CT image processing lacks completeness. The existing technology is not practical for the classification of pulmonary nodules, and the accuracy o...

AI Technical Summary

Problems solved by technology

Due to the complexity of pulmonary nodules, current pulmonary nodule classification techniques based on lung CT image processing are not complete

The existing technology is not practical for the classification of pulmonary nodules, and the accuracy of the evaluation system for the malignancy of pulmonary nodules is not high, and it lacks practicality in practical applications

Images