Method and system for assisting in screening lung cancer based on artificial intelligence

Abstract

A method and system based on artificial intelligence to assist lung cancer screening. By generating a model for distinguishing lung cancer and a benign and malignant evaluation model for pulmonary nodules, the basic information, basic health information, general living conditions, and current status of the subject are collected in real time during online detection. Respiratory symptoms, chronic disease and lung disease history and smoking status, and the risk value of cancer and the probability of malignancy of nodules were detected through the identification model of lung cancer and the evaluation model of benign and malignant pulmonary nodules. The present invention fully utilizes various related features, divides high- and low-risk groups of lung cancer and evaluates benign and malignant pulmonary nodules through multi-dimensional information, and can help to distinguish high-risk groups.

Description

technical field [0001] The present invention relates to a technology in the medical and health field, in particular to a method and system for assisting lung cancer screening based on artificial intelligence. Background technique [0002] The judgment of high-risk groups for lung cancer has been studied. Low-dose computed tomography (LDCT) examination is an effective method for screening lung cancer in high-risk groups of lung cancer. Early diagnosis of lung cancer can effectively improve prognosis and reduce mortality. Accurately identifying high-risk groups can not only improve screening efficiency, but also reduce the waste of medical resources and prevent low-risk groups from receiving unnecessary radiation. Currently, the National Comprehensive Cancer Network (NCCN) of the United States defines high-risk groups based on risk factors such as smoking and family history, and lacks quantitative standards. In recent years, studies have established mathematical models for r...

AI Technical Summary

Problems solved by technology

However, the method for distinguishing high- and low-risk groups of lung cancer still needs to be improved. In addition, there is also a lack of effective benign and malignant discriminative models for pulmonary nodules found in CT images of people undergoing screening.

CT interpretation has high requirements for professional level and clinical experience. Large tertiary hospitals have high standards and can meet the needs of screening and diagnosis and treatment. However, in grassroots hospitals, due to the limited experience of doctors, it is easy to cause misdiagnosis and missed diagnosis.

In addition, for lung cancer screening, the degree of digitalization of medical and health care information is relatively low, and the data lacks effective management and integration. It is difficult to effectively use the massive data

Images