Lung cancer prognosis auxiliary evaluation method and system based on CT radiomics

Abstract

The invention discloses a lung cancer prognosis auxiliary evaluation method and system based on CT imaging omics. The method comprises the steps: collecting original medical images and clinical information of lung cancer patients using radiotherapy, and performing screening; drawing a focus area of an original medical image through high-resolution computed tomography, and extracting radiomics characteristics from the focus area to obtain initial radiomics characteristics; analyzing and screening the preliminary image omics characteristics to obtain target image omics characteristics; and training a prediction model for the target radiomics characteristics in the training set by using a machine learning algorithm, constructing a radiomics evaluation model, and verifying the model in a verification set. According to the method, the radiotherapy effect of the patient can be qualitatively and quantitatively analyzed, so that a doctor is assisted in formulating a personalized treatment scheme and evaluating the survival and recurrence time of the patient, meanwhile, the performance of the obtained radiomics evaluation model is verified, and the accuracy of the radiomics evaluation model is ensured.

Description

technical field [0001] The invention belongs to the technical field of auxiliary assessment of lung cancer prognosis, and in particular relates to a method and system for auxiliary assessment of lung cancer prognosis based on CT radiomics. Background technique [0002] Lung cancer ranks first in the incidence of cancer in the world and is the leading cause of death from cancer. Most of the patients are in the advanced stage when they are diagnosed, and about 60% of the patients are inoperable. Radiation therapy is one of the most important treatments for malignant tumors. 70% of the patients with malignant tumors need to receive radiotherapy at different stages of treatment, but after radiation The overall effective rate after treatment is far from satisfactory. [0003] As a non-invasive method for early diagnosis of tumors, computed tomography (CT) has been widely used in various clinical disease detection and auxiliary diagnosis. It is worth noting that radiomics has be...

AI Technical Summary

Problems solved by technology

[0004] The same lung cancer patients have differences in the appearance of CT imaging lesions, and the differences in the intrinsic heterogeneity of lesions may reveal potential information about the efficacy of radiotherapy in patients. Regarding the sensitivity of lung cancer patients to radiotherapy in related technologies, it has not yet been raised. Therefore, it is of great practical significance to establish an auxiliary evaluation system and method for the efficacy of radiotherapy for lung cancer based on CT radiomics

Images