Construction method of tumor local control prediction model, prediction method and electronic equipment

Abstract

The invention discloses a tumor local control prediction model construction method, a prediction method and electronic equipment. The model construction method comprises the following steps: acquiring data of screening clinical factors before treatment of a lung cancer patient subjected to stereotactic radiotherapy, data of screening dosimetry factors before treatment, a medical image before treatment and a tumor state after treatment; based on the medical image, obtaining a radiomics score about the medical image; taking the data of the screened clinical factors, the data of the screened dosimetry factors and the radiomics score as input of a comprehensive model, the tumor state after treatment as output of the comprehensive model, training the comprehensive model, and obtaining the comprehensive model. According to the method, all tumor characteristics are comprehensively considered, radiomics characteristics, clinical factors and dosimetry factors are introduced to establish a local control model for predicting one year after primary and metastatic lung cancer patients are subjected to SBRT treatment, and the local control prediction accuracy of one year after the lung cancer patients are subjected to SBRT treatment is greatly improved.

Description

technical field [0001] The invention relates to the related technical field of medical data processing, in particular to a construction method, a prediction method and electronic equipment for a local tumor control prediction model. Background technique [0002] With the advancement of radiotherapy technology, stereotactic radiotherapy (SBRT) has been further used in patients with early primary lung cancer who cannot tolerate surgery and are unwilling to undergo surgery due to various medical comorbidities, and can be used in advanced Radical or neoadjuvant or adjuvant therapy for primary lung cancer or metastatic lung cancer. This precise approach uses high doses to ablate the tumor and low doses to protect surrounding tissue. The local tumor control rate of lung cancer patients after SBRT is considerable, and the toxicity of normal tissues is small, but some patients have poor local tumor control. Computed tomography (CT), 18F-fluorodeoxyglucose / positron emission tomogra...

AI Technical Summary

Problems solved by technology

[0003] Based on this, it is necessary to provide a method for constructing a local tumor control prediction model, a prediction method, and electronic equipment for the inaccurate prediction of local tumor control in patients with lung cancer treated with stereotactic radiotherapy in the prior art.

Images