Establishing method of preoperative prediction model for lung cancer cell KI-67 expression index

Abstract

The invention provides an establishing method of a preoperative prediction model for the lung cancer cell KI-67 expression index. The establishing method comprises the following steps: (1) screening cases, thus obtaining patients meeting the standards; (2) detecting the KI-67 expression index of the patients; (3) carrying out CT image scanning and three-dimensional reconstruction on the lungs of the patients, thus obtaining CT parameter data and three-dimensional images; and (4) carrying out statistical processing and analysis and cross validation on the CT parameter data and the KI-67 expression index, and establishing the prediction model for KI-67. According to the establishing method, the relevant CT parameters measured in the GGO (ground-glass opacity) three-dimensional reconstruction model and having good objectivity and accuracy are associated with the lung cancer cell KI-67 expression index in pathological samples innovatively, and the multiple regression model for predicting KI-67 LI by adopting the three-dimensional reconstruction parameters is established by researching the quantization coherence of the relevant CT parameters and the lung cancer cell KI-67 expression index.

Description

technical field [0001] The invention relates to the field of medicine, in particular to a method for establishing a preoperative prediction model based on three-dimensional measurement of imaging parameters KI-67 expression index of lung cancer cells. Background technique [0002] With the development and popularization of high-resolution CT (High resolution CT, HRCT), the detection rate of pulmonary ground-glass opacity (GGO) has increased significantly. Domestic and foreign studies have shown that focal GGO is mostly an early lesion of lung adenocarcinoma. GGO is a non-specific lesion, which can be the manifestation of various diseases on CT. It is a focal shadow of the lungs found on HRCT. It is usually described by scholars as a cloudy shadow with increased lung density. Vascular structure image. However, it is generally accepted at home and abroad that it is more prone to early lung tumors. A number of domestic and foreign studies and clinicopathological data have su...

AI Technical Summary

Problems solved by technology

The analysis of previous diagnostic methods was limited to the level of imaging, and did not involve the evaluation of the pathological level as the gold standard for diagnosis, making the diagnosis too subjective and not accurate

[0005] Therefore, if the KI-67 index can be correlated with relevant CT parameters to obtain a preoperative prediction model, it is of great practical value, but in the field of existing technologies, this area is still blank

Images