Method for constructing benign and malignant lung tumor prediction model

Abstract

The invention discloses a method for constructing a benign and malignant lung tumor prediction model. The method comprises the following steps that (1) a lung tumor patient sample is selected and computerized tomography (CT) is performed on the lung region of the lung tumor patient so as to acquire the corresponding CT image; (2) the CT image acquired in the step (1) is sketched and the lung lesion region is segmented so as to obtain the marked lesion region; (3) quantitative image features are extracted from the marked lesion region; (4) feature selection is performed by using the Lasso algorithm; and (5) the selected feature data act as the input, parameter optimization is performed on Logistic regression by using the gradient descent algorithm and finally the benign and malignant lung tumor prediction model is obtained by using Logistic training. The method for constructing the benign and malignant lung tumor prediction model is simple, short in time consumption and high in accuracyof the prediction model and can be applied to qualitative diagnosis of the benign and malignant lung tumors.

Description

technical field [0001] The invention belongs to the technical field of medical imaging omics, in particular to a method for constructing a benign and malignant lung tumor prediction model. Background technique [0002] According to the statistics of the American Cancer Society in 2016, lung cancer has the highest cancer mortality rate, among which the incidence and mortality of lung cancer in men are the highest, and the incidence and mortality of lung cancer in women occupy the second place. The onset of lung cancer is generally hidden, and most patients are already in the middle and late stages when they are discovered. The 5-year survival rate of patients detected and treated early can reach more than 80%. It can be seen that the detection of benign and malignant tumors in the early stage is of great significance to the treatment of lung cancer. At present, the main diagnostic method for clinical doctors to determine benign and malignant tumors is through biopsy, which o...

AI Technical Summary

Problems solved by technology

Biopsy can help clinicians make a diagnosis, but the method has obvious disadvantages

First, biopsy is invasive, and it is difficult for patients to accept multiple biopsies, and the long time may delay the patient's treatment

Second, due to the spatiotemporal heterogeneity of tumors, biopsy can only reflect part of the information of the tumor, but not all the information of the tumor

Obviously, it is difficult for doctors to fully tap the big data information contained in the images in this way of using and processing images.

Images