Method for constructing lymph node metastasis prediction model of breast cancer patient based on radiomics

Abstract

The invention discloses a method for constructing a lymph node metastasis prediction model of a breast cancer patient based on radiomics. The method comprises the following steps: acquiring magnetic resonance image data and clinical feature data of the patient; extracting image features based on the magnetic resonance image data; screening the image features by using a random forest algorithm to obtain a plurality of key image features, and establishing an image feature prediction model based on the key image features by using a support vector machine algorithm; performing single-factor analysis screening on the clinical feature data to obtain key clinical features, and establishing a clinical feature prediction model according to the key clinical features by adopting a support vector machine algorithm; and establishing a lymph node metastasis comprehensive prediction model according to the key image features and the key clinical features by adopting a support vector machine algorithm. According to the embodiment, the model is established by adopting the random forest algorithm and the support vector machine algorithm, the prediction model can be established based on the structure risk minimum principle, and the problem of over-learning can be avoided, so that the constructed prediction model is more stable and accurate.

Description

technical field [0001] The invention relates to the field of biomedicine, in particular to a method for constructing a prediction model of lymph node metastasis of breast cancer patients based on radiomics. Background technique [0002] Breast cancer is the most common malignant tumor in women worldwide and the second leading cause of cancer death in women after lung cancer. Invasive breast cancer is the main pathological type of breast cancer, and axillary lymph node metastasis is a common metastatic location of invasive breast cancer. About 40% of invasive breast cancer patients are accompanied by ipsilateral axillary lymph node metastasis when they are first diagnosed. The greater the number of lymph nodes, the shorter the disease-free survival and overall survival of patients. Therefore, the presence or absence of axillary lymph node metastasis in patients with invasive breast cancer is of great significance to the staging, treatment and prognosis of the disease, and it...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for constructing a prediction model of lymph node metastasis in breast cancer patients based on radiomics to solve the technical problem that it is difficult to construct a stable and accurate prediction model for lymph node metastasis in the existing lymph node prediction model construction method

Images