Machine learning-based bimodal image omics ground glass nodule classification method

Abstract

The invention belongs to the technical field of medical treatment, and discloses a machine learning-based bimodal image omics ground glass nodule classification method, which comprises the following steps of: step 1, case data collection: collecting patients who receive 18F-FDG PET / CT examination due to suspicious ground glass nodules (GGN); step 2, image acquisition and reconstruction: performing image acquisition by adopting a PET / CT (positron emission tomography / computed tomography) imaging instrument; step 3, image feature extraction; and step 4, data processing and analysis. According to the method, the image omics model based on the combination of the PET image and the HRCT image is constructed by applying a machine learning method, the GGN is classified, including pre-infiltration lesion, micro-infiltration adenocarcinoma, infiltration adenocarcinoma and benign lesion, verification and testing, the method is good in robustness, high in accuracy, simple and feasible. According to the method, the functional metabolism information and the physical anatomical information of the molecular level of the focus are integrated, the prediction efficiency of traditional CT parameters and single CT radiomics is effectively improved, and clinical management of the GGN is facilitated.

Description

technical field [0001] The present invention relates to the field of medical technology, and more specifically, it relates to a method for classifying ground-glass nodules based on dual-mode radiomics based on machine learning. Background technique [0002] Lung cancer is the leading cause of cancer-related death worldwide, especially in China, where the incidence of lung cancer is increasing rapidly. It is estimated that the mortality rate of lung cancer in China will increase by about 40% from 2015 to 2030. Early identification and individualized management are the key to improving the prognosis of lung cancer patients. With the significant increase in the detection of many asymptomatic pulmonary nodules and the change of the epidemiological trend of lung cancer in China, the diagnosis and differential diagnosis of ground glass nodules (GGN) have become a great challenge for clinicians. HRCT is recognized as a routine method for differentiating GGN. However, due to the ov...

AI Technical Summary

Problems solved by technology

In addition, the traditional radiomics feature dimensionality reduction method mostly uses LASSO regression, which is mainly based on a linear model and does not consider nonlinear factors.

Images