An Algorithm for Inferring Lung Cancer Genotyping Using PET/CT Images

Abstract

A calculation method that uses PET / CT images to calculate the genotype of lung cancer. The outline of the lesion is drawn layer by layer, and then the two-dimensional tumor area is reorganized into a three-dimensional volume to generate a three-dimensional volume of interest, and feature data are extracted from it. Once the lesion (tumor) area is determined, the image features can be extracted, the radiomics data can be directly extracted and analyzed, and the radiogenomics data model can be established. The random forest algorithm uses the Pearson correlation coefficient to improve the model prediction, calculates the genotype of lung cancer according to deep learning, and improves the diagnostic efficiency of lung cancer.

Description

technical field [0001] The invention relates to the technical field of tumor detection, in particular to a method for calculating the genotype of lung cancer by using PET / CT images based on a deep learning model. Background technique [0002] Worldwide, tumors are one of the leading causes of death, and the diagnosis of tumors has always been a key issue in the field of cancer research. How to judge the disease condition of tumor patients more accurately has become a common goal of medical researchers, which plays a vital role in saving medical resources and improving patient satisfaction. In recent years, PET / CT imaging technology has been used in the diagnosis of malignant tumors, tumor staging, etc., and has been promoted to a certain extent due to its high accuracy. [0003] Radiomics, also known as radiomics, refers to the extraction and analysis of a large number of quantitative imaging features using methods such as computed tomography (CT), positron emission tomogra...

AI Technical Summary

Problems solved by technology

The inventor discovered during the research and development process that at present, for the diagnosis of tumors, the chest CT is firstly used for inspection. If the chest CT finds that there is a space occupying the chest, and when the area is large and the shape is irregular, it is possible to clarify the nature of the space occupying. CT is strengthened for judgment, and at the same time, biopsy can be performed for relevant pathological examination to determine the type and degree of differentiation of the tumor, and genotyping can be achieved through sequencing technology, which takes a long time for detection and causes certain damage to the patient's body

Images