A liver cancer radiomics data processing method, system, device and storage medium

Abstract

The invention discloses a liver cancer radiomics data processing method, system, device and storage medium. The method includes acquiring an upper abdominal CT image of a liver cancer patient, calculating radiomics data corresponding to the upper abdominal CT image, and calculating the obtained radiomics data. A linear combination of the above multiple radiomics feature values, and according to the relationship between the predicted value and the preset threshold value, divide the liver cancer patients into the TACE responder group or TACE non-response group and other steps. The radiomics technology used in the present invention can extract tumor characteristic information contained in CT images from a three-dimensional perspective, which overcomes the shortcomings of existing methods that do not consider tumor heterogeneity; The distinction between responding group and non-responsive group has good clinical guiding significance and provides better decision-making reference for clinicians. The invention is widely used in the technical field of data processing.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a data processing method, system, device and storage medium of liver cancer radiomics. Background technique [0002] Primary liver cancer is currently the sixth most common malignant tumor in the world, and its fatality rate also ranks third in the world. Since the symptoms of early liver cancer are not typical, and most patients have no obvious discomfort, most patients with liver cancer are already in the advanced stage of tumor when they are diagnosed, and even have vascular invasion or distant metastasis, and have lost radical curative effects such as surgical resection or liver transplantation. treatment approach. [0003] According to the pathological type, primary liver cancer can be divided into three types, namely, hepatocellular carcinoma, intrahepatic cholangiocarcinoma and mixed liver cancer, among which hepatocellular carcinoma accounts for 80% of al...

AI Technical Summary

Problems solved by technology

The prior art has the following deficiencies: the differences in age, gender and physiological factors between individual patients make some biochemical indicators measured clinically different from the actual values, which affects the prediction accuracy; the measurement methods of biochemical indicators such as blood biochemical values ​​have not Standardization makes the prediction results in different environments unstable; the characteristics reflected by the existing technical means are relatively single, and cannot fully reflect the characteristics of tumor heterogeneity; during the measurement process using electronic counters, there may be multiple variables that affect biochemical Result authenticity; tumor heterogeneity difficult to quantify

Images