Enhanced CT (Computed Tomography) imageomics feature processing method for upper abdomen of liver cirrhosis patient and application thereof

Abstract

The invention provides a processing method for enhancing CT (Computed Tomography) image omics characteristics of the upper abdomen of a liver cirrhosis patient and application of the processing method in judging esophageal varicosity of the liver cirrhosis patient. The processing method comprises the following steps: S1, collecting an enhanced CT image of the upper abdomen of a liver cirrhosis patient; s2, marking the lower section areas of the liver, the spleen and the esophagus in the enhanced CT image layer by layer; s3, performing three-dimensional reconstruction on the marked areas respectively; s4, image omics features are extracted from each three-dimensional area and then fused, and original image omics features of the patient are obtained; s5, performing dimensionality reduction processing on the original radiomics characteristics by applying a principal component analysis method to obtain dimensionality-reduced radiomics characteristics; and S6, constructing a patient esophageal varicosity radiomics classification model by using a classification algorithm.

Description

technical field [0001] The invention relates to the fields of medicine, nuclear medicine and radiomics, in particular to a method for processing radiomics features of enhanced abdominal CT in patients with liver cirrhosis and its application in judging esophageal varices in patients with liver cirrhosis. Background technique [0002] Cirrhosis is the terminal stage of progression of various chronic liver diseases and is the 11th most common cause of death worldwide. Variceal bleeding is a serious and fatal complication of liver cirrhosis. Esophageal varices have a higher mortality rate than gastric varices. About 1 / 3 of patients with esophageal varices will experience bleeding from esophageal varices, and the mortality rate after acute hemorrhage is as high as 15%-25% within 6 weeks, and as high as 40% within 1 year after hemorrhage. Therefore, early diagnosis of varices, especially esophageal varices, prediction of bleeding risk, and selection of appropriate treatment are...

AI Technical Summary

Problems solved by technology

However, HVPG measurement is an invasive angiographic intervention that requires specialized equipment and is relatively expensive; at the same time, it is easily affected by some factors: such as body position, breathing, anesthetic drugs and intrahepatic shunt, etc.

Some scholars have proposed several diagnostic and predictive models based on serum markers, such as FIB-4 (Fibrosis Index Based on Four Factors, liver fibrosis index), Lok score, APRI (Aspartate aminotransferase to platelet count ratio index, aspartate aminotransferase to platelet count ratio index, aspartate aminotransferase and Platelet count ratio index), AAR (Aspartate aminotransferase to alanine aminotransferaseratio, ratio of aspartate aminotransferase to alanine aminotransferase), VITRO score (Von Willebrand factor antigen / platelet ratio, ratio of von Willebrand factor antigen level to platelet count), etc., but These models are not very accurate

[0005] In CT imaging examination, in addition to the size, shape, edge shape, enhanced structure and other characteristics of organs or lesions that can be observed by the naked eye, a large amount of image data will be generated at the same time, and these data cannot be completely read and interpreted by doctors

Images