Processing method and processing system for dividing liver graphs of CT (computed tomography) image

Abstract

The invention is applicable to the field of medical image processing, and provides a processing method and a processing system for dividing liver graphs of a CT (computed tomography) image. The processing method includes steps of acquiring the to-be-divided image; automatically positioning a liver position in the to-be-divided image by preliminarily testing a liver grayscale volume and liver grayscale; registering and extracting initial liver tissue graphs by rotary registering and sampling bands B with low degrees of freedom; combining distance graphs with the initial extracted liver tissue graphs to detect whether the graphs contain liver tumor tissue graphs or not; and precisely dividing the liver graphs in a registering manner by the aid of a liver distribution probability map and the sampling bands B based on mutual information. The processing method and the processing system have the advantages that manual intervention is omitted in an integral dividing procedure, the average volumetric error of the divided liver graphs is about 7.0%, accurate data can be provided for three-dimensional reconstruction and final simulation surgery for livers of patients, and the processing method and the processing system have certain clinical application value.

Description

technical field [0001] The invention belongs to the field of medical image processing, and in particular relates to a processing method and system for CT image liver segmentation. Background technique [0002] At present, many clinical applications need to segment liver tissue from 3D CT images, such as 3D liver volume rendering, liver volume measurement, and liver transplant surgery evaluation and surgery planning. In recent years, many researchers have tried a variety of methods for liver segmentation, including the following methods: region growing, gray-level based methods, level sets, neural networks, clustering methods, graph cutting, deformation models and atlas methods. Due to the variability of liver shape and the existence of liver tumors, most liver segmentation methods cannot meet the clinical accuracy requirements. Therefore, manual segmentation or interactive segmentation is often used clinically at this stage. However, such methods It is tedious and time-cons...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a processing method and system for liver segmentation of CT images, aiming at solving the clinical problem existing in the prior art that manual segmentation or interactive segmentation is often used for liver segmentation. It is tedious and time-consuming, and the segmentation accuracy depends heavily on the problem of the segmenter's experience

Images