An Automatic Extraction Method of 3D Liver Bounding Box Based on CT Image

Abstract

The invention relates to an automatic extraction method of a three-dimensional liver bounding box based on a CT image, which measures the volume of N cases of abdominal CT liver segmentation data, selects the three-dimensional CT slice and liver mask closest to the average liver volume, and determines the corresponding The liver area rectangle frame of the CT slice; the CT image of the determined liver rectangle area is used as the standard CT image and the CT image of the undetermined liver bounding box for rough registration, and the step size and iteration number of the optimizer in the rough registration are changed. Output the transformation matrix; geometrically transform the binary image of the rectangular frame of the liver area, put the transformed matrix in the two-dimensional coordinate system, find the coordinates of all points in the matrix with a gray value of 1, and calculate the maximum The value and min determine the rectangle bounds as the liver area rectangle. The invention reduces the amount of image processing data, guides the rapid and accurate segmentation of the liver, is of great significance for guiding the segmentation of liver tumors, and lays the foundation for subsequent research.

Description

technical field [0001] The invention relates to an image processing technology, in particular to an automatic extraction method of a three-dimensional liver bounding box based on a CT image. Background technique [0002] With the rapid development of science and technology and the continuous improvement of people's living standards, people pay more and more attention to their own health. Early and accurate detection of diseases and timely treatment can not only save the lives of patients, relieve their pain, but also reduce their pain. economic burden. Today, with the explosion of information technology, images, as the most basic, direct and real way for human beings to perceive the external environment, are constantly developing towards higher requirements. As a non-invasive medical diagnosis reference, medical imaging technology is playing an increasingly important role in modern medicine. Computed tomography (CT), ultrasound imaging (US), nuclear magnetic resonance (MRI...

AI Technical Summary

Problems solved by technology

These methods still have drawbacks such as: requiring manual interaction, sensitive to noise, high complexity, not very adaptable, and therefore not suitable for clinical use

Images