Blood vessel modeling method

Abstract

The invention relates to a blood vessel modeling method, which comprises the following steps of: constructing density distribution of spherical bodies, cylindrical bodies and target bodies; using the constructed spherical bodies to generate a tubular target; using Gaussian noise to simulate a target background; using a Markov statistical model to generate textures of the background; and using a proportional control method to fuse the background with the target to form a simulated image. The blood vessel modeling method can provide a systematic simulation training dataset for mathematic split models of various medical images such as computerized tomography (CT) or magnetic resonance (MR) angiograms.

Description

【Technical field】 [0001] The invention belongs to the field of medical image processing, in particular to a blood vessel modeling method. 【Background technique】 [0002] Computer modeling and simulation is a very broad technical field. From the perspective of computer modeling and simulation of medical organs (such as the heart), it can be roughly divided into: shape modeling, structural data modeling, function and system Modeling and more. Among them, the modeling of structural data is of great significance to the analysis and research of medical images. Structural data modeling usually has the following approaches: (1) Manually or semi-automatically generate simulation data; (2) Obtain image data after imaging natural objects or specimens with similar shapes and adding some imaging agent; ( 3) Computer simulation data. Among them, the advantage of computer simulation data is that it can avoid the shortcomings of other methods that are difficult to control the proportion...

AI Technical Summary

Problems solved by technology

(2) The angiographic data collected from the clinical practice does not contain the real standard of the target and the background, and cannot directly evaluate the blood vessel segmentation algorithm; while the generation of the simulation model contains the determined blood vessel and background parameters, which can be directly used for blood vessel segmentation Initial evaluation of the algorithm

[0005] However, in the process of analyzing and modeling two-dimensional or three-dimensional tubular targets with commonly used structural data modeling, the characteristics and indicators of clinical data sets often do not meet the objective requirements of clinical and experimental, such as: clinical data target category and shape The set is incomplete, the specific algorithm functions cannot be verified from limited clinical data, and the robustness evaluation of the segmentation model under different noise levels and background complexity cannot be achieved

Images