Multimode medical image registration method based on SURF algorithm

Abstract

A multimode medical image registration method based on the SURF algorithm comprises the following steps: S1, employing the SURF algorithm to extract the feature points in different mode medical images; S2, determining the main directions of the feature points in each mode medical image, and constructing corresponding SURF feature descriptors; S3, performing matrix operation of the SURF feature descriptors of the feature points, and obtaining a transition matrix; and S4, employing the transition matrix to complete the registration of different mode medical images. The SURF algorithm compares to the SIFI algorithm, the calculation rate is greatly improved. The parallelization technology such as GPU and the like is employed to reach real-time linear registration of a big-resolution images.

Description

technical field [0001] The present invention relates to the field of medical image processing, especially a multi-modal medical image registration method based on SURF algorithm that can improve the registration accuracy of lesions or interested parts, and is helpful for clinical diagnosis and radiotherapy plan formulation and evaluation . Background technique [0002] At present, with the rapid development of computer science and technology and medical impact engineering, many advanced medical imaging devices have appeared in the world, providing medical images of various modalities for clinical medical diagnosis, and these images reflect the structure of the human body from different aspects , different information about organs and diseased tissues. [0003] For example, CT (Computed Tomography) images have strong spatial resolution and geometric characteristics, and the imaging of bones is very clear. It can provide a good reference for lesion location, but the contrast ...

AI Technical Summary

Problems solved by technology

MR (Magnetic Resonance) images can clearly reflect the anatomical structure of soft tissues, organs, blood vessels, etc., which is helpful to determine the scope of lesions, but MR images are not sensitive to calcification points, and geometric distortion will occur due to magnetic interference

SPEC and PET images can obtain the radioactivity concentration distribution of the human body at any angle, which can reflect the metabolic level and blood flow status of tissues and organs, present "hot spots" for tumor lesions, and provide functional information of the human body. Difficult to obtain accurate anatomical structures, and difficult to distinguish the boundaries of tissues and organs

Images