Medical image fusion method based on multidirectional empirical mode decomposition

Abstract

The invention relates to a medical image fusion method based on multidirectional empirical mode decomposition. The method comprises the following steps of: performing the multi-scale and multidirectional decomposition on the collected medical source images in different varieties by adopting the multidirectional empirical mode decomposition, acquiring an intrinsic mode component of a multi-scale and multidirectional high-frequency component of a source image; performing the fusion treatment according to the local energy rule in order to effectively extract the high-frequency detailed information of every source image; performing the fusion treatment on the residual low-frequency component of the source image by adopting the energy contribution rules; and finally, inversely transforming to obtain the fused image. The fused image can effectively improve the visual effect of the fused image and avoid the shortcomings of partial distortion or deletion of the fusion image caused by small wave, ultra-small wave and window empirical mode decomposition fusion algorithm; the parameter does not need to be selected manually, the detailed information of the source image can be well extracted, and the self-adaptive image fusion based on a brand-new multi-scale decomposition structure is achieved; the medical image fusion method based on the multidirectional empirical mode decomposition has complete adaptability driven by data and stronger ability of obtaining the detailed information.

Description

technical field [0001] The invention belongs to the technical field of image fusion, and relates to a medical image fusion method based on multidirectional empirical mode decomposition. Background technique [0002] Image fusion is an information fusion technology whose main research content is image. It is to combine two or more images into one image to obtain a more accurate, comprehensive and reliable image description of the same scene. Image fusion technology effectively utilizes the redundancy and complementarity between multiple images to make the fused image more suitable for the human visual system and the needs of computer understanding, analysis and subsequent processing. [0003] Medical image fusion is an important application in image fusion. At present, medical imaging equipment mainly includes: computer tomography (Computer Tomography, CT), magnetic resonance imaging (Magnetic Resonance Imaging, MRI) or the newer positron emission tomography (Positron Emissi...

AI Technical Summary

Problems solved by technology

But no matter what kind of wavelet it is based on, there is a problem in image fusion: the fused image will be distorted in a local position, which is acceptable in general applications, but in medical images, this may cause doctors Misdiagnosis affects the patient's follow-up treatment

However, the traditional two-dimensional empirical mode decomposition has defects: there are dark spots in the intrinsic mode component image obtained from the decomposition

[0006] In summary, there are still some deficiencies in the existing fusion technology applied to medical image fusion: the fusion image based on wavelet and ultrawavelet will appear local distortion, and the dark spots of the intrinsic mode component image decomposed by the traditional empirical mode decomposition method are all right. The fusion result has a great influence. In the fusion graph decomposed by the window empirical mode, a small amount of detail information will be missing, and the quality of the fusion rule also has a huge impact on the fusion effect.

Images