Real-time multi-modal medical image fusion method

Abstract

The invention discloses a real-time multi-modal medical image fusion method. The method comprises the steps of conducting Laplacian Pyramid decomposition on multiple registered medical source images to obtain low-frequency components and high-frequency components corresponding to each source image, conducting fusion on the low-frequency components of all the source images based on the sparse representation method and conducting fusion on the high-frequency components of all the source images based on the coefficient absolute value method, and conducting Laplacian Pyramid reconstruction on the low-frequency component and high-frequency component obtained after fusion to obtain a multi-modal medical fused image. The method well overcomes the defects of the traditional method based on Laplacian Pyramid conversion and the traditional method based on sparse representation, and can obtain a result obviously better than that obtained with the traditional methods. Meanwhile, the method is high in calculation efficiency and good in real-time performance, and has high application value in occasions such as clinical diagnosis.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a real-time multimodal medical image fusion method. Background technique [0002] With the rapid development of biomedical engineering and computer science and technology, CT (computed tomography), MRI (magnetic resonance imaging), PET (positron emission tomography), SPECT (single photon emission computed tomography) and other different modalities State-of-the-art medical imaging has been widely used in clinical diagnosis. However, in clinical applications, medical images of a single modality often cannot provide comprehensive medical information for doctors. For example, CT images have high spatial resolution and can clearly locate rigid bones and transplanted objects, but the imaging contrast of soft tissues is low and cannot clearly display the lesion itself; It can provide high-contrast imaging, but the spatial resolution is often lower than that of CT images, and it...

AI Technical Summary

Problems solved by technology

When fusing images collected by the same type of sensor, this method of directly block-sparse representation of images in the airspace can generally achieve good results, but when the input is images of different modalities, considering factors such as noise Influence, this method is easy to introduce spatial discontinuity in the fusion image and reduce the fusion quality

At the same time, some studies have shown that the dictionary used for sparse representation cannot contain too many atoms, otherwise it will lead to unstable results. For reference: M.Elad and I.Yavneh, "A plurality of sparse representations is better than the sparsest one alone ", IEEE Transactions on Information Theory, Vol.55, No.10, pp.4701-4714, 2009, but the insufficient number of atoms will limit the expression ability of the dictionary, which will cause errors in sparse reconstruction, which will lead to some details are blurred

Images