Research advances in multi-modality medical image registration and fusion methods and their clinical application

Abstract

Multi-modality medical image processing has become a hot topic for research in the field of image processing and plays an important role in clinical diagnosis and treatment. Images with different modalities provide different information on patients. Anatomical images (such as computed tomography and magnetic resonance imaging) provide information on anatomical morphology and the structure of human body, and functional images (such as single-photon emission computed tomography and positron emission tomography) provide the functional information on the distribution of radioactive concentration within human body. Such information needs to be fused to obtain comprehensive fusion images, and the images with different modalities need to be registered to obtain useful fusion images. This article reviews several image registration and fusion techniques used in the medical field, points out their advantages and shortcomings, and introduces the application of various processing techniques in clinical practice. Key words: Image processing; Image registration; Image fusion