مقاله انگلیسی رایگان در مورد ترکیب تصویر پزشکی سنسور چند مودال – IEEE 2019

In this paper, we propose an efficient image fusion algorithm using multiple salient features with guided image filter to prevent the problem of low contrast detail. First, we employ the guided image filter to decompose the input images into a series of smoothed and detailed images at different scales. Second, the salient features are extracted from the decomposed smoothed images and detailed images using two different algorithms: the spectral residual (SR) algorithm for extracting mainframe information and the graphbased visual saliency (GBVS) model for extracting gradient saliency information to construct the fusion rules. In addition, generalized intensity-hue-saturation (GIHS) is adopted to combine the decomposition coefficients. Finally, the fused image is reconstructed by the fused smoothed and fused detailed images. The experimental results demonstrate that the proposed algorithm can achieve better performance than other fusion methods in the domains of MRI-PET and MRI-SPECT fusion.

Introduction

With the development of medical imaging technology, modern medical imaging provides multiple diagnostic images for clinical diagnosis, such as computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single-photon emission computed tomography (SPECT) images. They focus on various aspects to provide information. CT and MRI images are anatomical images with a high spatial resolution that provide body contours and soft tissue information. PET and SPECT images are functional images with lower spatial resolution that contain color information that reflects the body’s metabolic level. To overcome the limitations of single medical image information expression and to provide more comprehensive and complementary information for medical diagnosis and treatment, multimodal medical image fusion has been proposed. Multimodal medical image fusion obtains a single fused image in terms of human visual perception to increase the clinical applicability of medical images for the diagnosis and assessment of medical problems [1]. Brain diseases have a high incidence and present a high risk to people’s lives. To provide additional auxiliary information for such diseases, this paper focuses on the fusion of anatomical images and functional images of brain diseases.