Fusion of 3-D medical image gradient domain based on detail-driven and directional structure tensor

Multimodal brain image fusion based on error texture elimination and salient feature detection

As an important clinically oriented information fusion technology, multimodal medical image fusion integrates useful information from different modal images into a comprehensive fused image. Nevertheless, existing methods routinely consider only energy information when fusing low-frequency or base layers, ignoring the fact that useful texture information may exist in pixels with lower energy values. Thus, erroneous textures may be introduced into the fusion results. To resolve this problem, we propose a novel multimodal brain image fusion algorithm based on error texture removal. A two-layer decomposition scheme is first implemented to generate the high- and low-frequency subbands. We propose a salient feature detection operator based on gradient difference and entropy. The proposed operator integrates the gradient difference and amount of information in the high-frequency subbands to effectively identify clearly detailed information. Subsequently, we detect the energy information of the low-frequency subband by utilizing the local phase feature of each pixel as the intensity measurement and using a random walk algorithm to detect the energy information. Finally, we propose a rolling guidance filtering iterative least-squares model to reconstruct the texture information in the low-frequency components. Through extensive experiments, we successfully demonstrate that the proposed algorithm outperforms some state-of-the-art methods. Our source code is publicly available at https://github.com/ixilai/ETEM.

A Survey of Multi-Focus Image Fusion Methods

As an important branch in the field of image fusion, the multi-focus image fusion technique can effectively solve the problem of optical lens depth of field, making two or more partially focused images fuse into a fully focused image. In this paper, the methods based on boundary segmentation was put forward as a group of image fusion method. Thus, a novel classification method of image fusion algorithms is proposed: transform domain methods, boundary segmentation methods, deep learning methods, and combination fusion methods. In addition, the subjective and objective evaluation standards are listed, and eight common objective evaluation indicators are described in detail. On the basis of lots of literature, this paper compares and summarizes various representative methods. At the end of this paper, some main limitations in current research are discussed, and the future development of multi-focus image fusion is prospected.

Artificial Intelligence Algorithm-Based Differential Diagnosis of Crohn's Disease and Ulcerative Colitis by CT Image

The aim of this study was to investigate the effect of low-dose CT enterography (CTE) based on modified guided image filtering (GIF) algorithm in the differential diagnosis of ulcerative colitis (UC) and Crohn's disease (CD). Methods. One hundred and twenty patients with suspected diagnosis of IBD were studied. They were randomly divided into control group (routine CT examination) and observation group (low-dose CTE examination based on improved GIF algorithm), with 60 cases in each group. Comprehensive diagnosis was used as the standard to assess the diagnostic effect. Results. (1) The peak signal-to-noise ratio (PSNR) (26.02 dB) and structural similarity (SSIM) (0.8921) of the algorithm were higher than those of GIF (17.22 dB/0.8491), weighted guided image filtering (WGIF) (23.78 dB/0.8489), and gradient domain guided image filtering (GGIF) (23.77 dB/0.7567) (P < 0.05); (2) the diagnostic sensitivity (91.49%), specificity (92.31%), accuracy (91.67%), positive predictive value (97.73%), and negative predictive value (75%) of the observation group were higher than those of the control group (P < 0.05); the sensitivity and specificity of CTE in the diagnosis of UD and CD were 96.77% and 81.25% and 98.33% and 93.33%, respectively (P < 0.05); there were significant differences in symmetrical intestinal wall thickening and smooth serosal surface between UD and CD (P < 0.05). Conclusion. (1) The improved GIF algorithm has a more effective application value in the denoising processing of low-dose CT images and can better improve the image quality; (2) the accuracy of CTE in the diagnosis of IBD is high, and CTE is of great value in the differential diagnosis of UD and CD.

HID: The Hybrid Image Decomposition Model for MRI and CT Fusion

Multimodal medical image fusion can combine salient information from different source images of the same part and reduce the redundancy of information. In this paper, an efficient hybrid image decomposition (HID) method is proposed. It combines the advantages of spatial domain and transform domain methods and breaks through the limitations of the algorithms based on single category features. The accurate separation of base layer and texture details is conducive to the better effect of the fusion rules. First, the source anatomical images are decomposed into a series of high frequencies and a low frequency via nonsubsampled shearlet transform (NSST). Second, the low frequency is further decomposed using the designed optimization model based on structural similarity and structure tensor to get an energy texture layer and a base layer. Then, the modified choosing maximum (MCM) is designed to fuse base layers. The sum of modified Laplacian (SML) is used to fuse high frequencies and energy texture layers. Finally, the fused low frequency can be obtained by adding fused energy texture layer and base layer. And the fused image is reconstructed by the inverse NSST. The superiority of the proposed method is verified by amounts of experiments on 50 pairs of magnetic resonance imaging (MRI) images and computed tomography (CT) images and others, and compared with 12 state-of-the-art medical image fusion methods. It is demonstrated that the proposed hybrid decomposition model has a better ability to extract texture information than conventional ones.