Fine grained medical image fusion using type-2 fuzzy logic

2019 ◽  
Vol 14 (2) ◽  
pp. 999
Author(s):  
Ramya H.R ◽  
B K Sujatha
Keyword(s):  
Fuzzy Logic ◽  
Image Fusion ◽  
Medical Image ◽  
Objective Evaluation ◽  
Medical Image Fusion ◽  
Fine Grained ◽  
Sharp Feature ◽  
Sugeno Model ◽  
Image Fusion Technique

<p>In recent years, many fast-growing technologies coupled with wide volume of medical data for the digitalization of that data. Thus, researchers have shown their immense interest on Multi-sensor image fusion technologies which convey image information based on data from various sensor modalities into a single image. The image fusion technique is a widespread technique for the diagnosis of medical instrumentation and measurement. Therefore, in this paper we have introduced a novel multimodal sensor medical image fusion method based on type-2 fuzzy logic is proposed using Sugeno model. Moreover, a Gaussian smoothen filter is introduced to extract the detailed information of an image using sharp feature points.Type-2 fuzzy algorithm is used to achieve highly efficient feature points from both the b images to provide high visually classified resultant image. The experimental results demonstrate that the proposed method can achieve better performance than the state-of-the- art methods in terms of visual quality and objective evaluation.</p>

Multimodal Sensor Medical Image Fusion Based on Type-2 Fuzzy Logic in NSCT Domain

2016 ◽  
Vol 16 (10) ◽  
pp. 3735-3745 ◽  
Author(s):  
Yong Yang ◽  
Yue Que ◽  
Shuying Huang ◽  
Pan Lin
Keyword(s):  
Fuzzy Logic ◽  
Image Fusion ◽  
Medical Image ◽  
Medical Image Fusion

scholarly journals Pulse Coupled Neural Network-Based Multimodal Medical Image Fusion via Guided Filtering and WSEML in NSCT Domain

Entropy ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. 591
Author(s):  
Liangliang Li ◽  
Hongbing Ma
Keyword(s):  
Neural Network ◽  
Image Fusion ◽  
High Frequency ◽  
Medical Image ◽  
Fusion Rule ◽  
Objective Evaluation ◽  
Fusion Model ◽  
Pulse Coupled Neural Network ◽  
Medical Image Fusion ◽  
Frequency Components

Multimodal medical image fusion aims to fuse images with complementary multisource information. In this paper, we propose a novel multimodal medical image fusion method using pulse coupled neural network (PCNN) and a weighted sum of eight-neighborhood-based modified Laplacian (WSEML) integrating guided image filtering (GIF) in non-subsampled contourlet transform (NSCT) domain. Firstly, the source images are decomposed by NSCT, several low- and high-frequency sub-bands are generated. Secondly, the PCNN-based fusion rule is used to process the low-frequency components, and the GIF-WSEML fusion model is used to process the high-frequency components. Finally, the fused image is obtained by integrating the fused low- and high-frequency sub-bands. The experimental results demonstrate that the proposed method can achieve better performance in terms of multimodal medical image fusion. The proposed algorithm also has obvious advantages in objective evaluation indexes VIFF, QW, API, SD, EN and time consumption.

scholarly journals Assessment of 3D Lumbosacral Vascular Anatomy for OLIF51 by Non-Enhanced MRI and CT Medical Image Fusion Technique

Diagnostics ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1744
Author(s):  
Masakazu Nagamatsu ◽  
Sameer Ruparel ◽  
Masato Tanaka ◽  
Yoshihiro Fujiwara ◽  
Koji Uotani ◽  
...  
Keyword(s):  
Image Fusion ◽  
Vertebral Body ◽  
Medical Image ◽  
Interbody Fusion ◽  
Vascular Anatomy ◽  
Lumbar Interbody Fusion ◽  
Fusion Technique ◽  
Medical Image Fusion ◽  
The Mean ◽  
Image Fusion Technique

Study design: Prospective study. Objective: Medical image fusion can provide information from multiple modalities in a single image. The present study aimed to determine whether three-dimensional (3D) lumbosacral vascular anatomy could be adequately portrayed using a non-enhanced CT–MRI medical image fusion technique. Summary of Background Data: Lateral lumbar interbody fusion has gained popularity for the surgical treatment of adult spinal deformity (ASD). Oblique lumbar interbody fusion at L5–S1 (OLIF51) is receiving considerable attention as a method of creating good L5–S1 lordosis. Access in OLIF51 requires evaluation of the vascular anatomy in the lumbosacral region. Conventional imaging modalities need a contrast medium to describe the vascular anatomy. Methods: Participants comprised 15 patients with ASD or degenerative lumbar disease who underwent corrective surgery at our hospital between January 2020 and June 2021. A 3D vascular image with bony structures was obtained by fusing results from MRI and CT. We processed the merged image and measured the distance between left and right common iliac arteries and veins at two levels: the lower end of the L5 vertebral body (Window A) and the upper end of the S1 vertebral body (Window B). Results: The mean sizes of Window A and Window B were 29.7 ± 10.7 mm and 36.9 ± 10.3 mm, respectively. The mean distance from the bifurcation to the lower end of the L5 vertebra was 23.7 ± 10.9 mm. Coronal deviation of the bifurcation was, from center to left, 12.6 ± 12.3 mm, and the distance from the center of the L5 vertebral body to the bifurcation was 0.79 ± 7.3 mm. Only one case showed a median sacral vein (6.7%). Clinically, we performed OLIF51 in 12 of the 15 cases (80%). Conclusion: Evaluating 3D lumbosacral vascular anatomy using a non-enhanced MRI and CT medical image fusion technique is very useful for OLIF51, particularly for patients in whom the use of contrast medium is contraindicated.

Sign in / Sign up

Export Citation Format

Share Document