scholarly journals Multi-modality medical image fusion technique using multi-objective differential evolution based deep neural networks

2020 ◽  
Author(s):  
Manjit Kaur ◽  
Dilbag Singh
Keyword(s):  
Neural Networks ◽  
Differential Evolution ◽  
Image Fusion ◽  
Medical Image ◽  
Deep Neural Networks ◽  
Fusion Technique ◽  
Multi Objective ◽  
Medical Image Fusion ◽  
Image Fusion Technique

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.

scholarly journals Medical Image Fusion using BEMD and an Efficient Fusion Scheme

2018 ◽  
Author(s):  
M Mozaffarilegha ◽  
A Yaghobi Joybari ◽  
A Mostaar
Keyword(s):  
Image Fusion ◽  
Medical Image ◽  
Medical Images ◽  
Energy Operator ◽  
Fusion Rule ◽  
Fusion Technique ◽  
Medical Image Fusion ◽  
Fused Image ◽  
Image Fusion Technique ◽  
Fusion Scheme

Background: Medical image fusion is being widely used for capturing complimentary information from images of different modalities. Combination of useful information presented in medical images is the aim of image fusion techniques, and the fused image will exhibit more information in comparison with source images.Objective: In the current study, a BEMD-based multi-modal medical image fusion technique is utilized. Moreover, Teager-Kaiser energy operator (TKEO) was applied to lower BIMFs. The results were compared to six routine methods.Methods: An image fusion technique using bi-dimensional empirical mode decomposition (BEMD), Teager-Kaiser energy operator (TKEO) as a local feature selection and HMAX model is presented. BEMD fusion technique can preserve much functional information. In the process of fusion, we adopt the fusion rule of TKEO for lower bi-dimensional intrinsic mode functions (BIMFs) of two images and HMAX visual cortex model as a fusion rule for higher BIMFs, which are verified to be more appropriate for human vision system. Integrating BEMD and this efficient fusion scheme can retain more spatial and functional features of input images.Results: We compared our method with IHS, DWT, LWT, PCA, NSCT and SIST methods. The simulation results and fusion performance show that the presented method is effective in terms of mutual information, quality of fused image (QAB/F), standard deviation, peak signal to noise ratio, structural similarity and considerably better results compared to six typical fusion methods.Conclusion: The statistical analyses revealed that our algorithm significantly improved spatial features and diminished the color distortion compared to other fusion techniques. The proposed approach can be used for routine practice. Fusion of functional and morphological medical images is possible before, during and after treatment of tumors in different organs. Image fusion can enable interventional events and can be further assessed.

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>

Sign in / Sign up

Export Citation Format

Share Document