Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Apr 12;13(8):1395.
doi: 10.3390/diagnostics13081395.

Multimodality Medical Image Fusion Using Clustered Dictionary Learning in Non-Subsampled Shearlet Transform

Manoj Diwakar  1 , Prabhishek Singh  2 , Ravinder Singh  3 , Dilip Sisodia  3 , Vijendra Singh  4 , Ankur Maurya  2 , Seifedine Kadry  5   6   7 , Lukas Sevcik  8
Affiliations

Multimodality Medical Image Fusion Using Clustered Dictionary Learning in Non-Subsampled Shearlet Transform

Manoj Diwakar et al. Diagnostics (Basel). .

Abstract

Imaging data fusion is becoming a bottleneck in clinical applications and translational research in medical imaging. This study aims to incorporate a novel multimodality medical image fusion technique into the shearlet domain. The proposed method uses the non-subsampled shearlet transform (NSST) to extract both low- and high-frequency image components. A novel approach is proposed for fusing low-frequency components using a modified sum-modified Laplacian (MSML)-based clustered dictionary learning technique. In the NSST domain, directed contrast can be used to fuse high-frequency coefficients. Using the inverse NSST method, a multimodal medical image is obtained. Compared to state-of-the-art fusion techniques, the proposed method provides superior edge preservation. According to performance metrics, the proposed method is shown to be approximately 10% better than existing methods in terms of standard deviation, mutual information, etc. Additionally, the proposed method produces excellent visual results regarding edge preservation, texture preservation, and more information.

Keywords: bioelectronics; clustered dictionary learning; medical imaging; shearlet domain; sum-modified Laplacian.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Multimodality medical image fusion proposed framework.
Figure 2
Figure 2
Results of multimodality medical image fusion; (a) input multimodality medical image 1; (b) input multimodality medical image 2; (c) Zhang et al. [12]; (d) Ramlal et al. [13]; (e) Dogra et al. [14]; (f) Ullah et al. [15]; (g) Huang et al. [16]; (h) Liu et al. [17]; (i) Mehta et al. [18]; (j) proposed method.
Figure 3
Figure 3
Results of multimodality medical image fusion; (a) input multimodality medical image 1; (b) input multimodality medical image 2; (c) Zhang et al. [12]; (d) Ramlal et al. [13]; (e) Dogra et al. [14]; (f) Ullah et al. [15]; (g) Huang et al. [16]; (h) Liu et al. [17]; (i) Mehta et al. [18]; (j) proposed method.
Figure 4
Figure 4
Results of multimodality medical image fusion; (a) input multimodality medical image 1; (b) input multimodality medical image 2; (c) Zhang et al. [12]; (d) Ramlal et al. [13]; (e) Dogra et al. [14]; (f) Ullah et al. [15]; (g) Huang et al. [16]; (h) Liu et al. [17]; (i) Mehta et al. [18]; (j) proposed method.
Figure 5
Figure 5
Zoomed results of multimodality medical image fusion; (a) input multimodality medical image 1; (b) input multimodality medical image 2; (c) Zhang et al. [12]; (d) Ramlal et al. [13]; (e) Dogra et al. [14]; (f) Ullah et al. [15]; (g) Huang et al. [16]; (h) Liu et al. [17]; (i) Mehta et al. [18]; (j) proposed method.
See this image and copyright information in PMC

References

    1. Xu Z. Medical image fusion using multi-level local extrema. Inf. Fusion. 2014;19:38–48.
    1. Zhang P., Yuan Y., Fei C., Pu T., Wang S. Infrared and visible image fusion using co-occurrence filter. Infrared Phys. Technol. 2018;93:223–231. doi: 10.1016/j.infrared.2018.08.004. - DOI
    1. Li S., Yin H., Fang L. Group-sparse representation with dictionary learning for medical image denoising and fusion. IEEE Trans. Biomed. Eng. 2012;59:3450–3459. doi: 10.1109/TBME.2012.2217493. - DOI - PubMed
    1. Sharma D., Kudva V., Patil V., Kudva A., Bhat R.S. A Convolutional Neural Network Based Deep Learning Algorithm for Identification of Oral Precancerous and Cancerous Lesion and Differentiation from Normal Mucosa: A Retrospective Study. Eng. Sci. 2022;18:278–287. doi: 10.30919/es8d663. - DOI
    1. Yin M., Liu W., Zhao X., Yin Y., Guo Y. A novel image fusion algorithm based on non subsampled shearlet transform. Optik. 2014;125:2274–2282. doi: 10.1016/j.ijleo.2013.10.064. - DOI

LinkOut - more resources