An Optimal Registration on Shearlet domain with Novel Weighted Energy fusion for Multi-Modal Medical Images

Medical images usually display various attributes of data on human viscera and abnormal tissue in different modalities. The fusion of images, ensures effective deployment of all relevant information from several modalities into a single image. Finally, the paper leads to a novel multi-modal medical...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Optik (Stuttgart) Ročník 225; s. 165742
Hlavní autoři:	Nair, Rekha R., Singh, Tripty
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier GmbH 01.01.2021
Témata:	Active Contour Model Multi-modal medical image fusion Optimal B-spline registration Weighted Energy fusion rule Whale Optimization Algorithm Whale Optimization Algorithm Optimal B-spline registration Weighted Energy fusion rule Multi-modal medical image fusion Active Contour Model
ISSN:	0030-4026, 1618-1336
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Medical images usually display various attributes of data on human viscera and abnormal tissue in different modalities. The fusion of images, ensures effective deployment of all relevant information from several modalities into a single image. Finally, the paper leads to a novel multi-modal medical image fusion method based on Non-Subsampled Shearlet Transform (NSST) called Denoised Optimum B-Spline Shearlet Image Fusion(DOBSIF) that is based on real-time and standard radiological datasets. The proposed, novel registration based fusion technique DOBSIF, is compared with existing state-of-art techniques like PCA, DWT, SWT etc., and in comparison the proposed DOBSIF works effectively for both the color and grayscale images. To improve the fusion function, a novel pre-fusion method is carried out with the help of the Whale Optimization Algorithm(WOA), using the ideal B-spline-based registration method and in addition a novel Weighted Energy fusion rule is applied to derive relevant information from the source images. The proposed work initially follows normal pre-processing measures such as Gaussian filtering, edge sharpening, and resizing followed by optimal registration, fusion with novel fusion rule and segmentation of tumor part from the fused image. The visual quality of the fused image was evaluated by expert radiologists and the fused resultant image is robust, subject to the modified Active Contour(ACM) model for lesion identification.
ISSN:	0030-4026 1618-1336
DOI:	10.1016/j.ijleo.2020.165742