Title :
A new MRI and PET image fusion algorithm based on pulse coupled neural network
Author :
Nobariyan, Behzad Kalafje ; Daneshvar, Sabalan ; Foroughi, Andia
Author_Institution :
Fac. of Electr. Eng., Sahand Univ. of Technol., Tabriz, Iran
Abstract :
The fusion of multimodal brain imaging for a given clinical application is a very important performance. Generally, the PET (positron emission tomography) image indicates the brain function and it has a low spatial resolution, the MRI image shows the brain tissue anatomy and contains no functional information. In this paper, we propose a novel medical image fusion algorithm which enhances the spatial resolution of the functional images by combining them with a high-resolution anatomic image. In the event, after the registration process, perform YCbCr on the multispectral image and get luminance, blue-difference and red difference chromatic components, and then DWT (discrete wavelet transform) image fusion algorithm based on PCNN (pulse coupled neural networks) is applied to fuse the MRI image and the luminance component (Y). Ultimately, fused image is obtained by inverse YCbCr transform of the new luminance and the old blue-difference and red difference chromatic components back into RGB space. An important feature of the algorithm is to use PCNN because it has the global couple and pulse synchronization characteristics. It has been proven suitable for image processing and successfully employed in image fusion. Our approach is compared with YCbCr, DWT, Contourlet, Curvelet methods. Results show proposed method preserves more spectral features with less spatial distortion.
Keywords :
biomedical MRI; brain; discrete wavelet transforms; feature extraction; image fusion; image registration; image resolution; medical image processing; neural nets; positron emission tomography; synchronisation; Contourlet methods; Curvelet methods; DWT; MRI; PET image fusion algorithm; blue difference; brain function; brain tissue anatomy; clinical application; discrete wavelet transform; global couple characteristics; high-resolution anatomic image; image processing; inverse YCbCr transform; luminance component; multimodal brain imaging; multispectral image; positron emission tomography; pulse coupled neural network; pulse coupled neural networks; pulse synchronization characteristics; red difference chromatic components; registration process; spatial distortion; spatial resolution; spectral features; Discrete wavelet transforms; Image color analysis; Image fusion; Joining processes; Magnetic resonance imaging; Positron emission tomography; Spatial resolution; DWT; MRI; PET; YCbCr transform; image fusion; multi-resolution; pcnn;
Conference_Titel :
Electrical Engineering (ICEE), 2014 22nd Iranian Conference on
Conference_Location :
Tehran
DOI :
10.1109/IranianCEE.2014.6999861