| MRI and PET images fusion based on human retina model |
| |
| 作者姓名： | DANESHVAR Sabalan GHASSEMIAN Hassan |
| |
| 作者单位： | Department of Electrical and Computer Engineering Tarbiat Modares University P.O.Box 14115-143 Tehran Iran，Department of Electrical and Computer Engineering Tarbiat Modares University P.O.Box 14115-143 Tehran Iran |
| |
| 基金项目： | Project （No, TMU 85-05-33） supported in part by the lran Telecommunication Research Center （ITRC） |
| |
| 摘 要： | The diagnostic potential of brain positron emission tomography (PET) imaging is limited by low spatial resolution. For solving this problem we propose a technique for the fusion of PET and MRI images. This fusion is a trade-off between the spectral information extracted from PET images and the spatial information extracted from high spatial resolution MRI. The proposed method can control this trade-off. To achieve this goal, it is necessary to build a multiscale fusion model, based on the retinal cell photoreceptors model. This paper introduces general prospects of this model, and its application in multispectral medical image fusion. Results showed that the proposed method preserves more spectral features with less spatial distortion. Comparing with hue-intensity-saturation (HIS), discrete wavelet transform (DWT), wavelet-based sharpening and wavelet-à trous transform methods, the best spectral and spatial quality is only achieved simultaneously with the proposed feature-based data fusion method. This method does not require resampling images, which is an advantage over the other methods, and can perform in any aspect ratio between the pixels of MRI and PET images.
|
| 关 键 词： | 影像融合 视网膜 多分辨率 多分辨率成像 正电子发射X射线层析照相术照相术 |
| 收稿时间： | 2007-04-28 |
| 修稿时间： | 2007-08-13 |
MRI and PET images fusion based on human retina model |
| |
| DANESHVAR Sabalan GHASSEMIAN Hassan.MRI and PET images fusion based on human retina model[J].Journal of Zhejiang University Science,2007,8(10):1624-1632. |
| |
| Authors: | Daneshvar Sabalan Ghassemian Hassan |
| |
| Institution: | (1) Department of Electrical and Computer Engineering, Tarbiat Modares University, P.O.Box, 14115-143 Tehran, Iran |
| |
| Abstract: | The diagnostic potential of brain positron emission tomography (PET) imaging is limited by low spatial resolution. For solving
this problem we propose a technique for the fusion of PET and MRI images. This fusion is a trade-off between the spectral
information extracted from PET images and the spatial information extracted from high spatial resolution MRI. The proposed
method can control this trade-off. To achieve this goal, it is necessary to build a multiscale fusion model, based on the
retinal cell photoreceptors model. This paper introduces general prospects of this model, and its application in multispectral
medical image fusion. Results showed that the proposed method preserves more spectral features with less spatial distortion.
Comparing with hue-intensity-saturation (HIS), discrete wavelet transform (DWT), wavelet-based sharpening and wavelet-à trous transform methods, the best spectral and spatial quality is only achieved simultaneously with the proposed feature-based
data fusion method. This method does not require resampling images, which is an advantage over the other methods, and can
perform in any aspect ratio between the pixels of MRI and PET images.
Project (No. TMU 85-05-33) supported in part by the Iran Telecommunication Research Center (ITRC) |
| |
| Keywords: | Image fusion Retina based Multiresolution Multiresolution image (MRI) Positron emission tomography (PET) |
| 本文献已被 CNKI 维普 SpringerLink 等数据库收录！ |
