Premium
SU‐E‐I‐74: Extracting Information From a Series of MR Images by MultiParameter Imaging
Author(s) -
Yu S,
Xie Y,
An M,
Li R,
Wu S,
Yang Y
Publication year - 2013
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4814185
Subject(s) - medical imaging , interpolation (computer graphics) , image fusion , computer science , artificial intelligence , image registration , series (stratigraphy) , computer vision , data mining , medical physics , image (mathematics) , medicine , paleontology , biology
Purpose: To develop a framework to integrate valuable information from a series of MR images by multi‐parameter imaging, and generate images for medical diagnosis and analysis. Methods: The proposed framework consists of three steps. Firstly, a technique, multi‐parameter imaging, is defined. It scans the same section of a subject with same situation except one variable imaging parameter. Then these images are interpolated by iterative curvature‐based interpolation (ICBI). Finally, we develop a new data fusion method by optimizing mean square error (MSE) to fuse information from these interpolated images. Results: The proposed framework is tested on 50 series of clinical MR images from 5 patients, and the results are validated from visual assessment and SNR. Conclusion: This paper contributes: 1) a technique, multi‐parameter imaging, is defined. 2) For the image series by multi‐parameter imaging, a data fusion method by optimizing MSE is developed. 3) A framework incorporating multi‐parameter imaging, interpolation and data fusion is presented. The framework generates two images with high visual quality. One provides tissue details for diagnosis, and the other enhances anatomical edges and variations of signals are valuable for medical analysis. This work is supported in part by grants from National Natural Science Foundation of China (NSFC: 81171402), NSFC Joint Research Fund for Overseas Research Chinese, Hong Kong and Macao Young Scholars (30928030), National Basic Research Program 973 (2010CB732606) from Ministry of Science and Technology of China, and Guangdong Innovative Research Team Program (No. 2011S013) of China.