https://scholars.lib.ntu.edu.tw/handle/123456789/611669
標題: | Direct Patlak Reconstruction from Dynamic PET Data Using the Kernel Method with MRI Information Based on Structural Similarity | 作者: | Gong K. Cheng-Liao J. Wang G. Chen K.T. Catana C. Qi J. TZE-HSIANG CHEN |
關鍵字: | Electrons;Feature extraction;Hospital data processing;Image enhancement;Image quality;Image reconstruction;Magnetic resonance imaging;Medical computing;Positrons;Kernel;Kernel methods;Magnetic Resonance Imaging (MRI);Positron emission tomography (PET);Resolution improvement;Spatial informations;Structural similarity;Structure similarity;Positron emission tomography;fluorodeoxyglucose;Article;computer simulation;evaluation study;gray matter;human;image analysis;image quality;image reconstruction;intermethod comparison;kernel method;neoplasm;neuroimaging;noise reduction;nuclear magnetic resonance imaging;positron emission tomography;quantitative analysis;signal processing;spatiotemporal analysis;total quality management;white matter;algorithm;brain;diagnostic imaging;image processing;imaging phantom;procedures;statistical model;Algorithms;Brain;Humans;Image Processing, Computer-Assisted;Magnetic Resonance Imaging;Models, Statistical;Phantoms, Imaging;Positron-Emission Tomography | 公開日期: | 2018 | 卷: | 37 | 期: | 4 | 起(迄)頁: | 955-965 | 來源出版物: | IEEE Transactions on Medical Imaging | 摘要: | Positron emission tomography (PET) is a functional imaging modality widely used in oncology, cardiology, and neuroscience. It is highly sensitive, but suffers from relatively poor spatial resolution, as compared with anatomical imaging modalities, such as magnetic resonance imaging (MRI). With the recent development of combined PET/MR systems, we can improve the PET image quality by incorporating MR information into image reconstruction. Previously, kernel learning has been successfully embedded into static and dynamic PET image reconstruction using either PET temporal or MRI information. Here, we combine both PET temporal and MRI information adaptively to improve the quality of direct Patlak reconstruction. We examined different approaches to combine the PET and MRI information in kernel learning to address the issue of potential mismatches between MRI and PET signals. Computer simulations and hybrid real-patient data acquired on a simultaneous PET/MR scanner were used to evaluate the proposed methods. Results show that the method that combines PET temporal information and MRI spatial information adaptively based on the structure similarity index has the best performance in terms of noise reduction and resolution improvement. ? 1982-2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85035797973&doi=10.1109%2fTMI.2017.2776324&partnerID=40&md5=ee0acc0782a7e1dc1f980acace839b30 https://scholars.lib.ntu.edu.tw/handle/123456789/611669 |
DOI: | 10.1109/TMI.2017.2776324 |
顯示於: | 醫學工程學研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。