Presentation | 2017-09-15 Posterior Mean Approximate Estimate Considering Uncertainty of Sensitivity Map in CS-SENSE Ken Harada, Masato Inoue, Kaori Togashi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Posterior mean (PM) estimation is generally more accurate than maximum a posteriori probability (MAP) estimation when we adopt the squared error for the accuracy evaluation of the estimated image and the true image. However, in rapid MR image reconstruction, a simple MAP solution is often substituted. In this research, we extend the CS-SENSE method by using not a single but multiple sensitivity maps with a variety of resolutions, and construct a model that approximates the PM solution by linear combination of MAP solutions corresponding to each sensitivity map. The connection weights (non-negative real values) are learned from the correct images, and they became sparse. As a result, we achieved 40% improvement over MAP solution. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Rapid MR Imaging / Compressed Sensing / CS-SENSE / Posterior Mean Estimate |
Paper # | PRMU2017-49,IBISML2017-21 |
Date of Issue | 2017-09-08 (PRMU, IBISML) |
Conference Information | |
Committee | PRMU / IBISML / IPSJ-CVIM |
---|---|
Conference Date | 2017/9/15(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinichi Sato(NII) / Kenji Fukumizu(ISM) |
Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Masashi Sugiyama(Univ. of Tokyo) |
Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Masashi Sugiyama(Kyoto Univ.) / (Univ. of Tokyo) |
Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Ichiro Takeuchi(Nagoya Inst. of Tech.) / Toshihiro Kamishima(AIST) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Posterior Mean Approximate Estimate Considering Uncertainty of Sensitivity Map in CS-SENSE |
Sub Title (in English) | |
Keyword(1) | Rapid MR Imaging |
Keyword(2) | Compressed Sensing |
Keyword(3) | CS-SENSE |
Keyword(4) | Posterior Mean Estimate |
1st Author's Name | Ken Harada |
1st Author's Affiliation | Waseda University(Waseda Univ.) |
2nd Author's Name | Masato Inoue |
2nd Author's Affiliation | Waseda University(Waseda Univ.) |
3rd Author's Name | Kaori Togashi |
3rd Author's Affiliation | Kyoto University(Kyoto Univ.) |
Date | 2017-09-15 |
Paper # | PRMU2017-49,IBISML2017-21 |
Volume (vol) | vol.117 |
Number (no) | PRMU-210,IBISML-211 |
Page | pp.pp.75-82(PRMU), pp.75-82(IBISML), |
#Pages | 8 |
Date of Issue | 2017-09-08 (PRMU, IBISML) |