Presentation 2018-11-05
[Poster Presentation] Posterior mean approximation solution combining multiple image prior distributions in MR image reconstruction
Nanako Kubota, Ken Harada, Koji Fujimoto, Tomohisa Okada, Masato Inoue,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the MR image reconstruction, combining multiple image prior distributions is preferred to obtain better results, but finding the optimal combination of prior weights by the cross-validation method is difficult because the number of combinations increases exponentially w.r.t. the number of priors. In this manuscript, we solve this problem by the ensemble learning. Furthermore, we give meaning to this solution as an approximate of the posterior mean. As a result, the accuracy (mean square error) of reconstructed images was improved without increasing the order of the calculation cost.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) MR image reconstruction / compressed censing / posterior mean estimate / ensemble learning
Paper # IBISML2018-47
Date of Issue 2018-10-29 (IBISML)

Conference Information
Committee IBISML
Conference Date 2018/11/5(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Hokkaido Citizens Activites Center (Kaderu 2.7)
Topics (in Japanese) (See Japanese page)
Topics (in English) Information-Based Induction Science Workshop (IBIS2018)
Chair Hisashi Kashima(Kyoto Univ.)
Vice Chair Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST)
Assistant Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] Posterior mean approximation solution combining multiple image prior distributions in MR image reconstruction
Sub Title (in English)
Keyword(1) MR image reconstruction
Keyword(2) compressed censing
Keyword(3) posterior mean estimate
Keyword(4) ensemble learning
1st Author's Name Nanako Kubota
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Ken Harada
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Koji Fujimoto
3rd Author's Affiliation Kyoto University(Kyoto Univ.)
4th Author's Name Tomohisa Okada
4th Author's Affiliation Kyoto University(Kyoto Univ.)
5th Author's Name Masato Inoue
5th Author's Affiliation Waseda University(Waseda Univ.)
Date 2018-11-05
Paper # IBISML2018-47
Volume (vol) vol.118
Number (no) IBISML-284
Page pp.pp.23-28(IBISML),
#Pages 6
Date of Issue 2018-10-29 (IBISML)