Presentation 2017-06-23
Similar CT image retrieval method based on lesion natures and their three-dimensional distribution
Hiroaki Takebe, Yasutaka Moriwaki, Takayuki Baba, Hiroaki Terada, Toru Higaki, Kazuo Awai, Akio Ozawa, Kohei Murao, Yasuharu Ogino, Mengjiao Wang, Rujie Liu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When radiologists encounter a difficult case to diagnose, retrieval of morphologically similar cases in which final diagnosis is established may provide clinically useful information. Existing methods retrieve similar cases for each case in which lesions exist within a certain range of region by calculating similarity for the region specified on a slice image of the query case. However, radiologists diagnose cases of diffuse lung disease (DLD) where lesions appear throughout lungs by observing 3D distribution of lesion textures. We propose a novel method which can retrieve morphologically similar cases based on radiologist’s view for lesion textures and their 3-dimensional (3D) distribution. In our method, we configured a 3D model for central-peripheral regions of a lung and calculated similarity for 3D distribution of lesions using the 3D model. We evaluated the average precision of the proposed method for real CT images, and the experimental result showed that our method improved the accuracy compared with the comparative method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image diagnosis / CT image / Diffuse lung disease / Similar case retrieval
Paper # PRMU2017-35,SP2017-11
Date of Issue 2017-06-15 (PRMU, SP)

Conference Information
Committee PRMU / SP
Conference Date 2017/6/22(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII) / Yoichi Yamashita(Ritsumeikan Univ.)
Vice Chair Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Hiroki Mori(Utsunomiya Univ.)
Secretary Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Hiroki Mori(Shizuoka Univ.)
Assistant Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Speech
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Similar CT image retrieval method based on lesion natures and their three-dimensional distribution
Sub Title (in English)
Keyword(1) Image diagnosis
Keyword(2) CT image
Keyword(3) Diffuse lung disease
Keyword(4) Similar case retrieval
1st Author's Name Hiroaki Takebe
1st Author's Affiliation FUJITSU LABORATORIES LTD.(FUJITSU LAB.)
2nd Author's Name Yasutaka Moriwaki
2nd Author's Affiliation FUJITSU LABORATORIES LTD.(FUJITSU LAB.)
3rd Author's Name Takayuki Baba
3rd Author's Affiliation FUJITSU LABORATORIES LTD.(FUJITSU LAB.)
4th Author's Name Hiroaki Terada
4th Author's Affiliation HIROSHIMAUNIVERSITY(Hiroshima Univ.)
5th Author's Name Toru Higaki
5th Author's Affiliation HIROSHIMAUNIVERSITY(Hiroshima Univ.)
6th Author's Name Kazuo Awai
6th Author's Affiliation HIROSHIMAUNIVERSITY(Hiroshima Univ.)
7th Author's Name Akio Ozawa
7th Author's Affiliation FUJITSU LIMITED(FUJITSU)
8th Author's Name Kohei Murao
8th Author's Affiliation FUJITSU LIMITED(FUJITSU)
9th Author's Name Yasuharu Ogino
9th Author's Affiliation FUJITSU LIMITED(FUJITSU)
10th Author's Name Mengjiao Wang
10th Author's Affiliation FRDC(FRDC)
11th Author's Name Rujie Liu
11th Author's Affiliation FRDC(FRDC)
Date 2017-06-23
Paper # PRMU2017-35,SP2017-11
Volume (vol) vol.117
Number (no) PRMU-105,SP-106
Page pp.pp.57-62(PRMU), pp.57-62(SP),
#Pages 6
Date of Issue 2017-06-15 (PRMU, SP)