Presentation 2009-05-29
Intracranial aneurysms detection using directional vector of luminance distribution in MRA images
Masahito AOYAMA, Takuya KUSU, Masauyki MUKUNOKI, Naoki ASADA, Yosuke KOMEDA, Takashi OKIGAWA, Joji URATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we describe a computerized scheme for detection the intracranial unruptured aneurysms in MRA images. Our computerized scheme consists of 1) blood vessel segmentation, 2) computation of directional vector field of luminance distribution, 3) aneurysm candidates detection using end-point and distribution characteristics of the vector, and 4) false positives (FPs) reduction based on linear discriminant analysis (LDA). This method applied to 24 cases with 32 aneurysms and 26 cases without aneurysms. The sensitivity obtained by our computerized scheme for the detection of aneurysms was 100% with 4.5 FPs per patients using end-point and distribution characteristics of the directional vector, and 97% with 1.5 FPs by LDA with three features.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) computer-aided detection / intracranial aneurysm / MRA / directional vector / luminance distribution
Paper # IE2009-35,PRMU2009-26,MI2009-26
Date of Issue

Conference Information
Committee IE
Conference Date 2009/5/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Intracranial aneurysms detection using directional vector of luminance distribution in MRA images
Sub Title (in English)
Keyword(1) computer-aided detection
Keyword(2) intracranial aneurysm
Keyword(3) MRA
Keyword(4) directional vector
Keyword(5) luminance distribution
1st Author's Name Masahito AOYAMA
1st Author's Affiliation Graduate School of Information Sciences, Hiroshima City University()
2nd Author's Name Takuya KUSU
2nd Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
3rd Author's Name Masauyki MUKUNOKI
3rd Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
4th Author's Name Naoki ASADA
4th Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
5th Author's Name Yosuke KOMEDA
5th Author's Affiliation Saiseikai Kumamoto Hospital
6th Author's Name Takashi OKIGAWA
6th Author's Affiliation Saiseikai Kumamoto Hospital
7th Author's Name Joji URATA
7th Author's Affiliation Saiseikai Kumamoto Hospital
Date 2009-05-29
Paper # IE2009-35,PRMU2009-26,MI2009-26
Volume (vol) vol.109
Number (no) 63
Page pp.pp.-
#Pages 6
Date of Issue