Presentation 2002/7/12
Detection of Nodules from Multi-detector Chest CT Images by Using Shape Features
Takashi KUSANAGI, Kensaku MORI, Yoshito MEKADA, Jun-ichi HASEGAWA, Jun-ichiro TORIWAKI, Masaki MORI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a method for detecting small nodules (≦ 5mm) from three dimensional chest CT images taken by multi-slice (multi-detector raw) CT scanners. This method suppresses false positive (F.P.) regions by using shape difference between nodule regions and normal structures. Here we introduce a new feature value called, the maximum distance value inside a connected component. This feature value efficiently discriminates nodule regions having spherical shapes and normal structures such as blood vessel and bronchi having cylindrical shapes. We applied the proposed method to four cases of chest CT images. The experimental results showed that the proposed method can reduce the number of F.P. regions drastically in comparison with our previous method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Chest X-ray CT image / lung cancer / nodule / computer aided diagnosis
Paper # MI2002-41
Date of Issue

Conference Information
Committee MI
Conference Date 2002/7/12(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 Medical Imaging (MI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Detection of Nodules from Multi-detector Chest CT Images by Using Shape Features
Sub Title (in English)
Keyword(1) Chest X-ray CT image
Keyword(2) lung cancer
Keyword(3) nodule
Keyword(4) computer aided diagnosis
1st Author's Name Takashi KUSANAGI
1st Author's Affiliation Dept. of Eng., Nagoya Univ.()
2nd Author's Name Kensaku MORI
2nd Author's Affiliation Research Center for Advanced Waste and Emission Management, Nagoya University
3rd Author's Name Yoshito MEKADA
3rd Author's Affiliation Dept. of Eng., Nagoya Univ.
4th Author's Name Jun-ichi HASEGAWA
4th Author's Affiliation School of Computer and Cognitive Sciences, Chukyo University
5th Author's Name Jun-ichiro TORIWAKI
5th Author's Affiliation Dept. of Eng., Nagoya Univ.
6th Author's Name Masaki MORI
6th Author's Affiliation Sapporo-Kosei Hospital
Date 2002/7/12
Paper # MI2002-41
Volume (vol) vol.102
Number (no) 223
Page pp.pp.-
#Pages 6
Date of Issue