Presentation 2002/5/9
A method for automated extraction of the aorta area from 3D abdominal X-ray CT images without contrast medium by using edge information
Hirofumi OGAWA, Takayuki KITASAKA, Kensaku MORI, Jui-ichi HASEGAWA, Junichiro TORIWAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have already developed a method for extracting aorta areas in abdominal CT images. In this method the region growing method was used. However mis-extraction was caused when aorta touched other organs extensively. Here we propose a new method for extraction of aorta areas to reduce the mis-extraction areas. The edge information and the medial line of the aorta are used in the proposed method. First, the minimum distance from the edge areas is calculated at each voxel. The obtained image is called the distance image. The spine area is also extracted to determine the position of the aorta using the anatomical relationship between spines and aortas. Second, the medial line of the aorta is extracted by tracing local maxima of the distance image using the position of the aorta obtained above. Finally, the aorta area is extracted by applying the reverse Euclidean distance transformation to voxels on the medial line. We applied the proposed method to eleven 3D abdominal X-ray CT images without the contrast medium, and showed that proper aorta areas were obtained.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) 3D abdominal X-ray CT image / aorta / Euclidean distance transformation / spine / 3D image processing
Paper # PRMU2002-2
Date of Issue

Conference Information
Committee PRMU
Conference Date 2002/5/9(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A method for automated extraction of the aorta area from 3D abdominal X-ray CT images without contrast medium by using edge information
Sub Title (in English)
Keyword(1) 3D abdominal X-ray CT image
Keyword(2) aorta
Keyword(3) Euclidean distance transformation
Keyword(4) spine
Keyword(5) 3D image processing
1st Author's Name Hirofumi OGAWA
1st Author's Affiliation Graduate School of Engineering, Nagoya University()
2nd Author's Name Takayuki KITASAKA
2nd Author's Affiliation Graduate School of Engineering, Nagoya University
3rd Author's Name Kensaku MORI
3rd Author's Affiliation Research center for Advanced Waste and Emission Management, Nagoya University
4th Author's Name Jui-ichi HASEGAWA
4th Author's Affiliation School of computer and Congnitive Sciences, Chukyo University
5th Author's Name Junichiro TORIWAKI
5th Author's Affiliation Graduate School of Engineering, Nagoya University
Date 2002/5/9
Paper # PRMU2002-2
Volume (vol) vol.102
Number (no) 54
Page pp.pp.-
#Pages 6
Date of Issue