IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2006-01-27 17:00
Study of classifiers for computer-aided detection system of liver lesions from two phase 3-D CT images
Takahiro Kawamura, Akinobu Shimizu, Hidefumi Kobatake, Mitsutaka Nemoto (TUAT)
Abstract (in Japanese) (See Japanese page) 
(in English) This paper proposes a method for automated extraction of tumor regions based on information fusion of two phases of three dimensional CT images.
At first it extracts the liver region using two phases and enhances tumor regions in the liver using a three dimensional adaptive convergence index filter.
Then it makes the fusion images by computing the sum of gray values in the enhanced images, and detects local maximum points and extracts candidates regions by a region growing method on the tumor likelihood images.
In the next step, several features about the candidates are measured and the system decides whether it corresponds to true tumors or not using classifiers.
In the experiment, three kinds of classifiers of Mahalanobis distance, support vector machine, and AdaBoosting are compared.
We applied the proposed system to three dimensional abdominal CT images from 26 patients obtained with multi-detector row CT scanners and confirmed that tumor detection rate was 100% with 0.07 false positives per case.
Keyword (in Japanese) (See Japanese page) 
(in English) Computer Aided Diagnosis / Abdominal CT Images / Mahalanobis Distance / Support Vector Machine / AdaBoosting / / /  
Reference Info. IEICE Tech. Rep., vol. 105, no. 579, MI2005-103, pp. 147-150, Jan. 2006.
Paper # MI2005-103 
Date of Issue 2006-01-20 (MI) 
ISSN Print edition: ISSN 0913-5685
Download PDF

Conference Information
Committee MI  
Conference Date 2006-01-27 - 2006-01-28 
Place (in Japanese) (See Japanese page) 
Place (in English) Miyakojimashi-Chuo-Kouminkan 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To MI 
Conference Code 2006-01-MI 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Study of classifiers for computer-aided detection system of liver lesions from two phase 3-D CT images 
Sub Title (in English)  
Keyword(1) Computer Aided Diagnosis  
Keyword(2) Abdominal CT Images  
Keyword(3) Mahalanobis Distance  
Keyword(4) Support Vector Machine  
Keyword(5) AdaBoosting  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Takahiro Kawamura  
1st Author's Affiliation Tokyo University of Agriculture and Technology (TUAT)
2nd Author's Name Akinobu Shimizu  
2nd Author's Affiliation Tokyo University of Agriculture and Technology (TUAT)
3rd Author's Name Hidefumi Kobatake  
3rd Author's Affiliation Tokyo University of Agriculture and Technology (TUAT)
4th Author's Name Mitsutaka Nemoto  
4th Author's Affiliation Tokyo University of Agriculture and Technology (TUAT)
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2006-01-27 17:00:00 
Presentation Time 15 minutes 
Registration for MI 
Paper # MI2005-103 
Volume (vol) vol.105 
Number (no) no.579 
Page pp.147-150 
#Pages
Date of Issue 2006-01-20 (MI) 


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan