ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2016-08-08 13:30
Multi-stage identification of GGO candidate regions using DCNN and SVM
Kazuki Hirayama, Joo Kooi Tan, Hyoungseop Kim (KIT), Takatoshi Aoki (UOEH), Shoji Kido (YU)
Abstract (in Japanese) (See Japanese page) 
(in English) Recently, the development of CAD (Computer Aided Diagnosis) system for the purpose of reducing the burden to the physicians and improving accuracy of lesion detection has been advanced. In this paper, we propose an automatic extraction method of GGO (Ground Glass Opacity) candidate regions from the chest CT image. The flow of the main processings are, extracting the lung area from the chest CT image, the removal of a blood vessel regions, bronchus region by 3D line enhancement filter. Then, we selected the initial GGO candidate regions by the density-gradient threshold processing, and identifies with DCNN (Deep Convolutional Neural Network) for that areas. Finally, we calculates the features, to reduce the false-positive shadow by the rule-based method, performs identification of the final GGO candidate regions by SVM (Support Vector Machine).
Keyword (in Japanese) (See Japanese page) 
(in English) Ground Glass Opacity / Computer Aided Diagnosis / Lung Image Database Consortium / Deep Convolutional Neural Network / Support Vector Machine / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
Download PDF

Conference Information
Conference Date 2016-08-08 - 2016-08-09 
Place (in Japanese) (See Japanese page) 
Place (in English)  
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To IEICE-IE 
Conference Code 2016-08-IE-ME-AVM-CE 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Multi-stage identification of GGO candidate regions using DCNN and SVM 
Sub Title (in English)  
Keyword(1) Ground Glass Opacity  
Keyword(2) Computer Aided Diagnosis  
Keyword(3) Lung Image Database Consortium  
Keyword(4) Deep Convolutional Neural Network  
Keyword(5) Support Vector Machine  
1st Author's Name Kazuki Hirayama  
1st Author's Affiliation Kyushu Institute of Technology (KIT)
2nd Author's Name Joo Kooi Tan  
2nd Author's Affiliation Kyushu Institute of Technology (KIT)
3rd Author's Name Hyoungseop Kim  
3rd Author's Affiliation Kyushu Institute of Technology (KIT)
4th Author's Name Takatoshi Aoki  
4th Author's Affiliation University of Occupational and Environmental Health (UOEH)
5th Author's Name Shoji Kido  
5th Author's Affiliation Yamaguchi University (YU)
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 2016-08-08 13:30:00 
Presentation Time 30 minutes 
Registration for IEICE-IE 
Paper #  
Volume (vol) vol.40 
Number (no)  
Date of Issue  

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan