Presentation 2012-02-10
A study on automated extraction of lymph nodes from two-phase 3D contrasted chest CT images
Mitsuhiro KISHIMOTO, Yukitaka NIMURA, Masahiro ODA, Takayuki KITASAKA, Shingo IWANO, Kensaku MORI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present a method for automated extraction of lymph nodes from 3D contrasted chest CT images taken in early- and late-phases. Image diagnoses of the lymph node metastases are quite important in lung cancer treatments. Automated extraction of lymph nodes from chest CT images by computers is expected to be developed. The previous extraction methods caused a lot of FPs (false positive) due to inadequate target processing regions and insufficient FP reduction processes. We extract lymph node candidates roughly by using the intensity features of the two-phase 3D contrasted chest CT images. We reduce FPs of the lymph node candidates based on the information of the smallest and longest axes of the candidates after processing by a region growing process. We evaluate our method using 42 cases of CT image pairs. The extraction results are compared with diagnosis results by a radiologist. Experimental results showed that the recall and precision rate of the extracted regions were 69.9% and 58.4%, respectively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Chest CT image / lymph nodes / computer assisted detection / local intensity structure analysis / region growing
Paper # PRMU2011-237,SP2011-152
Date of Issue

Conference Information
Committee SP
Conference Date 2012/2/2(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on automated extraction of lymph nodes from two-phase 3D contrasted chest CT images
Sub Title (in English)
Keyword(1) Chest CT image
Keyword(2) lymph nodes
Keyword(3) computer assisted detection
Keyword(4) local intensity structure analysis
Keyword(5) region growing
1st Author's Name Mitsuhiro KISHIMOTO
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Yukitaka NIMURA
2nd Author's Affiliation Strategy Office, Information and Communications Headquarters, Nagoya University
3rd Author's Name Masahiro ODA
3rd Author's Affiliation Graduate School of Information Science, Nagoya University
4th Author's Name Takayuki KITASAKA
4th Author's Affiliation School of Information Science, Aichi Institute of Technology
5th Author's Name Shingo IWANO
5th Author's Affiliation Graduate School of Medicine, Nagoya University
6th Author's Name Kensaku MORI
6th Author's Affiliation Strategy Office, Information and Communications Headquarters, Nagoya University:Graduate School of Information Science, Nagoya University
Date 2012-02-10
Paper # PRMU2011-237,SP2011-152
Volume (vol) vol.111
Number (no) 431
Page pp.pp.-
#Pages 6
Date of Issue