Presentation 2012-01-20
Robust Bronchus Extraction using Machine Learning and Minimum Spanning Tree
Tsutomu INOUE, Yoshiro KITAMURA, Yuanzhong LI, Wataru ITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Virtual bronchoscopy based on Chest CT is the important process, for a physician to grasp bronchial structure of patients before peripheral bronchuoscopy examination. However, extraction bronchium manually is a time-consuming task. To do the extraction automatically, there are two difficulties. The first is over-extraction of bronchus-like structure. The second is miss-extraction of bronchus regions due to stenoses and motion artifacts. Our method solves the first by introducing machine learning, and the second by introducing minimum spanning tree. Experimental results show our method solved the two difficulties successfully.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Chest Computed Tomography / Bronchus Extraction / Machine Learning / AdaBoost / Graph Theory / Minimum Spanning Tree
Paper # MI2011-116
Date of Issue

Conference Information
Committee MI
Conference Date 2012/1/12(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) Robust Bronchus Extraction using Machine Learning and Minimum Spanning Tree
Sub Title (in English)
Keyword(1) Chest Computed Tomography
Keyword(2) Bronchus Extraction
Keyword(3) Machine Learning
Keyword(4) AdaBoost
Keyword(5) Graph Theory
Keyword(6) Minimum Spanning Tree
1st Author's Name Tsutomu INOUE
1st Author's Affiliation Fujifilm Corporation()
2nd Author's Name Yoshiro KITAMURA
2nd Author's Affiliation Fujifilm Corporation
3rd Author's Name Yuanzhong LI
3rd Author's Affiliation Fujifilm Corporation
4th Author's Name Wataru ITO
4th Author's Affiliation Fujifilm Corporation
Date 2012-01-20
Paper # MI2011-116
Volume (vol) vol.111
Number (no) 389
Page pp.pp.-
#Pages 6
Date of Issue