Adaptive model based pulmonary artery segmentation in 3D chest CT

Marco Feuerstein; Takayuki Kitasaka; Kensaku Mori

doi:10.1117/12.843750

12 March 2010 Adaptive model based pulmonary artery segmentation in 3D chest CT

Marco Feuerstein, Takayuki Kitasaka, Kensaku Mori

Proceedings Volume 7623, Medical Imaging 2010: Image Processing; 76234S (2010) https://doi.org/10.1117/12.843750
Event: SPIE Medical Imaging, 2010, San Diego, California, United States

Abstract

The extraction and analysis of the pulmonary artery in computed tomography (CT) of the chest can be an important, but time-consuming step for the diagnosis and treatment of lung disease, in particular in non-contrast data, where the pulmonary artery has low contrast and frequently merges with adjacent tissue of similar intensity. We here present a new method for the automatic segmentation of the pulmonary artery based on an adaptive model, Hough and Euclidean distance transforms, and spline fitting, which works equally well on non-contrast and contrast enhanced data. An evaluation on 40 patient data sets and a comparison to manual segmentations in terms of Jaccard index, sensitivity, specificity, and minimum mean distance shows its overall robustness.

Citation Download Citation

Marco Feuerstein, Takayuki Kitasaka, and Kensaku Mori "Adaptive model based pulmonary artery segmentation in 3D chest CT", Proc. SPIE 7623, Medical Imaging 2010: Image Processing, 76234S (12 March 2010); https://doi.org/10.1117/12.843750

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available