Automatic Segmentation of Lung Carcinoma Using 3D Texture Features in 18-FDG PETCT
Joint Authors
Alasti, Hamideh
Markel, Daniel
Soliman, Hany
Caldwell, Curtis B.
Lee, Justin
Ung, Yee
Sun, Alexander
Source
International Journal of Molecular Imaging
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-02-26
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
Target definition is the largest source of geometric uncertainty in radiation therapy.
This is partly due to a lack of contrast between tumor and healthy soft tissue for computed tomography (CT) and due to blurriness, lower spatial resolution, and lack of a truly quantitative unit for positron emission tomography (PET).
First-, second-, and higher-order statistics, Tamura, and structural features were characterized for PET and CT images of lung carcinoma and organs of the thorax.
A combined decision tree (DT) with K-nearest neighbours (KNN) classifiers as nodes containing combinations of 3 features were trained and used for segmentation of the gross tumor volume.
This approach was validated for 31 patients from two separate institutions and scanners.
The results were compared with thresholding approaches, the fuzzy clustering method, the 3-level fuzzy locally adaptive Bayesian algorithm, the multivalued level set algorithm, and a single KNN using Hounsfield units and standard uptake value.
The results showed the DTKNN classifier had the highest sensitivity of 73.9%, second highest average Dice coefficient of 0.607, and a specificity of 99.2% for classifying voxels when using a probabilistic ground truth provided by simultaneous truth and performance level estimation using contours drawn by 3 trained physicians.
American Psychological Association (APA)
Markel, Daniel& Caldwell, Curtis B.& Alasti, Hamideh& Soliman, Hany& Ung, Yee& Lee, Justin…[et al.]. 2013. Automatic Segmentation of Lung Carcinoma Using 3D Texture Features in 18-FDG PETCT. International Journal of Molecular Imaging،Vol. 2013, no. 2013, pp.1-13.
https://search.emarefa.net/detail/BIM-513233
Modern Language Association (MLA)
Markel, Daniel…[et al.]. Automatic Segmentation of Lung Carcinoma Using 3D Texture Features in 18-FDG PETCT. International Journal of Molecular Imaging No. 2013 (2013), pp.1-13.
https://search.emarefa.net/detail/BIM-513233
American Medical Association (AMA)
Markel, Daniel& Caldwell, Curtis B.& Alasti, Hamideh& Soliman, Hany& Ung, Yee& Lee, Justin…[et al.]. Automatic Segmentation of Lung Carcinoma Using 3D Texture Features in 18-FDG PETCT. International Journal of Molecular Imaging. 2013. Vol. 2013, no. 2013, pp.1-13.
https://search.emarefa.net/detail/BIM-513233
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-513233