Table of Contents
International Journal of Molecular Imaging
Volume 2013, Article ID 980769, 13 pages
http://dx.doi.org/10.1155/2013/980769
Clinical Study

Automatic Segmentation of Lung Carcinoma Using 3D Texture Features in 18-FDG PET/CT

1Medical Physics Unit, University of McGill, Montreal, QC, Canada H3A 0G4
2Department of Radiation Oncology, Odette Cancer Centre, the Sunnybrook Health Sciences Centre, Toronto, ON, Canada M4N 3M5
3Department of Radiation Oncology, Princess Margaret Hospital, Toronto, ON, Canada M5G 2M9

Received 11 September 2012; Revised 6 January 2013; Accepted 7 January 2013

Academic Editor: Hiroshi Watabe

Copyright © 2013 Daniel Markel et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

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.