Share Email Print

Proceedings Paper

Differentiating solitary pulmonary nodules (SPNs) with 3D shape features
Author(s): Yang Wang; Michael F. Mcnitt-Gray; Matthew S. Brown; Jonathan G. Goldin; Haiming Zhao; Denise R. Aberle
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This study developed a methodology to extract the quantitative features of representing nodule 3D shape and investigate the performance of these features in differentiating between benign and malignant solitary pulmonary nodules (SPNs). 36 cases with solitary lung nodules (15 Benign, 21 Malignant) were examined in this study. The CT helical scanning-parameters were ⩽3 mm collimation, pitch 1-2, and 1.5-3 mm reconstruction interval. The nodule boundaries were contoured by radiologists on 3D volume data. Using these boundaries, the nodule physical 3D surfaces were created and several 3D nodule shape-features were computed, including: Compactness Factor (CF) of nodule, Shape Index (SI) and curvedness of each pixel in the physical 3D nodule surface. The histogram characteristic features of SI and curvedness were calculated. AdaBoost was performed to select the features and their statistically differences were analyzed. Logistic Regression Analysis (LRA) and AdaBoost were used to evaluate the overall diagnostic accuracy. For 36 patients, CF is the first feature selected by AdaBoost, which also has significant difference (t-test, P=0.6%) between Benign and malignant nodules. However, histogram features of SI and curvedness are not all significantly different. The accuracy of LRA is 75%, with accuracies of AdaBoost using all features is about 80% with cross validation. Generally, SI, curvedness and CF may provide a comprehensive examination of the nodule shape, which can be used in differentiating benign from malignant SPNs. However, other types' features (such as texture, angiogenesis) should be combined with shape information to assist radiologists in characterizing SPNs more accurately.

Paper Details

Date Published: 30 March 2007
PDF: 8 pages
Proc. SPIE 6514, Medical Imaging 2007: Computer-Aided Diagnosis, 65143D (30 March 2007); doi: 10.1117/12.713686
Show Author Affiliations
Yang Wang, Univ. of California, Los Angeles (United States)
Michael F. Mcnitt-Gray, Univ. of California, Los Angeles (United States)
Matthew S. Brown, Univ. of California, Los Angeles (United States)
Jonathan G. Goldin, Univ. of California, Los Angeles (United States)
Haiming Zhao, Univ. of California, Los Angeles (United States)
Denise R. Aberle, Univ. of California, Los Angeles (United States)

Published in SPIE Proceedings Vol. 6514:
Medical Imaging 2007: Computer-Aided Diagnosis
Maryellen L. Giger; Nico Karssemeijer, Editor(s)

© SPIE. Terms of Use
Back to Top