skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours

Abstract

We are developing a computer-aided diagnosis (CAD) system to classify malignant and benign lung nodules found on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a three-dimensional (3D) active contour (AC) method. A data set of 96 lung nodules (44 malignant, 52 benign) from 58 patients was used in this study. The 3D AC model is based on two-dimensional AC with the addition of three new energy components to take advantage of 3D information: (1) 3D gradient, which guides the active contour to seek the object surface (2) 3D curvature, which imposes a smoothness constraint in the z direction, and (3) mask energy, which penalizes contours that grow beyond the pleura or thoracic wall. The search for the best energy weights in the 3D AC model was guided by a simplex optimization method. Morphological and gray-level features were extracted from the segmented nodule. The rubber band straightening transform (RBST) was applied to the shell of voxels surrounding the nodule. Texture features based on run-length statistics were extracted from the RBST image. Amore » linear discriminant analysis classifier with stepwise feature selection was designed using a second simplex optimization to select the most effective features. Leave-one-case-out resampling was used to train and test the CAD system. The system achieved a test area under the receiver operating characteristic curve (A{sub z}) of 0.83{+-}0.04. Our preliminary results indicate that use of the 3D AC model and the 3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD. The segmentation performance of the 3D AC model trained with our data set was evaluated with 23 nodules available in the Lung Image Database Consortium (LIDC). The lung nodule volumes segmented by the 3D AC model for best classification were generally larger than those outlined by the LIDC radiologists using visual judgment of nodule boundaries.« less

Authors:
; ; ; ; ; ; ;  [1]
  1. Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109 (United States)
Publication Date:
OSTI Identifier:
20853206
Resource Type:
Journal Article
Journal Name:
Medical Physics
Additional Journal Information:
Journal Volume: 33; Journal Issue: 7; Other Information: DOI: 10.1118/1.2207129; (c) 2006 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA); Journal ID: ISSN 0094-2405
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; CLASSIFICATION; COMPUTERIZED TOMOGRAPHY; DIAGNOSIS; IMAGE PROCESSING; IMAGES; LUNGS; NEOPLASMS; OPTIMIZATION; PATIENTS; PERFORMANCE; PLEURA; RESPIRATORS; ROUGHNESS

Citation Formats

Way, Ted W, Hadjiiski, Lubomir M, Sahiner, Berkman, Chan, H -P, Cascade, Philip N, Kazerooni, Ella A, Bogot, Naama, and Chuan, Zhou. Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours. United States: N. p., 2006. Web. doi:10.1118/1.2207129.
Way, Ted W, Hadjiiski, Lubomir M, Sahiner, Berkman, Chan, H -P, Cascade, Philip N, Kazerooni, Ella A, Bogot, Naama, & Chuan, Zhou. Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours. United States. https://doi.org/10.1118/1.2207129
Way, Ted W, Hadjiiski, Lubomir M, Sahiner, Berkman, Chan, H -P, Cascade, Philip N, Kazerooni, Ella A, Bogot, Naama, and Chuan, Zhou. Sat . "Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours". United States. https://doi.org/10.1118/1.2207129.
@article{osti_20853206,
title = {Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours},
author = {Way, Ted W and Hadjiiski, Lubomir M and Sahiner, Berkman and Chan, H -P and Cascade, Philip N and Kazerooni, Ella A and Bogot, Naama and Chuan, Zhou},
abstractNote = {We are developing a computer-aided diagnosis (CAD) system to classify malignant and benign lung nodules found on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a three-dimensional (3D) active contour (AC) method. A data set of 96 lung nodules (44 malignant, 52 benign) from 58 patients was used in this study. The 3D AC model is based on two-dimensional AC with the addition of three new energy components to take advantage of 3D information: (1) 3D gradient, which guides the active contour to seek the object surface (2) 3D curvature, which imposes a smoothness constraint in the z direction, and (3) mask energy, which penalizes contours that grow beyond the pleura or thoracic wall. The search for the best energy weights in the 3D AC model was guided by a simplex optimization method. Morphological and gray-level features were extracted from the segmented nodule. The rubber band straightening transform (RBST) was applied to the shell of voxels surrounding the nodule. Texture features based on run-length statistics were extracted from the RBST image. A linear discriminant analysis classifier with stepwise feature selection was designed using a second simplex optimization to select the most effective features. Leave-one-case-out resampling was used to train and test the CAD system. The system achieved a test area under the receiver operating characteristic curve (A{sub z}) of 0.83{+-}0.04. Our preliminary results indicate that use of the 3D AC model and the 3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD. The segmentation performance of the 3D AC model trained with our data set was evaluated with 23 nodules available in the Lung Image Database Consortium (LIDC). The lung nodule volumes segmented by the 3D AC model for best classification were generally larger than those outlined by the LIDC radiologists using visual judgment of nodule boundaries.},
doi = {10.1118/1.2207129},
url = {https://www.osti.gov/biblio/20853206}, journal = {Medical Physics},
issn = {0094-2405},
number = 7,
volume = 33,
place = {United States},
year = {2006},
month = {7}
}