This paper focuses on characterizing the internal intensity structure of pulmonary nodules in thin-section CT images for classification between benign and malignant nodules. This approach makes use of shape index curvedness, and CT density to represent locally each voxel constructing the three-dimensional (3D) pulmonary nodule image. From the distribution of shape index, curvedness, and CT density over the 3D pulmonary nodule image a set of histogram features, and 3D texture features is computed to classify benign and malignant nodules. Linear discriminant analysis is used for classification and a receiver operating characteristic (ROC) analysis is used to evaluate the classification accuracy. The potential usefulness of the curvature-based features in the computer-aided differential diagnosis is demonstrated by using ROC curves as the performance measure.
Computer aided differential diagnosis of pulmonary nodules using curvature based analysis
1999-01-01
233779 byte
Conference paper
Electronic Resource
English
Computer Aided Differential Diagnosis of Pulmonary Nodules using Curvature Based Analysis
British Library Conference Proceedings | 1999
|Pulmonary nodules computer-aided diagnosis based on feature integration and ABC-LVQ network
British Library Online Contents | 2018
|Computer-aided fault diagnosis
Automotive engineering | 1985
Automated Computer Aided Diagnosis and Simulation
British Library Conference Proceedings | 1997
|An Automatic Pulmonary Nodules Detection Method Using 3D Adaptive Template Matching
British Library Conference Proceedings | 2014
|