Curvature-based characterization of shape and internal intensity structure for classification of pulmonary nodules using thin-section CT images

Yoshiki Kawata, Noboru Niki, Hironobu Ohmatsu, Masahiko Kusumoto, Ryutaro Kakinuma, Kiyoshi Mori, Hiroyuki Nishiyama, Kenji Eguchi, Masahiro Kaneko, Noriyuki Moriyama

Abstract

This paper presents a curvature based approach to characterize the internal intensity structure of pulmonary nodules in thin-section CT images. This approach makes use of shape index, curvedness, and CT value to represent locally each voxel in a 3D pulmonary nodule image. From the distribution of shape index, curvedness, and CT value over the 3D pulmonary nodule image a set of 3D moment features, histogram features, and 3D texture features is computed to classify benign and malignant pulmonary 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.
BibTeX
@inproceedings{kawata1999curvature,
  author = {Yoshiki Kawata and Noboru Niki and Hironobu Ohmatsu and Masahiko Kusumoto and Ryutaro Kakinuma and Kiyoshi Mori and Hiroyuki Nishiyama and Kenji Eguchi and Masahiro Kaneko and Noriyuki Moriyama},
  title = {{Curvature-based characterization of shape and internal intensity structure for classification of pulmonary nodules using thin-section CT images}},
  booktitle = {Image Processing},
  year = {1999},
  doi = {10.1117/12.348610},
}

Loading related content...

Figure