Segmentation of ground glass opacity pulmonary nodules using an integrated active contour model with wavelet energy-based adaptive local energy and posterior probability-based speed function
Ground-glass opacity (GGO) pulmonary nodules in computerized tomography (CT) images are potential manifestations of lung cancer, which are more likely to be malignant. Segmentation of potential nodule objects is the first necessary step in computer-aided detection system of pulmonary nodules. Due to the fuzzy boundary and intensity inhomogeneity of GGO pulmonary nodules, it is hard to accurately segment them using traditional active contour models. This paper studies a method to accurately segment GGO nodules. A novel segmentation method using the integrated active contour model with wavelet energy-based adaptive local energy and posterior probability-based speed function, is proposed in this paper. Our approach has several novel aspects: (1) multi-features including the wavelet energy and texture feature are incorporated into the integrated active contour model. (2) the local domain for local energy model is selected adaptively based on k-nearest-neighbour (KNN) estimate method. (3) the posterior probability-based speed function of evolution is used. As-proposed method has been validated on a clinical dataset of 102 chest CT scans that contain 23 GGO nodules determined by a ground truth reading process, and evaluating the algorithm on the provided data leads to an average true positive ratio (TP), false positive ratio (FP) and the similarity (SI) of 85.02%, 18.42% and 84.67%, respectively. Results demonstrate that our proposed model can accurately segment part solid and nonsolid GGO nodules.
No References for this article.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: August 1, 2016
More about this publication?
- Materials Express is a peer-reviewed multidisciplinary journal reporting emerging researches on materials science, engineering, technology and biology. Cutting-edge researches on the synthesis, characterization, properties, and applications of a very wide range of materials are covered for broad readership; from physical sciences to life sciences. In particular, the journal aims to report advanced materials with interesting electronic, magnetic, optical, mechanical and catalytic properties for industrial applications.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites