Bayesian wavelet snake for computer-aided diagnosis of lung nodules

Article type: Research Article

Authors: Yoshida, Hiroyuki^{a; *} | Keserci, Bilgin^b

Affiliations: [a] Department of Radiology, Biological Sciences Division, The University of Chicago, 5841 South Maryland Avenue, Chicago, IL 60637, USA | [b] The Chicago Medical School, Department of Medical Radiation Physics, Finch University of Health Sciences, 3333 Green Bay Road, North Chicago, IL 60064, USA

Correspondence: [*] Corresponding author. Tel.: +1 773 834 3154; Fax: +1 773 702 0371; E-mail: [email protected]

Abstract: An edge-guided active contour based on the wavelet transform called the Bayesian wavelet snake has been developed for identifying a closed-contour object with a fuzzy and low-contrast boundary. The wavelet snake is designed to deform its shape based on a maximum a posteriori estimate calculated by the fast wavelet transform. Our new method was applied to a computer-aided diagnosis scheme for detection of pulmonary nodules in digital chest radiographs. In this scheme, a filter based on the edge gradient was employed for enhancement of nodules, followed by creation of multiscale edges by spline wavelets for extraction of portions of the boundary of a candidate nodule. These multiscale edges are then used to “guide” the wavelet snake for estimation of the boundary of the nodule. The degree of overlap between the resulting snake and the multiscale edges was used as a feature for distinguishing nodules from false-positive detections that consist of only normal anatomic structures. The wavelet snake was combined with morphological features by means of an artificial neural network for further reduction of false detections. The performance of our scheme was evaluated by receiver operating characteristic analysis based on a publicly available database of chest radiographs.

DOI: 10.3233/ICA-2000-7306

Journal: Integrated Computer-Aided Engineering, vol. 7, no. 3, pp. 253-269, 2000