Automatic Lung Field Segmentation Based on Non Negative Matrix Factorization and Fuzzy Clustering

Abstract

Obtaining accurate and automated lung field segmentation is a challenging step in the development of Computer-Aided Diagnosis (CAD) system. In this paper fully automatic lung field segmentation is proposed. Initially, a visual appearance model is constructed by considering spatial interaction of the neighbouring pixels. Then constrained non-negative matrix factorization (CNMF) factorized the data matrix obtained from the visual appearance model into basis and coefficient matrices. Initial lung segmentation is achieved by applying fuzzy c-means clustering on the obtained coefficient matrix. Trachea and bronchi appearing in the initial lung segmentation are removed by 2-D region growing operation. Finally, the lung contour is smooth by using boundary smoothing step. The experimental results on different database shows that the proposed method produces significant DSC 0.987 as compared to the existing lung segmentation algorithms.