The Use of a Slice Feature Vector of Classifying Diffuse Lung Opacities in High-Resolution Computed Tomography Images
Yoshihiro Mitani, Yusuke Fujita, Naofumi Matsunaga, Yoshihiko Hamamoto · 2012
The classification of diffuse lung opacities in high resolution computed tomography(HRCT) images is an important step for developing a computer-aided diagnosis(CAD) system. In designing the CAD system for classifying diffuse lung opacities in HRCT images, a histogram feature vector approach has been shown to be effective. In order to improve further the classification performance of the CAD system, we have explored another type of feature vector. Furthermore, the combination of these features may be used for lung opacities classification. In this paper, we have proposed the use of a slice feature vector. The experimental results show that the proposed method is promising.