Lung2

International Journal of Computer Applications, 2015

A novel classification method for the four types of lung nodules, i.e., well-circumscribed, vascularized, juxta-pleural, and pleural-tail, in low dose computed tomography scans is proposed. The method is capable to perform fully automatic segmentation and nodule detection from CT Scan Lungs images, based solely on information contained by the image itself. The proposed method is based on contextual analysis by combining the lung nodule and surrounding anatomical structures, and has three main stages. An adaptive patch-based division is used to construct concentric multilevel partition and feature set is designed to incorporate intensity, texture, and gradient information for image patch feature description. Finally, Decision tree classifier is utilized for classification of lung nodules. The system has been tested with a number of real Computed Tomography lung images and has achieved satisfactory results in classifying the lung diseases. The results show that the proposed method achieves higher classification performance than traditional methods.

2007

Computers in Biology and Medicine, 2009