Article,

Lung Nodule Segmentation in CT Images using Rotation Invariant Local Binary Pattern

, and .
ACEEE International Journal of Signal and Image Processing, 4 (1): 4 (January 2013)

Abstract

As the lung cancer is the leading cause of cancer death in the medical field, Computed Tomography (CT) scan of the thorax is widely applied in diagnoses for identifying the lung cancer. In this paper, a technique of rotation invariant with Local Binary Pattern (LBP) for segmentation of various lung nodules from the Lung CT cancer data sets is used. This is tested on various lung data sets from teaching files of Casimage database and National Cancer Institute (NCI) of National Biomedical Imaging Archive (NBIA). The results show the segmented nodules with clear boundaries, which is helpful in diagnosis of lung cancer. Further, the results are compared with the watershed segmentation method, which shows that LBP based method yields better segmentation accuracy.

Tags

Users

  • @ideseditor

Comments and Reviews