By Topic

Computerized Detection of Lung Nodules in CT Images by Use of Multiscale Filters and Geometrical Constraint Region Growing

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Pei Xiaomin ; Sino -Dutch Biomed. & Inf. Eng. Sch., Northeastern Univ., Shenyang, China ; Guo Hongyu ; Dai Jianping

It is important to enhance and detect pulmonary nodules in computed tomography(CT) images in order to assist radiologists in the detection of lung cancer. Nodules which are included in medical image generally have multiple size and scale and have blob-like structure. Recently, 3D multiscale filter approach is proposed for lung nodules detection. However, the 3D method takes too much computing time to be applicable in computer-aided diagnostic (CAD). In this paper, we propose a three step method for lung nodule detection in CT images. Firstly, we use 2D multiscale filter to detect the candidates of lung nodules on the slice images. Secondly, distinguish nodules between non-nodules which have blob-like shape by use of geometrical constraint region growing. Finally, extract shape features of each region and use an automated rule-based classifier for reduction of false positives. The experimental results indicate that our algorithm can achieve a relatively high performance for nodule detection.

Published in:

Bioinformatics and Biomedical Engineering (iCBBE), 2010 4th International Conference on

Date of Conference:

18-20 June 2010