Shape-based CT lung nodule segmentation using five-dimensional mean shift clustering and MEM with shape information

Ye, Xujiong and Siddique, Musib and Beddoe, Gareth and Slabaugh, Greg (2009) Shape-based CT lung nodule segmentation using five-dimensional mean shift clustering and MEM with shape information. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro ISBI'09, June 28 - July 1 2009, Boston, MA, USA.

Full content URL: http://dx.doi.org/10.1109/ISBI.2009.5193089

Documents
SHAPE-BASED_CT_LUNG_NODULE_SEGMENTATION_USING_FIVE-DIMENSIONAL_MEAN_ISBS_2009.pdf

Request a copy
[img] PDF
SHAPE-BASED_CT_LUNG_NODULE_SEGMENTATION_USING_FIVE-DIMENSIONAL_MEAN_ISBS_2009.pdf
Restricted to Repository staff only

166kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

This paper presents a joint spatial-intensity-shape (JSIS)
feature-based method for the segmentation of CT lung nodules. First, a volumetric shape index (SI) feature based
on the second-order partial derivatives of the CT image is
calculated. Next, the SI feature is combined with spatial and intensity features to form a five-dimensional feature vectors, which are then clustered using mean shift to produce intensity and shape mode maps. Finally, a modified
expectation-maximization (MEM) algorithm is applied on
the mean shift intensity mode map to merge the neighboring
modes with spatial and shape mode maps as priors.
The proposed method has been evaluated on a clinical
dataset of thoracic CT scans that contains 80 nodules. A
volume overlap ratio between each segmented nodule and
the ground truth annotation is calculated. Using the proposed method, the mean overlap ratio over all the nodules is 0.81 with standard deviation of 0.05. Most of the nodules, including challenging juxta-vascular and juxta-pleural nodules, can be properly separated from adjoining tissues.

Additional Information:This paper presents a joint spatial-intensity-shape (JSIS) feature-based method for the segmentation of CT lung nodules. First, a volumetric shape index (SI) feature based on the second-order partial derivatives of the CT image is calculated. Next, the SI feature is combined with spatial and intensity features to form a five-dimensional feature vectors, which are then clustered using mean shift to produce intensity and shape mode maps. Finally, a modified expectation-maximization (MEM) algorithm is applied on the mean shift intensity mode map to merge the neighboring modes with spatial and shape mode maps as priors. The proposed method has been evaluated on a clinical dataset of thoracic CT scans that contains 80 nodules. A volume overlap ratio between each segmented nodule and the ground truth annotation is calculated. Using the proposed method, the mean overlap ratio over all the nodules is 0.81 with standard deviation of 0.05. Most of the nodules, including challenging juxta-vascular and juxta-pleural nodules, can be properly separated from adjoining tissues.
Keywords:Mean shift, mode map, expectationmaximization (EM), shape index, lung nodule
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:7317
Deposited On:23 Jan 2013 16:11

Repository Staff Only: item control page