DocumentCode :
2571442
Title :
An AAM-based detection approach of lung nodules from LDCT scans
Author :
Farag, Aly ; Abdelmunim, Hossam ; Graham, James ; Farag, A.A. ; Carter, Campbell ; Elshazly, Salwa ; El-Mogy, M.S. ; El-Mogy, S. ; Falk, Robert
Author_Institution :
Comput. Vision & Image Process. Lab. (CVIP Lab.), Univ. of Louisville, Louisville, KY, USA
fYear :
2012
fDate :
2-5 May 2012
Firstpage :
1040
Lastpage :
1043
Abstract :
In this, paper a new approach for lung nodules detection from LDCT scans is proposed. Intensity models of the nodules are generated using an active appearance model formulation. Template matching is used to compute a similarity score between the AAM template and the input image. The goal is to maximize the similarity measure at different image pixels to increase nodule detection. Conventional template matching does not account for rotation variations. Our proposed template matching approach is formulated as an energy optimization problem that computes a transformation that includes rotation(s) parameters as well as the AAM weighting coefficients. The approach is flexible to different scans and different nodule locations because of the ability to handle the variations in the rotation between the template and the input images. The approach can employ different similarity measures. Experimental results will be shown using three similarity measures from the literature: NCC, ZNCC and ZSSD; which illustrate the efficiency of the proposed approach. ROC curves for various nodule types are constructed on a clinical study with known ground truth, showing significant enhancements over conventional parametric nodule models and traditional template matching criterion.
Keywords :
computerised tomography; diseases; lung; medical image processing; optimisation; AAM based lung nodule detection; AAM template; LDCT scans; ROC curves; ZNCC similarity measure; ZSSD similarity measure; active appearance model formulation; energy optimization problem; input image; low dose CT; nodule intensity models; similarity measure maximisation; similarity score; template matching; zero mean normalized cross correlation; zero mean sum of squared differences; Active appearance model; Computational modeling; Computed tomography; Correlation; Lungs; Shape; Solid modeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on
Conference_Location :
Barcelona
ISSN :
1945-7928
Print_ISBN :
978-1-4577-1857-1
Type :
conf
DOI :
10.1109/ISBI.2012.6235736
Filename :
6235736
Link To Document :
بازگشت