DocumentCode :
2520717
Title :
MODEL-BASED JUNCTION DETECTION ALGORITHM WITH APPLICATIONS TO LUNG NODULE DETECTION
Author :
Zhao, Fei ; Mendonça, Paulo R S ; Bhotika, Rahul ; Miller, James V.
Author_Institution :
Dept. of Electr. Eng., Iowa Univ., Iowa City, IA
fYear :
2007
fDate :
12-15 April 2007
Firstpage :
504
Lastpage :
507
Abstract :
Among the many features used for classification in computer-aided detection (CAD) systems targeting pulmonary nodules, those based on differences between the shapes of nodules and vessels are most common. However, the explicit modeling of vessel junctions, often reported as the main source of false positive detections in CAD algorithms, has been largely neglected in the literature. We introduce a parametric junction model that captures the shape aspects of vessel junctions. Model parameters are expressed through probability distributions that encode medical knowledge on pulmonary vasculature. The usefulness of the model is demonstrated through its impact on the performance of a lung CAD algorithm
Keywords :
biomedical measurement; blood vessels; cancer; image classification; lung; medical image processing; physiological models; probability; CAD system classification; computer-aided detection; false positive detections; lung CAD algorithm; lung nodule; model-based junction detection algorithm; nodule shape; parametric junction model; probability distributions; pulmonary nodules; pulmonary vasculature; vessel junctions; vessel shape; Biomedical imaging; Design automation; Detection algorithms; Lungs; Medical diagnostic imaging; Probability distribution; Shape; Solid modeling; Surface fitting; US Department of Defense;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on
Conference_Location :
Arlington, VA
Print_ISBN :
1-4244-0672-2
Electronic_ISBN :
1-4244-0672-2
Type :
conf
DOI :
10.1109/ISBI.2007.356899
Filename :
4193333
Link To Document :
بازگشت