UNIGE document Scientific Article
previous document  unige:40055  next document
add to browser collection

Contourlet-based active contour model for PET image segmentation

Abdoli, M
Dierckx, R A J O
Published in Medical Physics. 2013, vol. 40, no. 8, p. 082507
Abstract PET-guided radiation therapy treatment planning, clinical diagnosis, assessment of tumor growth, and therapy response rely on the accurate delineation of the tumor volume and quantification of tracer uptake. Most PET image segmentation techniques proposed thus far are suboptimal in the presence of heterogeneity of tracer uptake within the lesion. This work presents an active contour model approach based on the method of Chan and Vese ["Active contours without edges," IEEE Trans. Image Process. 10, 266-277 (2001)] designed to take into account the high level of statistical uncertainty (noise) and to handle the heterogeneity of tumor uptake typically present in PET images.
Keywords HumansImage Processing, Computer-Assisted/methodsLung Neoplasms/radionuclide imagingModels, TheoreticalPhantoms, ImagingPositron-Emission Tomography/methods
PMID: 23927352
Full text
Article (Published version) (1.3 MB) - public document Free access
Research group Imagerie Médicale (TEP et TEMP) (542)
Project FNS: SNF 31003A-149957
(ISO format)
ABDOLI, M, DIERCKX, R A J O, ZAIDI, Habib. Contourlet-based active contour model for PET image segmentation. In: Medical Physics, 2013, vol. 40, n° 8, p. 082507. doi: 10.1118/1.4816296 https://archive-ouverte.unige.ch/unige:40055

394 hits



Deposited on : 2014-09-09

Export document
Format :
Citation style :