TY - GEN
T1 - A new 3D automatic segmentation framework for accurate segmentation of prostate from DCE-MRI
AU - Firjani, A.
AU - Elnakib, A.
AU - Khalifa, F.
AU - Gimel'Farb, G.
AU - Abo El-Ghar, M.
AU - Suri, J.
AU - Elmaghraby, A.
AU - El-Baz, A.
PY - 2011
Y1 - 2011
N2 - Prostate segmentation is an essential step in developing any noninvasive Computer-Assisted Diagnostic (CAD) system for the early diagnosis of prostate cancer using Magnetic Resonance Images (MRI). In this paper, a novel framework for 3D segmentation of the prostate region from Dynamic Contrast Enhancement MRI (DCE-MRI) is proposed. The framework is based on Maximum A Posteriori (MAP) estimate of a new log-likelihood function that consists of : (i) 1 st-order visual appearance descriptors of the DCE-MRI, (ii) a 3D spatially rotation-variant 2nd-order homogeneity descriptor, and (iii) a 3D prostate shape descriptor. The shape prior is learned from the co-aligned 3D segmented prostate data. The visual appearances of the object and its background are described with marginal gray-level distributions obtained by separating their mixture over prostate data. The spatial interactions between the prostate voxels are modeled by a 3D 2nd-order rotation-variant Markov-Gibbs Random Field (MGRF) of object/background labels with analytically estimated potentials. Experiments with in vivo prostate DCE-MRI confirm the robustness and accuracy of the proposed approach.
AB - Prostate segmentation is an essential step in developing any noninvasive Computer-Assisted Diagnostic (CAD) system for the early diagnosis of prostate cancer using Magnetic Resonance Images (MRI). In this paper, a novel framework for 3D segmentation of the prostate region from Dynamic Contrast Enhancement MRI (DCE-MRI) is proposed. The framework is based on Maximum A Posteriori (MAP) estimate of a new log-likelihood function that consists of : (i) 1 st-order visual appearance descriptors of the DCE-MRI, (ii) a 3D spatially rotation-variant 2nd-order homogeneity descriptor, and (iii) a 3D prostate shape descriptor. The shape prior is learned from the co-aligned 3D segmented prostate data. The visual appearances of the object and its background are described with marginal gray-level distributions obtained by separating their mixture over prostate data. The spatial interactions between the prostate voxels are modeled by a 3D 2nd-order rotation-variant Markov-Gibbs Random Field (MGRF) of object/background labels with analytically estimated potentials. Experiments with in vivo prostate DCE-MRI confirm the robustness and accuracy of the proposed approach.
UR - http://www.scopus.com/inward/record.url?scp=80055056277&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80055056277&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2011.5872679
DO - 10.1109/ISBI.2011.5872679
M3 - Conference contribution
AN - SCOPUS:80055056277
SN - 9781424441280
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1476
EP - 1479
BT - 2011 8th IEEE International Symposium on Biomedical Imaging
T2 - 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
Y2 - 30 March 2011 through 2 April 2011
ER -
