TY - JOUR
T1 - Deformable registration of glioma images using em algorithm and diffusion reaction modeling
AU - Gooya, Ali
AU - Biros, George
AU - Davatzikos, Christos
N1 - Funding Information:
Manuscript received July 08, 2010; revised September 11, 2010; accepted September 11, 2010. Date of publication September 27, 2010; date of current version February 02, 2011. This work was supported by National Institute of Health Grant 5R01NS042645. Asterisk indicates corresponding author. *A. Gooya is with the Section of Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104 USA (e-mail: ali.gooya@uphs.upenn.edu). C. Davatzikos is with the Section of Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104 USA (e-mail: christos.davatzikos@uphs.upenn.edu). G. Biros is with the College of Engineering Biomedical Engineering, Georgia ColorversionsofoneormoreofthefiguresinthispaperareavailableonlineInstituteofTechnology,Atlanta,GA30332USA(e-mail:biros@gatech.edu). LIOBLASTOMA multiforme (GBM), a primary malig-athttp://ieeexplore.ieee.org. G nant brain tumor, is the most common form of the glioma Digital Object Identifier 10.1109/TMI.2010.2078833 tumors, which in spite of multimodality treatments, remains as
PY - 2011/2
Y1 - 2011/2
N2 - This paper investigates the problem of atlas registration of brain images with gliomas. Multiparametric imaging modalities (T1, T1-CE, T2, and FLAIR) are first utilized for segmentations of different tissues, and to compute the posterior probability map (PBM) of membership to each tissue class, using supervised learning. Similar maps are generated in the initially normal atlas, by modeling the tumor growth, using reaction-diffusion equation. Deformable registration using a demons-like algorithm is used to register the patient images with the tumor bearing atlas. Joint estimation of the simulated tumor parameters (e.g., location, mass effect and degree of infiltration), and the spatial transformation is achieved by maximization of the log-likelihood of observation. An expectation-maximization algorithm is used in registration process to estimate the spatial transformation and other parameters related to tumor simulation are optimized through asynchronous parallel pattern search (APPSPACK). The proposed method has been evaluated on five simulated data sets created by statistically simulated deformations (SSD), and fifteen real multichannel glioma data sets. The performance has been evaluated both quantitatively and qualitatively, and the results have been compared to ORBIT, an alternative method solving a similar problem. The results show that our method outperforms ORBIT, and the warped templates have better similarity to patient images.
AB - This paper investigates the problem of atlas registration of brain images with gliomas. Multiparametric imaging modalities (T1, T1-CE, T2, and FLAIR) are first utilized for segmentations of different tissues, and to compute the posterior probability map (PBM) of membership to each tissue class, using supervised learning. Similar maps are generated in the initially normal atlas, by modeling the tumor growth, using reaction-diffusion equation. Deformable registration using a demons-like algorithm is used to register the patient images with the tumor bearing atlas. Joint estimation of the simulated tumor parameters (e.g., location, mass effect and degree of infiltration), and the spatial transformation is achieved by maximization of the log-likelihood of observation. An expectation-maximization algorithm is used in registration process to estimate the spatial transformation and other parameters related to tumor simulation are optimized through asynchronous parallel pattern search (APPSPACK). The proposed method has been evaluated on five simulated data sets created by statistically simulated deformations (SSD), and fifteen real multichannel glioma data sets. The performance has been evaluated both quantitatively and qualitatively, and the results have been compared to ORBIT, an alternative method solving a similar problem. The results show that our method outperforms ORBIT, and the warped templates have better similarity to patient images.
KW - Brain tumor
KW - deformable registration
KW - expectation-maximization (EM) algorithm
KW - reaction-diffusion equation
KW - statistical atlas
KW - tumor growth modeling
UR - http://www.scopus.com/inward/record.url?scp=79551591281&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79551591281&partnerID=8YFLogxK
U2 - 10.1109/TMI.2010.2078833
DO - 10.1109/TMI.2010.2078833
M3 - Article
C2 - 20876010
AN - SCOPUS:79551591281
SN - 0278-0062
VL - 30
SP - 375
EP - 390
JO - IEEE transactions on medical imaging
JF - IEEE transactions on medical imaging
IS - 2
M1 - 5585769
ER -