Abstract #1177
A Multi-Atlas and Label Fusion Approach for Patient-Specific MRI Based Skull Segmentation
Angel Torrado-Carvajal 1,2 , Juan A. Hernandez-Tamames 1,2 , Joaquin L. Herraiz 2 , Yigitcan Eryaman 2,3 , Yves Rozenholc 4 , Elfar Adalsteinsson 5,6 , Lawrence L. Wald 3,6 , and Norberto Malpica 1,2
1
Dept. of Electronics, Universidad Rey Juan
Carlos, Mostoles, Madrid, Spain,
2
Madrid-MIT
M+Vision Consortium in RLE, MIT, Cambridge,
Massachusetts, United States,
3
Dept. of
Radiology, MGH, Martinos Center for Biomedical Imaging,
Charlestown, Massachusetts, United States,
4
MAP5,
CNRS UMR 8145, University Paris Descartes, Paris, Paris,
France,
5
Dept.
of Electrical Engineering and Computer Science, MIT,
Cambridge, Massachusetts, United States,
6
Harvard-MIT
Health Sciences and Technology, MIT, Cambridge,
Massachusetts, United States
MRI-based bone segmentation is a challenging but
important task for accurate construction of
patient-specific models. We propose a method for
complete skull segmentation based only on T1-weighted
images of the human head. The skull is estimated using a
multi-atlas (CT database) segmentation and label-fusion
approach. CTs are elastically registered to the patient
MRI image and thresholded. Then, the patient-specific
skull is estimated using label-fusion algorithms. The
method was tested in 12 healthy subjects; a radiologist
evaluated and considered all the segmentations as
accurate. The results may allow removing CT acquisitions
in several protocols, thus decreasing patient
ionization.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Click here for more information on becoming a member.
