Meeting Banner
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.

This abstract and the presentation materials are available to members only; a login is required.

Join Here