Meeting Banner
Abstract #4906

Automatic Segmentation Pipeline for Patient-Specific MRI Tissue Models

Angel Torrado-Carvajal 1,2 , Juan A. Hernandez-Tamames 1,2 , Joaquin L. Herraiz 2 , Yigitcan Eryaman 2,3 , Elfar Adalsteinsson 4,5 , Lawrence L. Wald 3,5 , 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 Dept. of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, United States, 5 Harvard-MIT Health Sciences and Technology, MIT, Cambridge, Massachusetts, United States

Specific absorption rate (SAR) may cause unsafe tissue heating in High-Field MRI scanners. We propose a pipeline for patient-specific tissue modeling based only on MRI data that could enable patient-specific pulse design in High-Field MRI. We used open-source tools to automatically segment eleven tissue classes: brain white matter (WM), gray matter (GM), cerebrospinal fluid (CSF), cerebellum WM and GM, skull, skin, eyeballs, main arteries, muscle and fat/cartilage. The method was tested in 12 healthy subjects, and its accuracy was confirmed by an expert radiologist. The models are automatically meshed and exported in a format compatible with EM simulation software.

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

Join Here