Program Information
Fast MR-Based DRR Generation Using Highly Undersampled 3D Radial Trajectories
G Pereira1*, M Traughber2 , B Traughber1 , L Hu2 , K Su3 , R Muzic Jr3 , (1) University Hospitals Case Medical Center, Cleveland, OH, (2) Philips Healthcare, Highland Heights, OH, (3) Case Western Reserve University / University Hospitals Case Medical Center, Cleveland, OH.
Presentations
SU-E-J-251 Sunday 3:00PM - 6:00PM Room: Exhibit HallPurpose: The construction of a digitally reconstructed radiograph (DRR) from a magnetic resonance image (MRI) is possible if the cortical bone signal can be acquired and separated from air and soft tissue. This may be accomplished by subtracting a long echo-time, in-phase, gradient echo (GRE) image volume from an ultra-short echo time free induction decay (FID) image to produce a bone-enhanced (BE) image that reveals cortical bone. One limitation of this approach is the length of time required for data acquisition, which can limit the quality of the DRRs due to patient and organ motion. This study aimed to significantly reduce the acquisition time without compromising DRR quality.
Methods: Brain data were acquired from two volunteers using a 3T MR scanner (Ingenia, Philips Healthcare). The FID and GRE images were acquired in a single acquisition using a 3D radial readout sequence with the following parameters: TE1=0.142ms (ultra-short), TE2=2.197ms (nearly in-phase), 2*2*2mm3 isotropic voxels, 250*250*250mm3 FOV. To reduce the acquisition time, k-space was sampled at 75, 50 and 25% of a full 3D sphere . The TE2 image was subtracted from the TE1 image to generate the BE images. The BE images were used to generate DRRs using the Pinnacle treatment planning system (Philips-version 9.2). The quality of the DRRs was evaluated qualitatively by 5 board certified medical physicists for clinical usefulness.
Results: The acquisition time for 75, 50 and 25% sampling schemes were 219s, 146s, and 73s, respectively, the latter of which was a four-fold reduction in scan time compared to a 300s fully-sampled acquisition. All DRRs obtained were of acceptable quality and were shown to have sufficient information for clinical 2D image matching.
Conclusion: Undersampling k-space while maintaining the same range of frequency information results in significantly reduced scan time and clinically acceptable DRR image quality.
Funding Support, Disclosures, and Conflict of Interest: Drs. B Traughber and R Muzic have research support from Philips Healthcare. Drs. M Traughber and L Hu are employees of Philips Healthcare.
Contact Email: