TU‐AB‐BRA‐03: Atlas‐Based Algorithms with Local Registration‐Goodness Weighting for MRI‐Driven Electron Density Mapping

Abstract

Purpose:To develop image‐analysis algorithms to synthesize CT with accurate electron densities for MR‐only radiotherapy of head & neck (H&N) and pelvis anatomies.Methods:CT and 3T‐MRI (Philips, mDixon sequence) scans were randomly selected from a pool of H&N (n=11) and pelvis (n=12) anatomies to form an atlas. All MRIs were pre‐processed to eliminate scanner and patient‐induced intensity inhomogeneities and standardize their intensity histograms. CT and MRI for each patient were then co‐registered to construct CT‐MRI atlases. For more accurate CT‐MR fusion, bone intensities in CT were suppressed to improve the similarity between CT and MRI. For a new patient, all CT‐MRI atlases are deformed onto the new patients’ MRI initially. A newly‐developed generalized registration error (GRE) metric was then calculated as a measure of local registration accuracy. The synthetic CT value at each point is a 1/GRE‐weighted average of CTs from all CT‐MR atlases. For evaluation, the mean absolute error (MAE) between the original and synthetic CT (generated in a leave‐one‐out scheme) was computed. The planning dose from the original and synthetic CT was also compared.Results:For H&N patients, MAE was 67±9, 114±22, and 116±9 HU over the entire‐CT, air and bone regions, respectively. For pelvis anatomy, MAE was 47±5 and 146±14 for the entire and bone regions. In comparison with MIRADA medical, an FDA‐approved registration tool, we found that our proposed registration strategy reduces MAE by ∼30% and ∼50% over the entire and bone regions, respectively. GRE‐weighted strategy further lowers MAE by ∼15% to ∼40%. Our primary dose calculation also showed highly consistent results between the original and synthetic CT.Conclusion:We've developed a novel image‐analysis technique to synthesize CT for H&N and pelvis anatomies. Our proposed image fusion strategy and GRE metric help generate more accurate synthetic CT using locally more similar atlases (Support: Philips Healthcare).The research is supported by Philips HealthCare