MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Image Regression Motion Prediction for MRI-Guided Radiotherapy

J Ginn*, D Ruan , D Low , J Lamb , University of California, Los Angeles, Los Angeles, CA

Presentations

(Thursday, 7/18/2019) 10:00 AM - 12:00 PM

Room: 303

Purpose: Develop and evaluate an image regression (IR) motion prediction method to overcome gating latency and improve deformable registration based target tracking in magnetic resonance image (MRI) guided radiotherapy.

Methods: A novel IR motion prediction method was developed and evaluated using 26.9 hours of image data acquired from 8 healthy volunteers and 13 patients using a 0.35T MRI-guided radiotherapy system. Motion predictions were performed 0.25-0.33 seconds in the future using a weighted sum of previously observed motion states with image-similarity derived weights. The previously observed motion states were continuously updated to incorporate changes in breathing patterns. The accuracy of the predicted radiotherapy gating decision, the beam-on positive predictive value (PPV), and the predicted versus ground-truth target centroid position errors are reported. Additionally, the proposed technique was compared against no prediction, linear extrapolation, and an established autoregressive linear prediction algorithm. Use of IR to initialize deformable registration and enhance target tracking was demonstrated in the healthy volunteer studies. Deformable registration with IR initialization was compared to the registration using the initialization performed by current clinical software: no initialization, previous image registration initialization and linear motion extrapolation initialization.

Results: The average IR predicted radiation beam gating decision accuracy was 95.8%, with a PPV of 95.7%, and median and 95th percentile centroid position errors of 0.63 mm and 2.08 mm respectively. Compared to the autoregressive linear prediction method gating accuracy was 1.73% greater, PPV was 2.30% greater, and median and 95th percentile centroid distances were 0.31 mm and 0.35 mm smaller. The IR initialized registration on average converged within 0.5 mm of the ground-truth position in fewer than 10 iterations whereas the next best initialization method required more than 25 iterations.

Conclusion: IR motion prediction could be used to help overcome gating latencies and improve deformable registration based target tracking in MRI-guided radiotherapy.

Funding Support, Disclosures, and Conflict of Interest: This work was supported in part by a National Institutes of Health grant (2T32EB2101-41). James Lamb has previously received speaking and consulting fees from ViewRay.

Keywords

MRI, Radiation Therapy, Modeling

Taxonomy

IM/TH- MRI in Radiation Therapy: MRI/Linear accelerator combined- IGRT and tracking

Contact Email