Real-time target localization on 1.5 T magnetic resonance imaging linac orthogonal cine images using transfer learning.

BACKGROUND AND PURPOSE

Deep learning-based tumor tracking is promising for real-time magnetic-resonance-imaging (MRI)-guided radiotherapy. We investigate the applicability of a tumor tracking model developed for 0.35 T MRI-linac sagittal cine-MRI for 1.5 T interleaved orthogonal cine-MRI and implement transfer learning to further improve its performance.

MATERIALS AND METHODS

We collected 3600 cine-MRI frames in sagittal, coronal and axial planes from 24 patients (validation 10, testing 14) treated on a 1.5 T MRI-linac, where two expert clinicians manually segmented target labels. A transformer-based deformation model trained on 0.35T MRI-linac images (baseline model, BL) was evaluated and used as a starting point to train patient-specific (PS) models. The Dice similarity coefficient (DSC) and the surface distance (50th and 95th percentiles, SD50%, SD95%) were used to compare the obtained target segmentations with the ground truth labels. The percentage of negative Jacobian determinant values (NegJ), accounting for the folding pixel ratio, was determined.

RESULTS

Outperformed by all the PS models, the BL model averaged in a DSC of 0.85, SD50% of 1.9 mm, SD95% of 5.9 mm and NegJ of 0.45 % in testing. The best PS model averaged in a DSC of 0.90, SD50% of 1.3 mm, SD95% of 3.9 mm and NegJ of 0.02 % in testing.

CONCLUSION

We have found the 0.35 T model trained on sagittal cine-MRIs cannot be directly applied to a 1.5 T interleaved orthogonal cine-MRI system. However, PS transfer learning could improve the target tracking performance and reach an accuracy comparable to the inter-observer variability.