Orthogonal 2D MR Imaging and Manifold Learning Enables Real-Time 3D Tumor Tracking

<h3>Purpose/Objective(s)</h3> In magnetic resonance image (MRI)-guided radiotherapy (MRgRT), 2D- rapid imaging is commonly used to avoid unacceptable gating latency. However, anatomical motion is not constrained to 2D, and a portion of the target may be missed during treatment if 3D motion is not evaluated. While some MRgRT systems attempt to capture 3D motion by sequentially tracking motion in 2D orthogonal imaging planes, this approach assesses 3D motion via independent 2D measurements at alternating instances, lacking a simultaneous 3D motion assessment in both imaging planes. We hypothesized that a motion model could be derived from prior 2D orthogonal imaging to estimate 3D motion in both planes simultaneously. We present a manifold learning technique to estimate 3D motion from 2D orthogonal imaging. <h3>Materials/Methods</h3> Five healthy volunteers were scanned under an IRB approved protocol using a 3.0 T Skyra simulator from a technology company. Images of the liver dome were acquired during free breathing for approximately 10 min in alternating sagittal and coronal planes with a 2.6 mm x 2.6 mm in-plane resolution at ∼5 frames per second. The motion model was derived using a combined manifold learning and alignment approach based on locally linear embedding. The model utilized the spatially overlapping MRI signal shared by both imaging planes to group together images that had similar signals, enabling motion estimation in both planes simultaneously. The model's motion estimates were compared to the ground-truth motion derived in each newly acquired image using deformable registration. A simulated target was defined on the dome of the liver and used to evaluate model performance. The Dice similarity coefficient and distance between the model-tracked and image-tracked contour centroids were evaluated. <h3>Results</h3> The average Dice coefficient and centroid distance between the model-tracked and ground-truth target contours were 0.96 ± 0.03 and 0.25 mm ± 0.30 mm respectively across all volunteer studies. The results for individual volunteers including the motion range observed are reported in Table 1. <h3>Conclusion</h3> The healthy volunteer studies indicate promising results using the proposed motion modeling technique. On average, the model demonstrated sub-millimeter precision and > 0.95 Dice coefficient compared to the ground-truth motion observed in the images. More studies are required to further evaluate the model.