Deep Learning model for markerless tracking in spinal SBRT

Abstract

Stereotactic Body Radiation Therapy (SBRT), alternatively termed Stereotactic ABlative Radiotherapy (SABR) or Stereotactic RadioSurgery (SRS), delivers high dose with a sub-millimeter accuracy. It requires meticulous precautions on positioning, as sharp dose gradients near critical neighboring structures (e.g. the spinal cord for spinal tumor treatment) are an important clinical objective to avoid complications such as radiation myelopathy, compression fractures, or radiculopathy. To allow for dose escalation within the target without compromising the dose to critical structures, proper immobilization needs to be combined with (internal) motion monitoring. Metallic fiducials, as applied in prostate, liver or pancreas treatments, are not suitable in clinical practice for spine SBRT. However, the latest advances in Deep Learning (DL) allow for fast localization of the vertebrae as landmarks. Acquiring projection images during treatment delivery allows for instant 2D position verification as well as sequential (delayed) 3D position verification when incorporated in a Digital TomoSynthesis (DTS) or Cone Beam Computed Tomography (CBCT). Upgrading to an instant 3D position verification system could be envisioned with a stereoscopic kilovoltage (kV) imaging setup. This paper describes a fast DL landmark detection model for vertebra (trained in-house) and evaluates its accuracy to detect 2D motion of the vertebrae with the help of projection images acquired during treatment. The introduced motion consists of both translational and rotational variations, which are detected by the DL model with a sub-millimeter accuracy.

Keywords: Artificial intelligence; Deep Learning; Marker-less tracking; Motion monitoring; Real-time image analysis; Stereotactic body radiotherapy; Stereotactic radiosurgery.