Residual intra-fraction error in robotic spinal stereotactic body radiotherapy without immobilization devices

Background and purpose: Spinal stereotactic body radiotherapy (SBRT) involves large dose gradients and high geometrical accuracy is therefore required. The aim of this work was to assess residual intra-fraction error with a tracking robotic system for non-immobilized patients. Shifts from the first alignment (i.e. mimicking the unavailability of tracking) were also quantified. Materials and methods: Forty-two patients treated for spinal metastasis (128 fractions, 4220 images) were analyzed. Residual error was quantified as the difference between translations/rotations referring to consecutive x-ray images during delivery (tracking) and to the initial set-up (no-tracking). The error distribution for each fraction/patient and the entire population was assessed for each axis/rotation angle. The impact of lesion sites, fractionation and patient's pain (VAS score) were investigated. Finally, the dosimetric impact of residual motion was quantified in the four most affected fractions. Results: Mean overall errors (OE) were near 0 (SD < 0.1 mm). Residual translations/rotations >1 mm/1. were found in less than 1.5%/1% of measurements. Lesion site and fractionation showed no impact. The dosimetric impact in the most affected fractions was negligible. For "no-tracking", mean OE was <1 mm/0.5 degrees; less than 2% of displacements were >2 mm/1 degrees within 10 min from the start of treatment with an increasing probability of shifts >2 mm over time. A significantly higher fraction of OE >= 2 mm was found for patients with pain in case of no-tracking. Conclusions: Spine tracking with a latest-generation robotic system is highly efficient for non-immobilized patients: residual error is time independent and close to 0. For delivery times >7-8 min, tracking should be considered as mandatory for non-immobilized patients.