Intrafractional Voxel-wise Anatomic Motion Tracking Guided by Multimodal Respiratory Surrogates in Radiotherapy: Framework Development and Multicenter Validation.

PURPOSE: Intrafractional respiratory motion management encounters trade-offs between target coverage, organ at risk (OAR) sparing, and treatment efficacy. Real-time tracking is promising but hindered by invasiveness risks, lack of global deformations, or inadaptability to irregular respiration. Currently respiratory modeling-based adaptive tracking may offer ideal solutions, but is limited by discrete clinical priors, highly-sparse observations, and complex motion variability. This study advances the constrained modeling toward a synergistic knowledge- and information-augmentation-driven paradigm, thereby bridging sparse real-time observations with voxel-wise anatomic deformations.

METHODS AND MATERIALS: Four multicenter cohorts were enrolled comprising 35 cases (10 prospective and 25 retrospective), including 7 patients undergoing reirradiation. Knowledge- and information-augmentation-driven paradigm was instantiated as MorphTracking, a patient-specific respiratory modeling framework that synergistically leveraged prior clinical materials and external-and-internal surrogates-optical surface images and single-view x-ray projections-to estimate 3-dimensional deformation vector fields. MorphTracking incorporated a comprehensive data-augmentation pipeline to enhance phase diversity with irregular variability. To enforce physical-consistency and anatomic plausibility, we performed optimization spanning deformation, image, and surrogate domains. MorphTracking was compared with 3 state-of-the-art methods and further validated through full-cycle evaluations, ablation studies, and simulated 4-dimensional treatment scenarios.

RESULTS

Across thoracic (n = 24) and abdominal (n = 11) cohorts, MorphTracking significantly outperformed state-of-the-art methods in computed tomography reconstruction and tracking of gross tumor volume (GTV) and OARs. It exhibited high consistency with ground-truths spanning full-cycle phases, operating at an average inference time of 15.622 ± 0.001 ms/frame. Comprehensive ablation studies substantiated the individual and synergistic contributions of data-augmentation, multimodal configuration, and cross-domain optimization. In simulated treatment scenarios, compared with the standard internal GTV approach, MorphTracking-driven 4-dimensional delivery effectively maintained GTV's dosimetric indices while enhancing OAR (spinal cord and lungs) sparing.

CONCLUSIONS

MorphTracking provides an innovative solution for intrafractional respiratory modeling, potentially enhancing voxel-wise geometric confidence for motion-aware highly-conformal dose delivery with real-time, robust, and adaptive anatomic tracking.