Intrafractional Voxel-wise Anatomic Motion Tracking Guided by Multimodal Respiratory Surrogates in Radiotherapy:...

Area of Science:

• Medical Physics
• Radiotherapy
• Image-guided therapy

Background:

• Respiratory motion introduces challenges in radiotherapy, impacting target coverage and organ sparing.
• Current real-time tracking methods face limitations like invasiveness and inability to handle irregular breathing patterns.
• Existing respiratory modeling approaches are constrained by limited data and complex motion variability.

Purpose of the Study:

• To develop a knowledge- and information-augmentation-driven paradigm (KIADP) for improved intra-fractional respiratory motion management.
• To bridge sparse real-time observations with voxel-wise anatomical deformations for adaptive radiotherapy.
• To enhance the accuracy and robustness of respiratory motion tracking in radiation oncology.

Main Methods:

• Developed MorphTracking, a patient-specific respiratory modeling framework using KIADP.
• Integrated optical surface images (OSIs) and single-view X-ray projections as surrogates.
• Employed a data augmentation pipeline for irregular respiratory variability and cross-domain optimization for physical consistency.

Main Results:

• MorphTracking significantly outperformed state-of-the-art methods in CT reconstruction and tracking of gross tumor volume (GTV) and organs at risk (OARs).
• Achieved high consistency with ground-truths and operated at a rapid inference time of 15.622±0.001 ms/frame.
• Demonstrated improved GTV dosimetric indices and enhanced OAR sparing in simulated 4D treatment scenarios compared to the standard IGTV approach.

Conclusions:

• MorphTracking offers an innovative solution for intra-fractional respiratory modeling in radiotherapy.
• It enhances voxel-wise geometric confidence for motion-aware, highly-conformal dose delivery.
• Provides real-time, robust, and adaptive anatomical tracking for improved treatment outcomes.