Related Experiment Video
Updated: Jun 6, 2026
10:25
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
Published on: September 2, 2025
Targeting accuracy in real-time tumor tracking via external surrogates: a comparative study.
A E Torshabi1, Andrea Pella, Marco Riboldi
1Biongineering Unit, Centro Nazionale di Adroterapia Oncologica, Strada privata Campeggi snc, 27100 Pavia, Italy. Torshabi@cnao.it
Technology in Cancer Research & Treatment
|November 13, 2010
Summary
Accurate tumor motion prediction for extra-cranial radiation therapy is challenging. Fuzzy logic models improved real-time tumor tracking accuracy by reducing errors compared to CyberKnife Synchrony.
Area of Science:
- Medical Physics
- Radiotherapy Technology
- Computational Biology
Background:
- Real-time tumor tracking in radiotherapy, particularly for extra-cranial sites using systems like CyberKnife Synchrony, relies on predicting tumor motion from external surrogates.
- Accurate correlation models are crucial for predicting tumor motion over extended periods, spanning multiple breathing cycles, which remains a significant challenge.
Purpose of the Study:
- To compare the accuracy of three distinct correlation models—linear/quadratic, artificial neural networks, and fuzzy logic—for inferring tumor motion from external surrogates.
- To evaluate these models in the context of real-time tumor tracking over long durations, addressing a gap in comparative studies.
Main Methods:
- Twenty patient cases undergoing real-time tumor tracking with CyberKnife Synchrony were analyzed.
- Three correlation models (linear/quadratic, artificial neural networks, fuzzy logic) were implemented to predict tumor motion based on external surrogate data.
- Model accuracy was assessed using ground truth tumor position data obtained from stereoscopic X-ray imaging during treatment.
Main Results:
- All implemented models demonstrated an error reduction compared to the standard CyberKnife Synchrony system.
- The fuzzy logic approach achieved the most significant error reduction, up to 10.8% at the 95% confidence level.
- Fuzzy logic models showed a notable improvement in reducing the incidence of tumor tracking errors exceeding 6 mm, enhancing accuracy for larger motion discrepancies.
Conclusions:
- Complex models, such as fuzzy logic, are recommended for predicting tumor motion over extended time periods in real-time tumor tracking.
- These advanced models offer effective improvements in accuracy compared to the CyberKnife Synchrony system.
- Future research should focus on the sensitivity of these models to input data variations to optimize prediction strategies.
