Hybrid Algorithm for Optimizing Beam Weights in Radiotherapy
Author Information
Author(s): Vaitheeswaran Ranganathan, Sathiya Narayanan V. K., Bhangle Janhavi R., Nirhali Amit, Kumar Namita, Basu Sumit, Maiya Vikram
Primary Institution: Siemens Ltd., HealthCare Sector, Pune, India
Hypothesis
Integrating an exact optimization algorithm with a heuristic optimization algorithm will lead to a more efficient global optimizer for beam weight optimization in anatomy-based intensity modulated radiotherapy.
Conclusion
The hybrid algorithm significantly improves optimization speed and treatment plan quality in anatomy-based IMRT compared to traditional methods.
Supporting Evidence
- The hybrid algorithm's convergence speed is approximately three times higher than that of the fast simulated annealing algorithm.
- The hybrid algorithm shows about 20% improvement in convergence compared to the Gaussian elimination method.
- Treatment plans generated by the hybrid algorithm demonstrate better conformity and homogeneity indices compared to those generated by Gaussian elimination and fast simulated annealing.
- The hybrid algorithm produces smoother beam weights, which can lead to more efficient treatment delivery.
Takeaway
This study created a new way to quickly and effectively plan cancer treatments using a special computer program that combines two different methods.
Methodology
The study used a hybrid approach combining Gaussian elimination and fast simulated annealing algorithms to optimize beam weights for 8 patients in anatomy-based IMRT.
Limitations
The study does not address potential variations in patient anatomy or treatment response that could affect the generalizability of the results.
Participant Demographics
Patients included in the study had various cancer types, specifically prostate and brain cases.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website