Room: Davidson Ballroom A
Purpose: To implement an autonomous planning strategy in a commercial treatment planning platform via API tools and effective use of a novel downsampling voxelation scheme and showcase the highly efficient and robust auto-planning approach by several clinical cases of different disease sites.
Methods: A sparse voxelization scheme, referred to as isodose-feature preserving voxelization (IFPV), introduced recently by our group for concise representation of a treatment plan, is used to represent prior knowledge and to facilitate the optimization. Briefly, anatomical and dosimetric information of a treatment plan is characterized by IFPV, which partitions the voxels into subgroups according to their geometric, anatomical and dosimetric features. For a given patient, the IFPV clusters are generated based on prior treatment reference plans with similar anatomy. A plan is then generated using a commercial TPS with its planning parameters initialized with the features of the clusters. API script programming is employed to interact with the TPS to implement autonomous plan evaluation and automated optimization parameter update. Clinical cases with different sites are tested to demonstrate the proposed approach.
Results: Compared with the organ DVH-based approach, it is found that the optimization with IFPV voxelization is easier to be guided toward the desired solution. This especially favors our autonomous planning approach and makes autonomous optimization more efficient. In addition, because of more effective use of both geometric and dose information during plan optimization, the IFPV voxelization-based inverse planning typically yields better treatment plans.
Conclusion: This work presents the first implementation of autonomous VMAT/IMRT planning in the IFPV voxelization scheme and in a realistic clinical TPS platform. The algorithm developed requires little human intervention and is capable of providing clinical grade treatment plans. The research is directly translatable to widespread clinical use and has the potential to significantly improve the radiation therapy workflow and patient care.
Funding Support, Disclosures, and Conflict of Interest: This work is supported by a grant from Varian Medical System
Optimization, Inverse Planning, Intensity Modulation
TH- External beam- photons: VMAT dose optimization algorithms