International journal of radiation oncology, biology, physics | 2021

Initial Plan Quality Evaluation Using a Novel AI-Driven Planning System and Paradigm for Adaptive Head and Neck Patients.



PURPOSE/OBJECTIVE(S)\nAn innovative ring gantry CBCT-guided adaptive radiotherapy system enables efficient planning and online adaptation to account for interfraction changes. Initial planning strategies and plan quality for head and neck (H&N) patients using the artificial intelligence (AI) plan optimizer for this system are evaluated.\n\n\nMATERIALS/METHODS\nNine previously treated H&N patients are used in this study. Planning target volumes (PTVs) have prescribed dose levels: PTVhigh\u202f=\u202f70.0/69.3/66.0, PTVmed\u202f=\u202f63.0/60, and PTVlow\u202f=\u202f56.0/54.1/54.0/52.8 Gy. Clinical planning CT and structures are used for AI plan generation with the novel paradigm based on clinical goal prioritization. The system automatically optimizes 5 candidates plans: 7/9/12 equidistant field IMRT and 2/3 full arc VMAT. Three planning approaches are tested: 1) input physician goals; 2) prioritize PTV coverage by excluding organ at risk (OAR) goals when OAR intersects PTVs; 3) generate and assign goals to OAR subvolumes cropped from PTVs. Utility of generalized helper structures for controlling hot spot location and low dose spillage is investigated. The best of each patient s 5 candidate AI plans (AcurosXB) is compared to clinical (collapsed cone) plan using NRG guidelines.\n\n\nRESULTS\nStrategies 1 and 2 consistently result in PTV under-coverage, high PTV hot spots, and failed OAR goals when intersecting PTVs. Strategy 3 provides acceptable PTV coverage and OAR dosimetry comparable to clinical plans. Helper structures (posterior block, distal OAR subvolumes, and PTVmed/low cropped from PTVhigh) were found to be necessary for shaping dose distributions similarly to clinical plans. Optimal plan type varied: 12 (n\u202f=\u202f5), 9 (n\u202f=\u202f2), 7 (n\u202f=\u202f1) field IMRT and 3 arc VMAT (n\u202f=\u202f1). Comparison of AI and clinical plans is based on using strategy (3) with helper structures. Compared to clinical plans, for all PTVs, average D99%, D95%, and Dmax are higher by 3.1% (103.6% vs. 100.5%), 1.3% (102.2 vs. 100.9%), and 3.3% (108.8% vs. 105.5%), respectively, but still within NRG guidelines. However, global hot spots may fall outside of PTVs and are higher by 5%. Hot spot differences may be from differences in dose calculation algorithms. The spinal cord, brainstem, parotid, oral cavity, mandible and thyroid doses are below NRG guidelines for both plans, with AI plan doses slightly lower. Larynx, Pharynx and submandibular doses on average are higher than the NRG guidelines due to PTV proximity for both plans, with AI plan doses slightly higher.\n\n\nCONCLUSION\nThe AI plan optimizer for this adaptive platform utilizes a novel planning paradigm based on clinical goals rather than direct optimization parameters and can efficiently generate H&N treatment plans. AI plans are comparable to clinical plans with slightly better PTV coverage and lower OAR doses. However, issues with higher and spatially undesirable calculated hot spots remain. All plans meet NRG guidelines.

Volume 111 3S
Pages \n e97\n
DOI 10.1016/j.ijrobp.2021.07.486
Language English
Journal International journal of radiation oncology, biology, physics

Full Text