Deep learning-based quick MLC sequencing for MRI-guided online adaptive radiotherapy: a feasibility study for pancreatic cancer patients. Phys Med Biol 2025 Feb 12;70(4)
Date
01/31/2025Pubmed ID
39883962Pubmed Central ID
PMC13361090DOI
10.1088/1361-6560/adb099Scopus ID
2-s2.0-85218491143 (requires institutional sign-in at Scopus site) 1 CitationAbstract
Objective.One bottleneck of magnetic resonance imaging (MRI)-guided online adaptive radiotherapy is the time-consuming daily online replanning process. The current leaf sequencing method takes up to 10 min, with potential dosimetric degradation and small segment openings that increase delivery time. This work aims to replace this process with a fast deep learning-based method to provide deliverable MLC sequences almost instantaneously, potentially accelerating and enhancing online adaption.Approach.Daily MRIs and plans from 242 daily fractions of 49 abdomen cancer patients on a 1.5 T MR-Linac were used. The architecture included: (1) a recurrent conditional generative adversarial network model to predict segment shapes from a fluence map (FM), recurrently predicting each segment's shape; and (2) a linear matrix equation module to optimize the monitor units (MUs) weights of segments. Multiple models with different segment numbers per beam (4-7) were trained. The final MLC sequences with the smallest relative absolute errors were selected. The predicted MLC sequence was imported into treatment planning system for dose calculation and compared with the original plans.Main results.The gamma passing rate for all fractions was 99.7 ± 0.2% (2%/2 mm criteria) and 92.7 ± 1.6% (1%/1 mm criteria). The average number of segments per beam in the proposed method was 6.0 ± 0.6 compared to 7.5 ± 0.3 in the original plan. The average total MUs were reduced from 1641 ± 262 to 1569.5 ± 236.7 in the predicted plans. The estimated delivery time was reduced from 9.7 min to 8.3 min, an average reduction of 14% and up to 25% for individual plans. Execution time for one plan was less than 10 s using a GTX1660TIGPU.Significance.The developed models can quickly and accurately generate an optimized, deliverable leaf sequence from a FM with fewer segments. This can seamlessly integrate into the current online replanning workflow, greatly expediting the daily plan adaptation process.
Author List
Ahunbay A, Paulson E, Ahunbay E, Zhang YAuthors
Ergun Ahunbay PhD, MS Professor in the Radiation Oncology department at Medical College of WisconsinEric Paulson PhD Chief, Professor in the Radiation Oncology department at Medical College of Wisconsin
MESH terms used to index this publication - Major topics in bold
Feasibility StudiesHumans
Magnetic Resonance Imaging
Pancreatic Neoplasms
Radiotherapy Dosage
Radiotherapy Planning, Computer-Assisted
Radiotherapy, Image-Guided
