PMID- 35043971 OWN - NLM STAT- MEDLINE DCOM- 20220310 LR - 20220311 IS - 2473-4209 (Electronic) IS - 0094-2405 (Linking) VI - 49 IP - 3 DP - 2022 Mar TI - A hybrid optimization strategy for deliverable intensity-modulated radiotherapy plan generation using deep learning-based dose prediction. PG - 1344-1356 LID - 10.1002/mp.15462 [doi] AB - PURPOSE: To propose a clinically feasible automatic planning solution for external beam intensity-modulated radiotherapy, including dose prediction via a deep learning and voxel-based optimization strategy. MATERIALS AND METHODS: The dose distribution of patients was predicted using a U-Net-based deep learning network based on the patient's anatomy information. One hundred seventeen patients with nasopharyngeal cancer (NPC) and 200 patients with rectal cancer were enrolled in this study. For NPC cases, 94 cases were included in the training dataset, 13 in the validation dataset, and 10 in the testing dataset. For rectal cancer cases, 172 cases were included in the training set, 18 in the validation set, and 10 in the testing set. A voxel-based optimization strategy, "Voxel," was proposed to achieve treatment planning optimization by dividing body voxels into two parts: inside planning target volumes (PTVs) and outside PTVs. Fixed dose-volume objectives were attached to the total objective function to realize individualized planning intended as the "hybrid" optimizing strategy. Automatically generated plans were compared with clinically approved plans to evaluate clinical gains, according to dosimetric indices and dose-volume histograms (DVHs). RESULTS: Similarities were found between the DVH of the predicted dose and clinical plan, although significant differences were found in some organs at risk. Better organ sparing and suboptimal PTV coverage were shown using the voxel strategy; however, the deviations in homogeneity indices (HIs) and conformity indices (CIs) of the PTV between automatically generated plans and manual plans were reduced by the hybrid strategy ([manual plans]/[voxel plans[/[hybrid plans]: HI of PTV70 [1.06/1.12/1.02] and CI of PTV70 [0.79/0.58/0.76]). The optimization time for each patient was within 1 min and included fluence map optimization, leaf sequencing, and control point optimization. All the generated plans (voxel and hybrid strategy) could be delivered on uRT-linac 506c (United Imaging Healthcare, Shanghai, China). CONCLUSION: Deliverable plans can be generated by incorporating a voxel-based optimization strategy into a commercial treatment planning system (TPS). The hybrid optimization method shows the benefit and clinical feasibility in generating clinically acceptable plans. CI - (c) 2022 American Association of Physicists in Medicine. FAU - Sun, Zihan AU - Sun Z AD - Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China. AD - Department of Oncology, Shanghai Medical College Fudan University, Shanghai, China. AD - Shanghai Key Laboratory of Radiation Oncology, Shanghai, China. FAU - Xia, Xiang AU - Xia X AD - Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China. AD - Department of Oncology, Shanghai Medical College Fudan University, Shanghai, China. AD - Shanghai Key Laboratory of Radiation Oncology, Shanghai, China. FAU - Fan, Jiawei AU - Fan J AD - Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China. AD - Department of Oncology, Shanghai Medical College Fudan University, Shanghai, China. AD - Shanghai Key Laboratory of Radiation Oncology, Shanghai, China. FAU - Zhao, Jun AU - Zhao J AD - Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China. AD - Department of Oncology, Shanghai Medical College Fudan University, Shanghai, China. AD - Shanghai Key Laboratory of Radiation Oncology, Shanghai, China. FAU - Zhang, Kang AU - Zhang K AD - United Imaging Healthcare, Shanghai, China. FAU - Wang, Jiazhou AU - Wang J AD - Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China. AD - Department of Oncology, Shanghai Medical College Fudan University, Shanghai, China. AD - Shanghai Key Laboratory of Radiation Oncology, Shanghai, China. FAU - Hu, Weigang AU - Hu W AD - Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China. AD - Department of Oncology, Shanghai Medical College Fudan University, Shanghai, China. AD - Shanghai Key Laboratory of Radiation Oncology, Shanghai, China. LA - eng GR - 11675042/National Natural Science Foundation of China/ GR - 11805039/National Natural Science Foundation of China/ GR - 11805038/National Natural Science Foundation of China/ GR - YX201703/Imaging Funding of Fudan University Shanghai Cancer Center/ GR - 19DZ1930902/Shanghai Committee of Science and Technology Fund/ PT - Journal Article DEP - 20220209 PL - United States TA - Med Phys JT - Medical physics JID - 0425746 SB - IM MH - China MH - *Deep Learning MH - Humans MH - *Nasopharyngeal Neoplasms MH - Organs at Risk MH - Radiotherapy Dosage MH - Radiotherapy Planning, Computer-Assisted/methods MH - *Radiotherapy, Intensity-Modulated/methods OTO - NOTNLM OT - IMRT autoplanning OT - NPC and rectal cancer OT - deep learning OT - hybrid objective function OT - voxel-based plan optimization EDAT- 2022/01/20 06:00 MHDA- 2022/03/11 06:00 CRDT- 2022/01/19 08:55 PHST- 2021/12/08 00:00 [revised] PHST- 2021/10/27 00:00 [received] PHST- 2021/12/22 00:00 [accepted] PHST- 2022/01/20 06:00 [pubmed] PHST- 2022/03/11 06:00 [medline] PHST- 2022/01/19 08:55 [entrez] AID - 10.1002/mp.15462 [doi] PST - ppublish SO - Med Phys. 2022 Mar;49(3):1344-1356. doi: 10.1002/mp.15462. Epub 2022 Feb 9.