PMID- 30870586 OWN - NLM STAT- MEDLINE DCOM- 20190912 LR - 20190912 IS - 2473-4209 (Electronic) IS - 0094-2405 (Linking) VI - 46 IP - 5 DP - 2019 May TI - A deep learning method for prediction of three-dimensional dose distribution of helical tomotherapy. PG - 1972-1983 LID - 10.1002/mp.13490 [doi] AB - PURPOSE: To develop a deep learning method for prediction of three-dimensional (3D) voxel-by-voxel dose distributions of helical tomotherapy (HT). METHODS: Using previously treated HT plans as training data, a deep learning model named U-ResNet-D was trained to predict a 3D dose distribution. First, the contoured structures and dose volumes were converted from plan database to 3D matrix with a program based on a developed visualization toolkit (VTK), then transferred to U-ResNet-D for correlating anatomical features and dose distributions at voxel-level. One hundred and ninety nasopharyngeal cancer (NPC) patients treated by HT with multiple planning target volumes (PTVs) in different prescription patterns were studied. The model was typically trained from scratch with weights randomly initialized rather than using transfer-learning method, and used to predict new patient's 3D dose distributions. The predictive accuracy was evaluated with three methods: (a) The dose difference at the position r, delta(r, r) = D(c) (r) - D(p) (r), was calculated for each voxel. The mean (mu(delta(r,r)) ) and standard deviation (sigma(delta(r,r)) ) of delta(r, r) were calculated to assess the prediction bias and precision; (b) The mean absolute differences of dosimetric indexes (DIs) including maximum and mean dose, homogeneity index, conformity index, and dose spillage for PTVs and organ at risks (OARs) were calculated and statistically analyzed with the paired-samples t test; (c) Dice similarity coefficients (DSC) between predicted and clinical isodose volumes were calculated. RESULTS: The U-ResNet-D model predicted 3D dose distribution accurately. For twenty tested patients, the prediction bias ranged from -2.0% to 2.3% and prediction error varied from 1.5% to 4.5% (relative to prescription) for 3D dose differences. The mean absolute dose differences for PTVs and OARs are within 2.0% and 4.2%, and nearly all the DIs for PTVs and OARs had no significant differences. The averaged DSC ranged from 0.95 to 1 for different isodose volumes. CONCLUSIONS: The study developed a new deep learning method for 3D voxel-by-voxel dose prediction, and shown to be able to produce accurately dose predictions for nasopharyngeal patients treated by HT. The predicted 3D dose map can be useful for improving radiotherapy planning design, ensuring plan quality and consistency, making clinical technique comparison, and guiding automatic treatment planning. CI - (c) 2019 American Association of Physicists in Medicine. FAU - Liu, Zhiqiang AU - Liu Z AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. FAU - Fan, Jiawei AU - Fan J AD - Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China. AD - Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, China. FAU - Li, Minghui AU - Li M AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. FAU - Yan, Hui AU - Yan H AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. FAU - Hu, Zhihui AU - Hu Z AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. FAU - Huang, Peng AU - Huang P AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. FAU - Tian, Yuan AU - Tian Y AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. FAU - Miao, Junjie AU - Miao J AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. FAU - Dai, Jianrong AU - Dai J AD - National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli, Chaoyang District, Beijing, 100021, China. LA - eng GR - LC2018B07/Beijing Hope Run Special Fund of Cancer Foundation of China/ GR - 11875320/National Natural Science Foundation of China/ GR - 11805039/National Natural Science Foundation of China/ GR - 2016YFC0904600/National Key Projects of Research and Development of China/ PT - Journal Article DEP - 20190330 PL - United States TA - Med Phys JT - Medical physics JID - 0425746 SB - IM MH - *Deep Learning MH - Humans MH - Image Processing, Computer-Assisted/methods MH - Nasopharyngeal Neoplasms/diagnostic imaging/*radiotherapy MH - Organs at Risk/radiation effects MH - Radiotherapy Dosage MH - Radiotherapy Planning, Computer-Assisted/*methods MH - Radiotherapy, Intensity-Modulated/methods MH - Tomography, X-Ray Computed/methods OTO - NOTNLM OT - 3D dose prediction OT - deep learning OT - helical tomotherapy OT - nasopharyngeal cancers EDAT- 2019/03/15 06:00 MHDA- 2019/09/13 06:00 CRDT- 2019/03/15 06:00 PHST- 2018/11/29 00:00 [received] PHST- 2019/02/14 00:00 [revised] PHST- 2019/03/04 00:00 [accepted] PHST- 2019/03/15 06:00 [pubmed] PHST- 2019/09/13 06:00 [medline] PHST- 2019/03/15 06:00 [entrez] AID - 10.1002/mp.13490 [doi] PST - ppublish SO - Med Phys. 2019 May;46(5):1972-1983. doi: 10.1002/mp.13490. Epub 2019 Mar 30.