PMID- 34858825
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220428
IS  - 2234-943X (Print)
IS  - 2234-943X (Electronic)
IS  - 2234-943X (Linking)
VI  - 11
DP  - 2021
TI  - Dose Prediction Using a Three-Dimensional Convolutional Neural Network for 
      Nasopharyngeal Carcinoma With Tomotherapy.
PG  - 752007
LID - 10.3389/fonc.2021.752007 [doi]
LID - 752007
AB  - PURPOSE: This study focused on predicting 3D dose distribution at high precision 
      and generated the prediction methods for nasopharyngeal carcinoma patients (NPC) 
      treated with Tomotherapy based on the patient-specific gap between organs at risk 
      (OARs) and planning target volumes (PTVs). METHODS: A convolutional neural 
      network (CNN) is trained using the CT and contour masks as the input and dose 
      distributions as output. The CNN is based on the "3D Dense-U-Net", which combines 
      the U-Net and the Dense-Net. To evaluate the model, we retrospectively used 124 
      NPC patients treated with Tomotherapy, in which 96 and 28 patients were randomly 
      split and used for model training and test, respectively. We performed comparison 
      studies using different training matrix shapes and dimensions for the CNN models, 
      i.e., 128 x128 x48 (for Model I), 128 x128 x16 (for Model II), and 2D Dense U-Net 
      (for Model III). The performance of these models was quantitatively evaluated 
      using clinically relevant metrics and statistical analysis. RESULTS: We found a 
      more considerable height of the training patch size yields a better model 
      outcome. The study calculated the corresponding errors by comparing the predicted 
      dose with the ground truth. The mean deviations from the mean and maximum doses 
      of PTVs and OARs were 2.42 and 2.93%. Error for the maximum dose of right optic 
      nerves in Model I was 4.87 +/- 6.88%, compared with 7.9 +/- 6.8% in Model II (p=0.08) 
      and 13.85 +/- 10.97% in Model III (p<0.01); the Model I performed the best. The 
      gamma passing rates of PTV(60) for 3%/3 mm criteria was 83.6 +/- 5.2% in Model I, 
      compared with 75.9 +/- 5.5% in Model II (p<0.001) and 77.2 +/- 7.3% in Model III 
      (p<0.01); the Model I also gave the best outcome. The prediction error of D(95) 
      for PTV(60) was 0.64 +/- 0.68% in Model I, compared with 2.04 +/- 1.38% in Model II 
      (p<0.01) and 1.05 +/- 0.96% in Model III (p=0.01); the Model I was also the best 
      one. CONCLUSIONS: It is significant to train the dose prediction model by 
      exploiting deep-learning techniques with various clinical logic concepts. 
      Increasing the height (Y direction) of training patch size can improve the dose 
      prediction accuracy of tiny OARs and the whole body. Our dose prediction network 
      model provides a clinically acceptable result and a training strategy for a dose 
      prediction model. It should be helpful to build automatic Tomotherapy planning.
CI  - Copyright (c) 2021 Liu, Chen, Wang, Wang, Qu, Ma, Zhao, Zhang and Xu.
FAU - Liu, Yaoying
AU  - Liu Y
AD  - Department of Radiation Oncology, the First Medical Center of the People's 
      Liberation Army General Hospital, Beijing, China.
AD  - School of Physics, Beihang University, Beijing, China.
FAU - Chen, Zhaocai
AU  - Chen Z
AD  - Manteia Technologies Co., Ltd, Xiamen, China.
FAU - Wang, Jinyuan
AU  - Wang J
AD  - Department of Radiation Oncology, the First Medical Center of the People's 
      Liberation Army General Hospital, Beijing, China.
FAU - Wang, Xiaoshen
AU  - Wang X
AD  - Department of Radiation Oncology, the First Medical Center of the People's 
      Liberation Army General Hospital, Beijing, China.
FAU - Qu, Baolin
AU  - Qu B
AD  - Department of Radiation Oncology, the First Medical Center of the People's 
      Liberation Army General Hospital, Beijing, China.
FAU - Ma, Lin
AU  - Ma L
AD  - Department of Radiation Oncology, the First Medical Center of the People's 
      Liberation Army General Hospital, Beijing, China.
FAU - Zhao, Wei
AU  - Zhao W
AD  - School of Physics, Beihang University, Beijing, China.
FAU - Zhang, Gaolong
AU  - Zhang G
AD  - School of Physics, Beihang University, Beijing, China.
FAU - Xu, Shouping
AU  - Xu S
AD  - Department of Radiation Oncology, the First Medical Center of the People's 
      Liberation Army General Hospital, Beijing, China.
LA  - eng
PT  - Journal Article
DEP - 20211111
PL  - Switzerland
TA  - Front Oncol
JT  - Frontiers in oncology
JID - 101568867
PMC - PMC8631763
OTO - NOTNLM
OT  - Tomotherapy
OT  - deep learning
OT  - dose prediction
OT  - nasopharyngeal carcinoma
OT  - radiotherapy plan
COIS- Manteia Technologies Co., Ltd employed author ZC. The remaining authors declare 
      that the research was conducted in the absence of any commercial or financial 
      relationships that could be construed as a potential conflict of interest.
EDAT- 2021/12/04 06:00
MHDA- 2021/12/04 06:01
PMCR- 2021/01/01
CRDT- 2021/12/03 07:07
PHST- 2021/08/02 00:00 [received]
PHST- 2021/10/21 00:00 [accepted]
PHST- 2021/12/03 07:07 [entrez]
PHST- 2021/12/04 06:00 [pubmed]
PHST- 2021/12/04 06:01 [medline]
PHST- 2021/01/01 00:00 [pmc-release]
AID - 10.3389/fonc.2021.752007 [doi]
PST - epublish
SO  - Front Oncol. 2021 Nov 11;11:752007. doi: 10.3389/fonc.2021.752007. eCollection 
      2021.