Technical Note: Dose prediction for radiation therapy using feature‐based losses and One Cycle Learning

Zimmermann, Lukas; Faustmann, Erik; Ramsl, Christian; Georg, Dietmar; Heilemann, Gerd

doi:10.1002/mp.14774

Cited by 26 publications

(27 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rough comparison results showed that the proposed model performance (MAE = 2.43 Gy) was competitive to that proposed by Liu et al 38 (MAE = 2.31 Gy) using Cascade 3D U-Net, which achieved the first place in the OpenKBP competition. Moreover, it was superior to the second-ranked method proposed by Gronberg et al 37 (MAE = 2.56 Gy) using 3D dense dilated U-Net, and the third-ranked method proposed by Zimmermann et al 41 (MAE = 2.62 Gy) using GAN. Also, a rough comparison was made to other dose prediction methods in the literature where the assessment process is typically similar to what we used in this study with the MAE calculated over all voxels within the body contour.…”

Section: Discussionmentioning

confidence: 70%

“…Moreover, it was superior to the second‐ranked method proposed by Gronberg et al 37 . (MAE = 2.56 Gy) using 3D dense dilated U‐Net, and the third‐ranked method proposed by Zimmermann et al 41 . (MAE = 2.62 Gy) using GAN.…”

Section: Discussionmentioning

confidence: 75%

“…31,32 Several studies assessed various deep learning convolutional network architectures for predicting IMRT/VMAT dose distributions in head-and-neck cancer given the patient's anatomical information (CT scan only or/and contour structures). These methods include residual network, 33,34 hierarchically densely connected U-Net, 35,36 dilated convolutional based U-Net, 37 cascade U-Net, 38 residual U-Net (Res U-Net), 39 generative adversarial networks (GANs), 22,40,41 and conditional GAN. 42 The reported results by those models were promising; however, there is still a need for investigating other methods for better prediction accuracy and generalizability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Attention‐aware 3D U‐Net convolutional neural network for knowledge‐based planning 3D dose distribution prediction of head‐and‐neck cancer

Osman

2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose Deep learning–based knowledge‐based planning (KBP) methods have been introduced for radiotherapy dose distribution prediction to reduce the planning time and maintain consistent high‐quality plans. This paper presents a novel KBP model using an attention‐gating mechanism and a three‐dimensional (3D) U‐Net for intensity‐modulated radiation therapy (IMRT) 3D dose distribution prediction in head‐and‐neck cancer. Methods A total of 340 head‐and‐neck cancer plans, representing the OpenKBP—2020 AAPM Grand Challenge data set, were used in this study. All patients were treated with the IMRT technique and a dose prescription of 70 Gy. The data set was randomly divided into 64%/16%/20% as training/validation/testing cohorts. An attention‐gated 3D U‐Net architecture model was developed to predict full 3D dose distribution. The developed model was trained using the mean‐squared error loss function, Adam optimization algorithm, a learning rate of 0.001, 120 epochs, and batch size of 4. In addition, a baseline U‐Net model was also similarly trained for comparison. The model performance was evaluated on the testing data set by comparing the generated dose distributions against the ground‐truth dose distributions using dose statistics and clinical dosimetric indices. Its performance was also compared to the baseline model and the reported results of other deep learning‐based dose prediction models. Results The proposed attention‐gated 3D U‐Net model showed high capability in accurately predicting 3D dose distributions that closely replicated the ground‐truth dose distributions of 68 plans in the test set. The average value of the mean absolute dose error was 2.972 ± 1.220 Gy (vs. 2.920 ± 1.476 Gy for a baseline U‐Net) in the brainstem, 4.243 ± 1.791 Gy (vs. 4.530 ± 2.295 Gy for a baseline U‐Net) in the left parotid, 4.622 ± 1.975 Gy (vs. 4.223 ± 1.816 Gy for a baseline U‐Net) in the right parotid, 3.346 ± 1.198 Gy (vs. 2.958 ± 0.888 Gy for a baseline U‐Net) in the spinal cord, 6.582 ± 3.748 Gy (vs. 5.114 ± 2.098 Gy for a baseline U‐Net) in the esophagus, 4.756 ± 1.560 Gy (vs. 4.992 ± 2.030 Gy for a baseline U‐Net) in the mandible, 4.501 ± 1.784 Gy (vs. 4.925 ± 2.347 Gy for a baseline U‐Net) in the larynx, 2.494 ± 0.953 Gy (vs. 2.648 ± 1.247 Gy for a baseline U‐Net) in the PTV_70, and 2.432 ± 2.272 Gy (vs. 2.811 ± 2.896 Gy for a baseline U‐Net) in the body contour. The average difference in predicting the D99 value for the targets (PTV_70, PTV_63, and PTV_56) was 2.50 ± 1.77 Gy. For the organs at risk, the average difference in predicting the Dmax${D_{max}}$ (brainstem, spinal cord, and mandible) and Dmean${D_{mean}}$ (left parotid, right parotid, esophagus, and larynx) values was 1.43 ± 1.01 and 2.44 ± 1.73 Gy, respectively. The average value of the homogeneity index was 7.99 ± 1.45 for the predicted plans versus 5.74 ± 2.95 for the ground‐truth plans, whereas the average value of the conformity index was 0.63 ± 0.17 for the predicted plans versus 0.89 ± 0.19 for the ground‐truth plans. The proposed model needs ...

show abstract

Section: Discussionmentioning

confidence: 70%

Section: Discussionmentioning

confidence: 75%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attention‐aware 3D U‐Net convolutional neural network for knowledge‐based planning 3D dose distribution prediction of head‐and‐neck cancer

Osman

2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

show abstract

“…Every dose prediction model used a neural network architecture that was based on either a U-Net [23], V-Net [24], or Pix2Pix [25] architecture. Many of the best performing models also used other generalizable techniques like ensembles [26], one-cycle learning [27], radiotherapy-specific loss functions [28], and deep supervision [29].…”

Section: B Developing Dose Prediction Modelsmentioning

confidence: 99%

OpenKBP-Opt: An international and reproducible evaluation of 76 knowledge-based planning pipelines

Babier,

Mahmood,

Zhang

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We establish an open framework for developing plan optimization models for knowledge-based planning (KBP) in radiotherapy. Our framework includes reference plans for 100 patients with head-and-neck cancer and high-quality dose predictions from 19 KBP models that were developed by different research groups during the OpenKBP Grand Challenge. The dose predictions were input to four optimization models to form 76 unique KBP pipelines that generated 7600 plans. The predictions and plans were compared to the reference plans via: dose score, which is the average mean absolute voxel-by-voxel difference in dose a model achieved; the deviation in dosevolume histogram (DVH) criterion; and the frequency of clinical planning criteria satisfaction. We also performed a theoretical investigation to justify our dose mimicking models. The range in rank order correlation of the dose score between predictions and their KBP pipelines was 0.50 to 0.62, which indicates that the quality of the predictions is generally positively correlated with the quality of the plans. Additionally, compared to the input predictions, the KBPgenerated plans performed significantly better (P <0.05; one-sided Wilcoxon test) on 18 of 23 DVH criteria. Similarly, each optimization model generated plans that satisfied a higher percentage of criteria than the reference plans. Lastly, our theoretical investigation demonstrated that the dose mimicking models generated plans that are also optimal for a conventional planning model. This was the largest international effort to date for evaluating the combination of KBP prediction and optimization models. In the interest of reproducibility, our data and code is freely available at https://github.com/ababier/open-kbp-opt.

show abstract

“…The DL-based methods perform well in automatic feature extraction and mapping transformation (5,8). The dose prediction model can make an end-to-end mapping transformation between patients' anatomical and dose distribution information with organs-atrisk (OARs) constraints (9)(10)(11)(12). Compared with using the conventional treatment planning system (TPS), using the DL model to generate predicted dose distribution reduces planning time significantly (13)(14)(15)(16).…”

Section: Introductionmentioning

confidence: 99%

Dose Prediction Using a Three-Dimensional Convolutional Neural Network for Nasopharyngeal Carcinoma With Tomotherapy

Liu

Chen²,

Wang

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

PurposeThis 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).MethodsA 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 ×128 ×48 (for Model I), 128 ×128 ×16 (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.ResultsWe 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 PTV60 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 D95 for PTV60 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.ConclusionsIt 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.

show abstract

Technical Note: Dose prediction for radiation therapy using feature‐based losses and One Cycle Learning

Cited by 26 publications

References 23 publications

Attention‐aware 3D U‐Net convolutional neural network for knowledge‐based planning 3D dose distribution prediction of head‐and‐neck cancer

Attention‐aware 3D U‐Net convolutional neural network for knowledge‐based planning 3D dose distribution prediction of head‐and‐neck cancer

OpenKBP-Opt: An international and reproducible evaluation of 76 knowledge-based planning pipelines

Dose Prediction Using a Three-Dimensional Convolutional Neural Network for Nasopharyngeal Carcinoma With Tomotherapy

Contact Info

Product

Resources

About