Sharp loss: a new loss function for radiotherapy dose prediction based on fully convolutional networks
Open Access
- 9 October 2021
- journal article
- research article
- Published by Springer Nature in BioMedical Engineering OnLine
- Vol. 20 (1) , 1-15
Abstract
Background: Neural-network methods have been widely used for the prediction of dose distributions in radiotherapy. However, the prediction accuracy of existing methods may be degraded by the problem of dose imbalance. In this work, a new loss function is proposed to alleviate the dose imbalance and achieve more accurate prediction results. The U-Net architecture was employed to build a prediction model. Our study involved a total of 110 patients with left-breast cancer, who were previously treated by volumetric-modulated arc radiotherapy. The patient dataset was divided into training and test subsets of 100 and 10 cases, respectively. We proposed a novel ‘sharp loss’ function, and a parameter γ was used to adjust the loss properties. The mean square error (MSE) loss and the sharp loss with different γ values were tested and compared using the Wilcoxon signed-rank test. Results: The sharp loss achieved superior dose prediction results compared to those of the MSE loss. The best performance with the MSE loss and the sharp loss was obtained when the parameter γ was set to 100. Specifically, the mean absolute difference values for the planning target volume were 318.87 ± 30.23 for the MSE loss versus 144.15 ± 16.27 for the sharp loss with γ = 100 (p < 0.05). The corresponding values for the ipsilateral lung, the heart, the contralateral lung, and the spinal cord were 278.99 ± 51.68 versus 198.75 ± 61.38 (p < 0.05), 216.99 ± 44.13 versus 144.86 ± 43.98 (p < 0.05), 125.96 ± 66.76 versus 111.86 ± 47.19 (p > 0.05), and 194.30 ± 14.51 versus 168.58 ± 25.97 (p < 0.05), respectively. Conclusions: The sharp loss function could significantly improve the accuracy of radiotherapy dose prediction.Keywords
Funding Information
- National Natural Science Foundation of China (12005190)
- Zhejiang Province Public Welfare Technology Application Research Project (2018ZD014, LSY19H180002)
This publication has 31 references indexed in Scilit:
- Contextual Atlas Regression Forests: Multiple-Atlas-Based Automated Dose Prediction in Radiation TherapyIEEE Transactions on Medical Imaging, 2015
- A quality control model that uses PTV-rectal distances to predict the lowest achievable rectum dose, improves IMRT planning for patients with prostate cancerRadiotherapy and Oncology, 2013
- Predicting dose‐volume histograms for organs‐at‐risk in IMRT planningMedical Physics, 2012
- Increased organ sparing using shape-based treatment plan optimization for intensity modulated radiation therapy of pancreatic adenocarcinomaRadiotherapy and Oncology, 2012
- Experience-Based Quality Control of Clinical Intensity-Modulated Radiotherapy PlanningInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2011
- A planning quality evaluation tool for prostate adaptive IMRT based on machine learningMedical Physics, 2011
- Prostate and seminal vesicle volume based consideration of prostate cancer patients for treatment with 3D-conformal or intensity-modulated radiation therapya)Medical Physics, 2010
- Patient geometry‐driven information retrieval for IMRT treatment plan quality controlMedical Physics, 2009
- Geometric factors influencing dosimetric sparing of the parotid glands using IMRTInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2006
- Wilcoxon Signed‐Rank Test2005