Sharp loss: a new loss function for radiotherapy dose prediction based on fully convolutional networks

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 a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biomedical engineering online 2021-10, Vol.20 (1), p.101-101, Article 101
Hauptverfasser: Bai, Xue, Zhang, Jie, Wang, Binbing, Wang, Shengye, Xiang, Yida, Hou, Qing
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 gamma was used to adjust the loss properties. The mean square error (MSE) loss and the sharp loss with different gamma 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 gamma 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 gamma = 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.
ISSN:1475-925X
1475-925X
DOI:10.1186/s12938-021-00937-w