Evaluating dose distribution in prostate IMRT patients using deep learning: the influence of loss function on model performance

Abstract

To estimate the influence of various loss functions on the performance of deep learning (DL) models for dose prediction in intensity-modulated radiotherapy (IMRT) for prostate cancer. A retrospective dataset comprising 110 prostate cancer patients was utilized. DL model was trained using various loss functions: mean absolute error (MAE), mean squared error (MSE), and combinations of MAE with predefined domain-specific knowledge, including dose-volume histogram (DVH) loss and moment loss function. The planned target volume (PTV) and dosimetric metrics for organs at risk (OARs) were used to assess the model's performance. A one-way analysis of variance (ANOVA) was applied to perform statistical comparisons between the clinical and predicted plans. In terms of dose deviations for OARs and PTV, the model trained with MAE plus moment loss performed better than models trained with MAE + DVH loss, MSE, or MAE. The MAE +/- standard deviation (SD) between clinical and predicted dose distributions in the test cohort were (1.76 +/- 0.5) Gy, (1.78 +/- 0.5) Gy, (1.93 +/- 0.6) Gy, and (2.02 +/- 0.4) Gy for MAE + moment, MAE + DVH, MSE, and MAE models, respectively. Compared to the ground truth plans, the accuracy of all predicted plans was clinically acceptable. This study highlights how important loss function choice is to the optimization of DL-based prostate IMRT dose prediction models. The performance of the model is greatly improved by incorporating domain-specific knowledge into the loss function, which supports the possible practical application of such models for more precise and personalized radiation planning.