Real-time, acquisition parameter-free voxel-wise patient-specific Monte Carlo dose reconstruction in whole-body CT scanning using deep neural networks

ObjectiveWe propose a deep learning-guided approach to generate voxel-based absorbed dose maps from whole-body CT acquisitions.MethodsThe voxel-wise dose maps corresponding to each source position/angle were calculated using Monte Carlo (MC) simulations considering patient- and scanner-specific characteristics (SP_MC). The dose distribution in a uniform cylinder was computed through MC calculations (SP_uniform). The density map and SP_uniform dose maps were fed into a residual deep neural network (DNN) to predict SP_MC through an image regression task. The whole-body dose maps reconstructed by the DNN and MC were compared in the 11 test cases scanned with two tube voltages through transfer learning with/without tube current modulation (TCM). The voxel-wise and organ-wise dose evaluations, such as mean error (ME, mGy), mean absolute error (MAE, mGy), relative error (RE, %), and relative absolute error (RAE, %), were performed.ResultsThe model performance for the 120 kVp and TCM test set in terms of ME, MAE, RE, and RAE voxel-wise parameters was - 0.0302 & PLUSMN; 0.0244 mGy, 0.0854 & PLUSMN; 0.0279 mGy, - 1.13 & PLUSMN; 1.41%, and 7.17 & PLUSMN; 0.44%, respectively. The organ-wise errors for 120 kVp and TCM scenario averaged over all segmented organs in terms of ME, MAE, RE, and RAE were - 0.144 & PLUSMN; 0.342 mGy, and 0.23 & PLUSMN; 0.28 mGy, - 1.11 & PLUSMN; 2.90%, 2.34 & PLUSMN; 2.03%, respectively.ConclusionOur proposed deep learning model is able to generate voxel-level dose maps from a whole-body CT scan with reasonable accuracy suitable for organ-level absorbed dose estimation.

Automated summary

We propose a deep learning-guided approach to generate voxel-based absorbed dose maps from whole-body CT acquisitions. Monte Carlo simulations (SP_MC) were used to calculate voxel-wise dose maps considering patient- and scanner-specific characteristics. A residual deep neural network (DNN) was trained to predict SP_MC using density map and SP_uniform dose maps. The performance of the DNN was evaluated for voxel-wise and organ-wise dose estimations using various error parameters.