We investigate the effects of training strategies, such as the dataset size, early stop and cross-validation, on the performance of deep neural network. We used the residual network architecture, dedicated to restore low-dose (LD) digital breast tomosynthesis (DBT) raw projections. For this assessment, we generated 500 synthetic breast phantoms through virtual clinical trials software (OpenVCT) and validated them in terms of noise and signal properties. We acquired real raw DBT projections using a physical anthropomorphic breast phantom and restored the LD projections after training the convolutional neural networks. We found that early stop can be applied in the training process depending on the denoising strength desired for the network. Also, different training realizations are necessary to achieve good results. Furthermore, the training sample size may be smaller compared to other computer vision tasks using deep learning algorithms.
|