Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks.

Abstract

Objective: Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T₂ in the prostate.

Materials and methods: Large physics-based synthetic datasets simulating T₂ mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.

Results: In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T₂ maps and showed the least deterioration with increasing input noise levels.

Discussion: This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T₂ estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.