基于蒙特卡洛 dropout 的深度学习定量磁共振成像精度与不确定性量化提升方法
Improving accuracy and uncertainty quantification of deep learning based quantitative MRI using Monte Carlo dropout
AI总结：
针对深度学习定量 MRI 的精度与不确定性问题，提出训练和推理均使用 Monte Carlo dropout 并平均多次预测的方法，在小数据集下显著提升 FA、MD 图精度，还能生成辅助诊断的置信图。
摘要：
Dropout 传统上在训练阶段用作正则化方法，并用于量化深度学习中的不确定性。我们提出在训练和推理步骤中均使用 dropout，对多次预测结果取平均以提升精度，同时降低并量化不确定性。我们对仅通过 3 个方向扫描得到的各向异性分数（FA）和平均扩散率（MD）图进行了结果评估。与不使用 dropout 的网络输出相比，我们的方法可显著提升精度，尤其在训练数据集较小时效果更明显。此外，该方法还能生成置信图，可辅助诊断未见过的病理或伪影。
英文摘要：
Dropout is conventionally used during the training phase as regularization method and for quantifying uncertainty in deep learning. We propose to use dropout during training as well as inference steps, and average multiple predictions to improve the accuracy, while reducing and quantifying the uncertainty. The results are evaluated for fractional anisotropy (FA) and mean diffusivity (MD) maps which are obtained from only 3 direction scans. With our method, accuracy can be improved significantly compared to network outputs without dropout, especially when the training dataset is small. Moreover, confidence maps are generated which may aid in diagnosis of unseen pathology or artifacts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
