IEEE Trans Med Imaging. 2022 Sep;41(9):2371-2384. doi: 10.1109/TMI.2022.3163018. Epub 2022 Aug 31.
Deep neural networks for medical image reconstruction are traditionally trained using high-quality ground-truth images as training targets. Recent work on Noise2Noise (N2N) has shown the potential of using multiple noisy measurements of the same object as an alternative to having a ground-truth. However, existing N2N-based methods are not suitable for learning from the measurements of an object undergoing nonrigid deformation. This paper addresses this issue by proposing the deformation-compensated learning (DeCoLearn) method for training deep reconstruction networks by compensating for object deformations. A key component of DeCoLearn is a deep registration module, which is jointly trained with the deep reconstruction network without any ground-truth supervision. We validate DeCoLearn on both simulated and experimentally collected magnetic resonance imaging (MRI) data and show that it significantly improves imaging quality.
用于医学图像重建的深度神经网络传统上使用高质量的真实图像作为训练目标进行训练。最近关于 Noise2Noise (N2N) 的研究表明，使用同一物体的多个噪声测量值作为替代真实值的可能性。然而，现有的基于 N2N 的方法不适用于学习经历非刚性变形的物体的测量值。本文通过提出变形补偿学习（DeCoLearn）方法来解决这个问题，该方法通过补偿物体变形来训练深度重建网络。DeCoLearn 的一个关键组成部分是一个深度配准模块，它与深度重建网络一起进行联合训练，而不需要任何真实值监督。我们在模拟和实验采集的磁共振成像（MRI）数据上验证了 DeCoLearn，并表明它显著提高了成像质量。
