Kläser Kerstin, Borges Pedro, Shaw Richard, Ranzini Marta, Modat Marc, Atkinson David, Thielemans Kris, Hutton Brian, Goh Vicky, Cook Gary, Cardoso M Jorge, Ourselin Sébastien
Dept. Medical Physics & Biomedical Engineering, University College London, UK.
School of Biomedical Engineering & Imaging Sciences, King's College London, UK.
Appl Sci (Basel). 2021 Feb 12;11(4):1667. doi: 10.3390/app11041667. eCollection 2021 Feb.
Synthesising computed tomography (CT) images from magnetic resonance images (MRI) plays an important role in the field of medical image analysis, both for quantification and diagnostic purposes. Convolutional neural networks (CNNs) have achieved state-of-the-art results in image-to-image translation for brain applications. However, synthesising whole-body images remains largely uncharted territory involving many challenges, including large image size and limited field of view, complex spatial context, and anatomical differences between images acquired at different times. We propose the use of an uncertainty-aware multi-channel multi-resolution 3D cascade network specifically aiming for whole-body MR to CT synthesis. The Mean Absolute Error on the synthetic CT generated with the MultiRes network (73.90 HU) is compared to multiple baseline CNNs like 3D U-Net (92.89 HU), HighRes3DNet (89.05 HU) and deep boosted regression (77.58 HU) and shows superior synthesis performance. We ultimately exploit the extrapolation properties of the MultiRes networks on sub-regions of the body.
从磁共振图像（MRI）合成计算机断层扫描（CT）图像在医学图像分析领域中发挥着重要作用，无论是用于量化还是诊断目的。卷积神经网络（CNN）在脑部应用的图像到图像转换方面取得了最先进的成果。然而，合成全身图像在很大程度上仍是未知领域，面临许多挑战，包括图像尺寸大、视野有限、复杂的空间背景以及不同时间采集的图像之间的解剖差异。我们提出使用一种不确定性感知多通道多分辨率3D级联网络，专门用于全身磁共振到计算机断层扫描的合成。将使用MultiRes网络生成的合成CT上的平均绝对误差（73.90 HU）与多个基线CNN（如3D U-Net（92.89 HU）、HighRes3DNet（89.05 HU）和深度增强回归（77.58 HU））进行比较，结果显示出卓越的合成性能。我们最终利用MultiRes网络在身体子区域上的外推特性。
