脑MRI中SE(3)等变且噪声不变的三维刚性运动追踪
SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI
AI总结：
提出EquiTrack混合框架，结合去噪器与SE(3)等变CNN解耦噪声处理和空间特征提取，并闭式估计刚性变换，在成人及胎儿脑MRI运动追踪中超越现有方法。
摘要：
刚性运动追踪在许多需要检测、校正或考虑运动的医学成像应用中至关重要。现代策略依赖卷积神经网络（CNN），并将该问题表述为刚性配准。然而，CNN并未利用此任务中的自然对称性，因为它们对平移具有等变性（其输出随输入而平移），但对旋转不具有等变性。本文提出EquiTrack，这是首个利用近期可导向SE(3)等变CNN（E-CNN）进行运动追踪的方法。虽然可导向E-CNN能够提取不同姿态之间的对应特征，但在含噪医学图像上测试表明，它们没有足够的学习容量来学习噪声不变性。因此，我们引入一种混合架构，将去噪器与E-CNN配对，以解耦对解剖学无关强度特征的处理与对等变空间特征的提取。随后以闭式解估计刚性变换。EquiTrack在成人大脑MRI和胎儿MRI时间序列的运动追踪中优于最先进的学习方法和优化方法。我们的代码可在https://github.com/BBillot/EquiTrack获取。
英文摘要：
Rigid motion tracking is paramount in many medical imaging applications where movements need to be detected, corrected, or accounted for. Modern strategies rely on convolutional neural networks (CNN) and pose this problem as rigid registration. Yet, CNNs do not exploit natural symmetries in this task, as they are equivariant to translations (their outputs shift with their inputs) but not to rotations. Here we propose EquiTrack, the first method that uses recent steerable SE(3)-equivariant CNNs (E-CNN) for motion tracking. While steerable E-CNNs can extract corresponding features across different poses, testing them on noisy medical images reveals that they do not have enough learning capacity to learn noise invariance. Thus, we introduce a hybrid architecture that pairs a denoiser with an E-CNN to decouple the processing of anatomically irrelevant intensity features from the extraction of equivariant spatial features. Rigid transforms are then estimated in closed-form. EquiTrack outperforms state-of-the-art learning and optimisation methods for motion tracking in adult brain MRI and fetal MRI time series. Our code is available at https://github.com/BBillot/EquiTrack.
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。
