Centre for Medical Image Computing, University College London, London, UK; Wellcome / EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK.
Centre for Medical Image Computing, University College London, London, UK; Wellcome / EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK.
Med Image Anal. 2021 Dec;74:102231. doi: 10.1016/j.media.2021.102231. Epub 2021 Sep 21.
We present Free Point Transformer (FPT) - a deep neural network architecture for non-rigid point-set registration. Consisting of two modules, a global feature extraction module and a point transformation module, FPT does not assume explicit constraints based on point vicinity, thereby overcoming a common requirement of previous learning-based point-set registration methods. FPT is designed to accept unordered and unstructured point-sets with a variable number of points and uses a "model-free" approach without heuristic constraints. Training FPT is flexible and involves minimizing an intuitive unsupervised loss function, but supervised, semi-supervised, and partially- or weakly-supervised training are also supported. This flexibility makes FPT amenable to multimodal image registration problems where the ground-truth deformations are difficult or impossible to measure. In this paper, we demonstrate the application of FPT to non-rigid registration of prostate magnetic resonance (MR) imaging and sparsely-sampled transrectal ultrasound (TRUS) images. The registration errors were 4.71 mm and 4.81 mm for complete TRUS imaging and sparsely-sampled TRUS imaging, respectively. The results indicate superior accuracy to the alternative rigid and non-rigid registration algorithms tested and substantially lower computation time. The rapid inference possible with FPT makes it particularly suitable for applications where real-time registration is beneficial.
我们提出了自由点变换（FPT）——一种用于非刚性点集配准的深度神经网络架构。FPT 由两个模块组成，一个是全局特征提取模块，另一个是点变换模块，它不基于点附近的显式约束，从而克服了以前基于学习的点集配准方法的一个常见要求。FPT 旨在接受具有可变点数的无序和非结构化的点集，并采用无启发式约束的“无模型”方法。训练 FPT 具有灵活性，涉及最小化直观的无监督损失函数，但也支持监督、半监督和部分或弱监督训练。这种灵活性使得 FPT 适用于多模态图像配准问题，在这些问题中，很难或不可能测量地面真实变形。在本文中，我们展示了 FPT 在前列腺磁共振（MR）成像和稀疏采样经直肠超声（TRUS）图像的非刚性配准中的应用。完整 TRUS 成像和稀疏采样 TRUS 成像的配准误差分别为 4.71mm 和 4.81mm。结果表明，FPT 的准确性优于测试的替代刚性和非刚性配准算法，并且计算时间大大缩短。FPT 可以快速推断，特别适合实时配准有益的应用。
