Sedghi Alireza, O'Donnell Lauren J, Kapur Tina, Learned-Miller Erik, Mousavi Parvin, Wells William M
Medical Informatics Laboratory, Queen's University, Kingston, Canada.
Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, USA.
Med Image Anal. 2021 Apr;69:101939. doi: 10.1016/j.media.2020.101939. Epub 2020 Dec 18.
In this work, we propose a theoretical framework based on maximum profile likelihood for pairwise and groupwise registration. By an asymptotic analysis, we demonstrate that maximum profile likelihood registration minimizes an upper bound on the joint entropy of the distribution that generates the joint image data. Further, we derive the congealing method for groupwise registration by optimizing the profile likelihood in closed form, and using coordinate ascent, or iterative model refinement. We also describe a method for feature based registration in the same framework and demonstrate it on groupwise tractographic registration. In the second part of the article, we propose an approach to deep metric registration that implements maximum likelihood registration using deep discriminative classifiers. We show further that this approach can be used for maximum profile likelihood registration to discharge the need for well-registered training data, using iterative model refinement. We demonstrate that the method succeeds on a challenging registration problem where the standard mutual information approach does not perform well.
在这项工作中，我们提出了一个基于最大轮廓似然的成对和分组配准理论框架。通过渐近分析，我们证明最大轮廓似然配准可使生成联合图像数据的分布的联合熵的上界最小化。此外，我们通过以封闭形式优化轮廓似然，并使用坐标上升或迭代模型细化，推导出分组配准的凝聚方法。我们还在同一框架中描述了一种基于特征的配准方法，并在分组纤维束成像配准中进行了演示。在文章的第二部分，我们提出了一种深度度量配准方法，该方法使用深度判别分类器实现最大似然配准。我们进一步表明，该方法可用于最大轮廓似然配准，以消除对配准良好的训练数据的需求，使用迭代模型细化。我们证明该方法在具有挑战性的配准问题上取得了成功，而标准互信息方法在该问题上表现不佳。
