Semi-Supervised Deep Metrics for Image Registration
Semi-Supervised Deep Metrics for Image Registration
复制标题
DOI：
--
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
A. Sedghi;Jie Luo;Alireza Mehrtash;S. Pieper;C. Tempany;T. Kapur;P. Mousavi;W. Wells
中科院分区：
文献类型：
--
作者：
A. Sedghi;Jie Luo;Alireza Mehrtash;S. Pieper;C. Tempany;T. Kapur;P. Mousavi;W. Wells
深度度量已被证明是多模态图像配准中有效的相似度量；然而，度量目前是由训练数据中的对齐图像对构建的。在本文中，我们提出了一种从大致对齐的训练数据中学习这些度量的策略。对称数据纠正了由于数据不一致（以增加方差为代价）而导致的度量偏差，而对数据的随机扰动，即抖动，确保度量具有单一模式，并且可以通过优化进行注册。对独立的未见测试图像对的配准任务进行评估。结果表明，从严重不一致的训练数据中学习有用的深度度量是可行的，在某些情况下，结果明显优于从互信息中学习。因此，通过抖动增强数据是一种有效的策略，可以满足对对齐良好的训练数据的需求；这将深度度量注册从监督机器学习领域带入了半监督机器学习领域。
Deep metrics have been shown effective as similarity measures in multi-modal image registration; however, the metrics are currently constructed from aligned image pairs in the training data. In this paper, we propose a strategy for learning such metrics from roughly aligned training data. Symmetrizing the data corrects bias in the metric that results from misalignment in the data (at the expense of increased variance), while random perturbations to the data, i.e. dithering, ensures that the metric has a single mode, and is amenable to registration by optimization. Evaluation is performed on the task of registration on separate unseen test image pairs. The results demonstrate the feasibility of learning a useful deep metric from substantially misaligned training data, in some cases the results are significantly better than from Mutual Information. Data augmentation via dithering is, therefore, an effective strategy for discharging the need for well-aligned training data; this brings deep metric registration from the realm of supervised to semi-supervised machine learning.