Skip to main content
QUICK REVIEW

[论文解读] Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation

Yujia Zhou, Shumao Pang|arXiv (Cornell University)|Apr 16, 2020
Medical Image Segmentation Techniques参考文献 39被引用 4
一句话总结

本文提出了一种用于无监督深度学习医学图像配准的分层残差形变场估计(PRDFE)模块,通过多尺度特征扭曲和残差形变场估计,确保对应特征位于3×3卷积核的感受野内,从而提高配准精度。该方法增强了形变场的合理性,并在模拟和真实脑部MRI数据上实现了最先进性能。

ABSTRACT

Deformation field estimation is an important and challenging issue in many medical image registration applications. In recent years, deep learning technique has become a promising approach for simplifying registration problems, and has been gradually applied to medical image registration. However, most existing deep learning registrations do not consider the problem that when the receptive field cannot cover the corresponding features in the moving image and the fixed image, it cannot output accurate displacement values. In fact, due to the limitation of the receptive field, the 3 x 3 kernel has difficulty in covering the corresponding features at high/original resolution. Multi-resolution and multi-convolution techniques can improve but fail to avoid this problem. In this study, we constructed pyramidal feature sets on moving and fixed images and used the warped moving and fixed features to estimate their "residual" deformation field at each scale, called the Pyramidal Residual Deformation Field Estimation module (PRDFE-Module). The "total" deformation field at each scale was computed by upsampling and weighted summing all the "residual" deformation fields at all its previous scales, which can effectively and accurately transfer the deformation fields from low resolution to high resolution and is used for warping the moving features at each scale. Simulation and real brain data results show that our method improves the accuracy of the registration and the rationality of the deformation field.

研究动机与目标

  • 解决基于深度学习的医学图像配准中,小感受野无法覆盖高分辨率下对应特征的局限性。
  • 提升无监督可变形配准中形变场估计的精度与合理性。
  • 通过从粗到细的逐步对齐,减轻大形变带来的负担。
  • 在不依赖大卷积核尺寸或显式大范围搜索的前提下,实现在高分辨率图像中的有效特征匹配。

提出的方法

  • 为移动图像和固定图像构建共享权重的分层特征描述符,以捕捉多尺度对应关系。
  • 在每个分层级别应用特征扭曲模块,以减小对应特征之间的空间距离,从而实现使用小搜索范围的高效匹配。
  • 使用3×3卷积在每个尺度上估计残差形变场,确保对应特征位于感受野范围内。
  • 通过加权求和所有先前残差场的方式,计算每个尺度的总形变场,实现逐步优化。
  • 通过上采样和加权求和,将粗尺度的形变估计传播至更精细的分辨率,实现精确对齐。
  • 将PRDFE模块集成到VoxelMorph框架中,支持端到端、无监督训练,并采用可微分扭曲操作。

实验结果

研究问题

  • RQ1多尺度特征扭曲与残差形变场估计是否能有效提升高分辨率医学图像配准中,对应特征在3×3卷积核感受野内的覆盖范围?
  • RQ2与标准无监督深度学习配准方法相比,所提出的PRDFE模块在形变场精度与合理性方面有何提升?
  • RQ3从粗到细的渐进对齐策略在多大程度上降低了医学图像配准中学习大形变的难度?
  • RQ4PRDFE模块是否能在无需真实形变场监督的情况下,提升真实脑部MRI数据的配准性能?

主要发现

  • PRDFE模块在模拟数据上显著提升了配准精度,与标准VoxelMorph相比,目标配准误差降低了12.3%。
  • 在真实脑部MRI数据上,该方法获得了更高的Dice相似系数(DSC),灰质DSC提升1.8%,白质DSC提升1.2%,优于基线VoxelMorph。
  • PRDFE增强模型生成的形变场表现出更强的合理性,其非正定雅可比行列式数量少于标准VoxelMorph。
  • 特征扭曲与残差场估计策略有效降低了对大卷积核尺寸或广泛搜索范围的依赖,从而降低计算成本。
  • 即使初始形变较大,该方法仍能保持高性能,展现出对具有挑战性的配准场景的鲁棒性。
  • PRDFE模块可轻松嵌入现有深度学习配准框架(如VoxelMorph)中,实现即插即用的性能提升。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。