[论文解读] Robust joint registration of multiple stains and MRI for multimodal 3D histology reconstruction: Application to the Allen human brain atlas

Adrià Casamitjana, Marco Lorenzi+7 more|arXiv (Cornell University)|Apr 30, 2021

Medical Image Segmentation Techniques参考文献 71被引用 22

一句话总结

本文提出了一种基于概率生成树的框架，通过潜在变换建模空间形变，实现对多种组织切片染色和MRI图像的鲁棒、联合3D重建。该方法可生成准确、平滑的重建结果，有效抑制褶皱、撕裂等伪影，在艾伦人类脑图谱数据上取得成功应用，包括与MNI空间的配准，实现跨图谱对齐。

ABSTRACT

Joint registration of a stack of 2D histological sections to recover 3D structure (``3D histology reconstruction'') finds application in areas such as atlas building and validation of \emph{in vivo} imaging. Straightforward pairwise registration of neighbouring sections yields smooth reconstructions but has well-known problems such as ``banana effect'' (straightening of curved structures) and ``z-shift'' (drift). While these problems can be alleviated with an external, linearly aligned reference (e.g., Magnetic Resonance (MR) images), registration is often inaccurate due to contrast differences and the strong nonlinear distortion of the tissue, including artefacts such as folds and tears. In this paper, we present a probabilistic model of spatial deformation that yields reconstructions for multiple histological stains that that are jointly smooth, robust to outliers, and follow the reference shape. The model relies on a spanning tree of latent transforms connecting all the sections and slices of the reference volume, and assumes that the registration between any pair of images can be see as a noisy version of the composition of (possibly inverted) latent transforms connecting the two images. Bayesian inference is used to compute the most likely latent transforms given a set of pairwise registrations between image pairs within and across modalities. The framework is used for accurate 3D reconstruction of two stains (Nissl and parvalbumin) from the Allen human brain atlas, showing its benefits on real data with severe distortions. Moreover, we also provide the registration of the reconstructed volume to MNI space, bridging the gaps between two of the most widely used atlases in histology and MRI. The 3D reconstructed volumes and atlas registration can be downloaded from https://openneuro.org/datasets/ds003590. The code is freely available at https://github.com/acasamitjana/3dhirest.

研究动机与目标

• 为解决成对组织切片配准方法的局限性，如'香蕉效应'和'z轴漂移'，引入外部MRI参考图像。
• 在存在严重组织形变与伪影的情况下，实现对多模态组织切片（如尼尔斯染色与钙结合蛋白-β染色）的准确、平滑3D重建。
• 通过统一的概率模型联合配准多个染色切片与MRI图像，提升一致性与鲁棒性。
• 提供公开可获取的、高分辨率的艾伦人类脑图谱3D重建结果，并完成与MNI空间的配准，支持跨尺度神经影像应用。

提出的方法

• 使用潜在形变变换的生成树连接所有组织切片与MRI切片，实现一致的重建。
• 将成对图像配准建模为潜在变换的噪声组合，通过贝叶斯推断估计最可能的变换。
• 采用两种似然模型：高斯分布（ℓ2范数）用于闭式优化，拉普拉斯分布（ℓ1范数）通过线性规划提升对异常值的鲁棒性。
• 将模态间与模态内配准（如尼尔斯-MRI、尼尔斯-钙结合蛋白-β染色）整合至统一推断框架，提升一致性。
• 通过建模多对比度下的观测图结构，支持染色切片的非规则采样，增强冗余性与鲁棒性。
• 采用分层推断策略，实现高效计算，避免完整二次观测计算。

实验结果

研究问题

• RQ1 能否通过潜在空间变换的概率模型，联合重建多种组织切片染色与MRI图像，并在组织伪影存在下提升鲁棒性？
• RQ2 在多模态3D组织切片重建中，ℓ1-范数（拉普拉斯似然）相比ℓ2-范数（高斯似然）在异常值处理方面有何优势？
• RQ3 该框架在无需预先去除伪影的情况下，对非线性形变（如褶皱、撕裂、染色不一致）的纠正能力有多强？
• RQ4 在真实人类脑组织数据上，该方法在严重组织形变条件下，能否有效保持解剖结构的准确性与表面平滑性？
• RQ5 该框架能否实现多染色切片的准确、一致3D重建，并成功配准至标准MNI空间，从而支持跨图谱整合？

主要发现

• 该方法成功重建了艾伦人类脑图谱中尼尔斯染色与钙结合蛋白-β染色的3D体积，即使在存在严重伪影（如撕裂、褶皱）的情况下，仍保持平滑过渡与准确的解剖保真度。
• ℓ1-范数（拉普拉斯似然）在高异常值率的合成测试中表现出更优的鲁棒性，未观察到性能下降。
• 该框架实现了重建组织切片体积与MNI空间的精确配准，支持与活体MRI图谱的直接比较。
• 在基于特征点的误差指标上，该方法优于基线迭代配准（IR）及SOTA工具RegNet与NiftyReg，尤其在切片间与切片内对齐方面表现更优。
• 采用潜在变换的生成树结构有效减少了误差传播，表现为局部配准误差未影响邻近切片或整体体积。
• 该框架计算效率高，在标准8核CPU上完成3D重建约耗时150分钟，且在扩展至多对比度时运行时间无显著增加。