Gum-Net: Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging.
Gum-Net: Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging.
复制标题
DOI：
10.1109/cvpr42600.2020.00413
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Xu M
中科院分区：
文献类型：
--
作者：
Zeng X;Xu M
我们提出了一个几何无监督匹配网络（口香糖网），用于寻找两个图像之间的几何对应关系，并应用于3D亚断层图像对齐和平均。亚断层图像对齐是冷冻电子断层扫描（cryo-ET）中最重要的任务，冷冻电子断层扫描是一种革命性的3D成像技术，用于可视化单细胞中未受干扰的细胞景观的分子组织。然而，由于噪音和缺失楔形效应等严重的成像限制，子断层图像对齐和平均非常具有挑战性。我们引入了一个端到端的可训练架构，其中有三个专门设计用于保存特征空间信息和传播特征匹配信息的新模块。训练以完全无监督的方式执行，以优化匹配度量。不需要地面实况转换信息，也不需要类别级或实例级匹配监督信息。在对6个真实的和9个模拟数据集进行系统评估后，我们证明Gum-Net将对齐误差降低了40%至50%，并将平均分辨率提高了10%。与最先进的子断层图像对齐方法相比，Gum-Net在实践中通过GPU加速实现了70到110倍的加速。我们的工作是第一个3D无监督几何匹配方法的图像的强变换变化和高噪声水平。训练代码、训练模型和数据集可在我们的开源软件AITom 1中获得。
We propose a Geometric unsupervised matching Network (Gum-Net) for finding the geometric correspondence between two images with application to 3D subtomogram alignment and averaging. Subtomogram alignment is the most important task in cryo-electron tomography (cryo-ET), a revolutionary 3D imaging technique for visualizing the molecular organization of unperturbed cellular landscapes in single cells. However, subtomogram alignment and averaging are very challenging due to severe imaging limits such as noise and missing wedge effects. We introduce an end-to-end trainable architecture with three novel modules specifically designed for preserving feature spatial information and propagating feature matching information. The training is performed in a fully unsupervised fashion to optimize a matching metric. No ground truth transformation information nor category-level or instance-level matching supervision information is needed. After systematic assessments on six real and nine simulated datasets, we demonstrate that Gum-Net reduced the alignment error by 40 to 50% and improved the averaging resolution by 10%. Gum-Net also achieved 70 to 110 times speedup in practice with GPU acceleration compared to state-of-the-art subtomogram alignment methods. Our work is the first 3D unsupervised geometric matching method for images of strong transformation variation and high noise level. The training code, trained model, and datasets are available in our open-source software AITom1.
登录
查看更多内容
影响因子：
10.9
作者：
de Vos, Bob D.;Berendsen, Floris F.;Isgum, Ivana
通讯作者：
Isgum, Ivana
影响因子：
5.4
作者：
Baldwin PR;Tan YZ;Eng ET;Rice WJ;Noble AJ;Negro CJ;Cianfrocco MA;Potter CS;Carragher B
通讯作者：
Carragher B
影响因子：
3
作者：
Amat, Fernando;Comolli, Luis R.;Horowitz, Mark
通讯作者：
Horowitz, Mark
DOI：
10.1109/tpami.2013.48
发表时间：
2013-09-01
影响因子：
23.6
作者：
Drira, Hassen;Ben Amor, Boulbaba;Slama, Rim
通讯作者：
Slama, Rim
影响因子：
64.5
作者：
Guo Q;Lehmer C;Martínez-Sánchez A;Rudack T;Beck F;Hartmann H;Pérez-Berlanga M;Frottin F;Hipp MS;Hartl FU;Edbauer D;Baumeister W;Fernández-Busnadiego R
通讯作者：
Fernández-Busnadiego R