Petascale pipeline for precise alignment of images from serial section electron microscopy.
Petascale pipeline for precise alignment of images from serial section electron microscopy.
复制标题
DOI：
10.1038/s41467-023-44354-0
复制
发表时间：
2024-01-04
影响因子：
16.6
通讯作者：
Seung, H. Sebastian
中科院分区：
文献类型：
--
作者：
Popovych, Sergiy;Macrina, Thomas;Kemnitz, Nico;Castro, Manuel;Nehoran, Barak;Jia, Zhen;Bae, J. Alexander;Mitchell, Eric;Mu, Shang;Trautman, Eric T.;Saalfeld, Stephan;Li, Kai;Seung, H. Sebastian
从连续切片电子显微镜（ssEM）图像的神经回路的重建正在加速自动图像分割方法。分割准确性通常受到对齐2D截面图像以创建3D图像堆栈的前一步骤的限制。在存在图像伪影的情况下进行精确和鲁棒的对齐是具有挑战性的，特别是当数据集达到千万亿次时。我们提出了一个计算流水线对齐ssEM图像与几个关键元素。自监督卷积网络通过度量学习进行训练，以编码和对齐图像对，并用于初始化对齐的迭代微调。一种称为矢量投票的过程增加了对图像伪影或丢失图像数据的鲁棒性。为了加速，该系列被划分为块，这些块被分发给计算工作者进行对齐。块通过组合具有衰减的变换来彼此对齐，这实现了全局对齐，而无需诉诸耗时的全局优化。我们将我们的流水线应用于整个苍蝇大脑数据集，并显示出相对于现有技术水平的更高的准确性。我们还证明了我们的流水线可以扩展到一立方毫米的小鼠视觉皮层。我们的管道通过两个开源Python包公开提供。连续切片电子显微镜（ssEM）图像的分割准确性可能受到对准2D切片图像以创建3D图像堆栈的步骤的限制。在这里，作者报告了一个用于对齐ssEM图像的计算管道，并将其应用于整个苍蝇大脑数据集。
The reconstruction of neural circuits from serial section electron microscopy (ssEM) images is being accelerated by automatic image segmentation methods. Segmentation accuracy is often limited by the preceding step of aligning 2D section images to create a 3D image stack. Precise and robust alignment in the presence of image artifacts is challenging, especially as datasets are attaining the petascale. We present a computational pipeline for aligning ssEM images with several key elements. Self-supervised convolutional nets are trained via metric learning to encode and align image pairs, and they are used to initialize iterative fine-tuning of alignment. A procedure called vector voting increases robustness to image artifacts or missing image data. For speedup the series is divided into blocks that are distributed to computational workers for alignment. The blocks are aligned to each other by composing transformations with decay, which achieves a global alignment without resorting to a time-consuming global optimization. We apply our pipeline to a whole fly brain dataset, and show improved accuracy relative to prior state of the art. We also demonstrate that our pipeline scales to a cubic millimeter of mouse visual cortex. Our pipeline is publicly available through two open source Python packages. Segmentation accuracy of serial section electron microscopy (ssEM) images can be limited by the step of aligning 2D section images to create a 3D image stack. Here the authors report a computational pipeline for aligning ssEM images and apply this to a whole fly brain dataset.
登录
查看更多内容
影响因子：
3.5
作者：
Hider R Jr;Kleissas D;Gion T;Xenes D;Matelsky J;Pryor D;Rodriguez L;Johnson EC;Gray-Roncal W;Wester B
通讯作者：
Wester B
影响因子：
64.8
作者：
Bock, Davi D.;Lee, Wei-Chung Allen;Kerlin, Aaron M.;Andermann, Mark L.;Hood, Greg;Wetzel, Arthur W.;Yurgenson, Sergey;Soucy, Edward R.;Kim, Hyon Suk;Reid, R. Clay
通讯作者：
Reid, R. Clay
影响因子：
3
作者：
Tasdizen, Tolga;Koshevoy, Pavel;Grimm, Bradley C.;Anderson, James R.;Jones, Bryan W.;Watt, Carl B.;Whitaker, Ross T.;Marc, Robert E.
通讯作者：
Marc, Robert E.
DOI：
10.1016/s0734-189x(89)80014-3
发表时间：
1989-04-01
期刊：
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING
影响因子：
--
作者：
BAJCSY, R;KOVACIC, S
通讯作者：
KOVACIC, S
影响因子：
48
作者：
Dorkenwald S;McKellar CE;Macrina T;Kemnitz N;Lee K;Lu R;Wu J;Popovych S;Mitchell E;Nehoran B;Jia Z;Bae JA;Mu S;Ih D;Castro M;Ogedengbe O;Halageri A;Kuehner K;Sterling AR;Ashwood Z;Zung J;Brittain D;Collman F;Schneider-Mizell C;Jordan C;Silversmith W;Baker C;Deutsch D;Encarnacion-Rivera L;Kumar S;Burke A;Bland D;Gager J;Hebditch J;Koolman S;Moore M;Morejohn S;Silverman B;Willie K;Willie R;Yu SC;Murthy M;Seung HS
通讯作者：
Seung HS