学习旋转不变特征用于低温电子显微图像重建
Learning Rotation Invariant Features for Cryogenic Electron Microscopy Image Reconstruction
摘要：
低温电子显微镜（Cryo-EM）是一项获得诺贝尔奖的技术，用于以近原子分辨率确定颗粒的3D结构。恢复3D单粒子结构的基本步骤是对齐其2D投影;因此，需要构建具有固定旋转角度的正则表示。大多数方法使用离散聚类，不能捕捉图像旋转的连续性质，其他方法遭受低质量的图像重建。我们提出了一种新的方法，利用了生成对抗网络的最新发展。我们介绍了一个编码器，解码器与旋转角度分类。此外，我们利用解码器的输出，以最大限度地减少重建误差。我们用Cryo-EM 5 HDB和旋转的MNIST数据集证明了我们的方法，这些数据集比最近的方法有了很大的改进。
英文摘要：
Cryo-Electron Microscopy (Cryo-EM) is a Nobel prize-winning technology for determining the 3D structure of particles at near-atomic resolution. A fundamental step in the recovering of the 3D single-particle structure is to align its 2D projections; thus, the construction of a canonical representation with a fixed rotation angle is required. Most approaches use discrete clustering which fails to capture the continuous nature of image rotation, others suffer from low-quality image reconstruction. We propose a novel method that leverages the recent development in the generative adversarial networks. We introduce an encoder-decoder with a rotation angle classifier. In addition, we utilize a discriminator on the decoder output to minimize the reconstruction error. We demonstrate our approach with the Cryo-EM 5HDB and the rotated MNIST datasets showing substantial improvement over recent methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
