Single-Molecule Localization by Voxel-Wise Regression Using Convolutional Neural Network.
Single-Molecule Localization by Voxel-Wise Regression Using Convolutional Neural Network.
复制标题
使用卷积神经网络进行体素回归的单分子定位。
DOI：
10.1016/j.rio.2020.100019
复制
发表时间：
2020
影响因子：
--
通讯作者：
Murata N
中科院分区：
文献类型：
--
作者：
Aritake T;Hino H;Namiki S;Asanuma D;Hirose K;Murata N
单分子局域显微镜被广泛应用于生物研究中，用于测量小于衍射极限的样品的纳米结构。本文提出了一种用于多焦平面显微镜的分子坐标回归新方法。将目标空间的回归问题分解为目标空间的小子集的回归问题。然后，用深度神经网络来解决这些问题。通过对回归问题的分解，可以使用完全卷积神经网络来解决回归问题。网络的计算效率很高，并且可以使用简单的、无参数的损失函数来训练网络。用四平面显微镜的模拟数据和实际数据验证了该算法的有效性。
Single-molecule localization microscopy is widely used in biological research for measuring the nanostructures of samples smaller than the diffraction limit. In this paper, a novel method for regression of the coordinates of molecules for multifocal plane microscopy is presented. A regression problem for the target space is decomposed into regression problems for small subsets of the target space. Then, a deep neural network is used to solve these problems. By decomposing the regression problem, a fully convolutional neural network can be used to solve the regression problems. The computation of the network is efficient, and a simple and parameter-free loss function can be used to train the network. The proposed algorithm is validated by both simulated and real data obtained by quad-plane microscopy.