首页>
外国专利>
Methods, instruments, and computer programs to improve the reconstruction of high-density ultra-resolution images from diffraction-limited images obtained by single-molecule localization microscopy.
Methods, instruments, and computer programs to improve the reconstruction of high-density ultra-resolution images from diffraction-limited images obtained by single-molecule localization microscopy.
展开▼
机译:从单分子定位显微镜获得的衍射极限图像中改善高密度超分辨率图像重建的方法,仪器和计算机程序。
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention reconstructs a synthetic high-density ultra-resolution image from at least one low-information content image, such as from a sequence of diffraction-limited images obtained by single-molecule localization microscopy. Regarding. After acquiring such a sequence of diffraction-limited images, a low-density localized image is reconstructed from the acquired sequence of diffraction-limited images according to single-molecule localized microscopy image processing. The reconstructed low-density localized image and / or the corresponding low-resolution wide-field image is input to the artificial neural network, and the synthetic super-density super-resolution image is acquired from the artificial neural network. A neural network is a function of a training objective function that compares a high-density ultra-resolution image with the output of a corresponding artificial neural network, a low-density localized image, at least a partially corresponding low-resolution wide-field image, and a corresponding. Trained by training data with triplets of high density ultra-resolution images. FIG. 21.
展开▼