Opt Express. 2022 Sep 26;30(20):36761-36773. doi: 10.1364/OE.470146.
Dipole-spread function (DSF) engineering reshapes the images of a microscope to maximize the sensitivity of measuring the 3D orientations of dipole-like emitters. However, severe Poisson shot noise, overlapping images, and simultaneously fitting high-dimensional information-both orientation and position-greatly complicates image analysis in single-molecule orientation-localization microscopy (SMOLM). Here, we report a deep-learning based estimator, termed Deep-SMOLM, that achieves superior 3D orientation and 2D position measurement precision within 3% of the theoretical limit (3.8° orientation, 0.32 sr wobble angle, and 8.5 nm lateral position using 1000 detected photons). Deep-SMOLM also demonstrates state-of-art estimation performance on overlapping images of emitters, e.g., a 0.95 Jaccard index for emitters separated by 139 nm, corresponding to a 43% image overlap. Deep-SMOLM accurately and precisely reconstructs 5D information of both simulated biological fibers and experimental amyloid fibrils from images containing highly overlapped DSFs at a speed ~10 times faster than iterative estimators.
偶极子展宽函数（DSF）工程可重塑显微镜图像，以最大程度地提高测量偶极子样发射器的 3D 取向的灵敏度。然而，严重的泊松光子噪声、重叠图像以及同时拟合高维信息——包括取向和位置——极大地增加了单分子取向定位显微镜（SMOLM）中的图像分析的复杂性。在这里，我们报告了一种基于深度学习的估算器，称为 Deep-SMOLM，它在 3%的理论极限内实现了卓越的 3D 取向和 2D 位置测量精度（使用 1000 个检测光子，分别为 3.8°的取向、0.32 sr 的抖动角和 8.5nm 的侧向位置）。Deep-SMOLM 还在发射器的重叠图像上表现出了最先进的估计性能，例如，对于间隔 139nm 的发射器，Jaccard 指数为 0.95，对应于 43%的图像重叠。Deep-SMOLM 可以从包含高度重叠 DSF 的图像中，以比迭代估算器快约 10 倍的速度，准确且精确地重建模拟生物纤维和实验性淀粉样纤维的 5D 信息。
