用5张图联合恢复荧光显微图像的相位与物体，提升成像分辨率。
DeepPD: Joint Phase and Object Estimation from Phase Diversity with Neural Calibration of a Deformable Mirror
- 用神经网络联合建模物体和波前，学习可变形镜的校准
- 仅需5张不同相位畸变图像，即可实现高精度重建
- 适用于生物样本，对严重像差仍有鲁棒性
样品引起的像差和光学缺陷限制了荧光显微镜的分辨率。相位多样性是一种强大技术，通过在连续采集的图像中引入人为畸变（即相位多样性）来获取互补相位信息，从而实现相位与物体重建，并恢复衍射极限分辨率。这些相位多样性通常通过可变形镜引入。现有基于相位多样性的方法受限于泽尼克模式、需要大量多样性图像，或依赖精确的镜面校准，均不理想。我们提出DeepPD，一种基于深度学习的框架，将物体与波前的神经表示与可变形镜的可学习模型结合，仅用五张图像即可联合估计物体和相位。DeepPD在严重像差下仍优于以往方法，提升了重建质量与鲁棒性。我们在标定靶和生物样本上验证了其性能，包括固定PtK2细胞中免疫标记的肌球蛋白。
原文摘要 · Abstract (English)
Sample-induced aberrations and optical imperfections limit the resolution of fluorescence microscopy. Phase diversity is a powerful technique that leverages complementary phase information in sequentially acquired images with deliberately introduced aberrations--the phase diversities--to enable phase and object reconstruction and restore diffraction-limited resolution. These phase diversities are typically introduced into the optical path via a deformable mirror. Existing phase-diversity-based methods are limited to Zernike modes, require large numbers of diversity images, or depend on accurate mirror calibration--which are all suboptimal. We present DeepPD, a deep learning-based framework that combines neural representations of the object and wavefront with a learned model of the deformable mirror to jointly estimate both object and phase from only five images. DeepPD improves robustness and reconstruction quality over previous approaches, even under severe aberrations. We demonstrate its performance on calibration targets and biological samples, including immunolabeled myosin in fixed PtK2 cells.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。