We present a data-driven approach to compensate for optical aberration in calibration-free quantitative phase imaging (QPI). Unlike existing methods that require additional measurements or a background region to correct aberrations, we exploit deep learning techniques to model the physics of aberration in an imaging system. We demonstrate the generation of a single-shot aberration-corrected field image by using a U-net-based deep neural network that learns a translation between an optical field with aberrations and an aberration-corrected field. The high fidelity of our method is demonstrated on 2D and 3D QPI measurements of various confluent eukaryotic cells, benchmarking against the conventional method using background subtractions.
Coordinate-based Speed of Sound Recovery for Aberration-Corrected Photoacoustic Computed Tomography
Northwestern University（西北大学）；California Institute of Technology（加州理工学院）；Tsinghua University（清华大学）；NSF-Simons AI Institute for the Sky (SkAI)（NSF-模拟斯通AI天空研究所（SkAI））
Quantitative Jones matrix imaging using vectorial Fourier ptychography
本文提出了一种显微成像技术，使用可变角度照明恢复复杂的偏振特性的标本在高分辨率和大视场。该方法扩展了傅立叶重叠关联成像，这是一种基于合成孔径的成像方法，可以通过无相位测量来提高分辨率，以额外考虑光的矢量性质。在使用配备有LED照明阵列和两个偏振器的标准显微镜获取图像后，我们的矢量傅立叶重叠关联（vFP）算法求解了每个解析空间位置处感兴趣的各向异性样本的复杂2x2琼斯矩阵。我们引入了一个新的顺序高斯-牛顿为基础的求解器，另外联合估计和消除偏振相关的成像系统像差。我们证明了有效的vFP性能，通过生成大面积（29 mm $^2$），高分辨率（1.24 $μ$ m全间距）的样品吸收，相位，取向，二向衰减和延迟的各种校准样品和生物标本的重建。
CalibFPA: A Focal Plane Array Imaging System based on Online Deep-Learning Calibration
ASELSAN（ASELSAN公司）；Nanodev Scientific（Nanodev Scientific公司）；Ostim Technical University（奥斯蒂姆技术大学）；National Magnetic Resonance Research Center (UMRAM)（国家磁共振研究中心（UMRAM））；Bilkent University（比尔肯特大学）
