[论文解读] PgNN: Physics-guided Neural Network for Fourier Ptychographic Microscopy

Yongbing Zhang, Yangzhe Liu+5 more|arXiv (Cornell University)|Sep 19, 2019

Advanced X-ray Imaging Techniques参考文献 39被引用 5

一句话总结

该论文提出PgNN，一种用于傅里叶叠层显微成像的物理引导神经网络，可在无需真实标签或大规模标注数据集的情况下重建高分辨率、大视场的图像。通过将正向成像过程建模为具有可解释物理约束（如总变差正则化和基于泽尼克多项式的像差补偿）的可学习神经网络，PgNN 实现了无监督、鲁棒的重建，即使在高离焦和高曝光条件下也表现优异，在模拟和实验数据集上均优于传统方法。

ABSTRACT

Fourier ptychography (FP) is a newly developed computational imaging approach that achieves both high resolution and wide field of view by stitching a series of low-resolution images captured under angle-varied illumination. So far, many supervised data-driven models have been applied to solve inverse imaging problems. These models need massive amounts of data to train, and are limited by the dataset characteristics. In FP problems, generic datasets are always scarce, and the optical aberration varies greatly under different acquisition conditions. To address these dilemmas, we model the forward physical imaging process as an interpretable physics-guided neural network (PgNN), where the reconstructed image in the complex domain is considered as the learnable parameters of the neural network. Since the optimal parameters of the PgNN can be derived by minimizing the difference between the model-generated images and real captured angle-varied images corresponding to the same scene, the proposed PgNN can get rid of the problem of massive training data as in traditional supervised methods. Applying the alternate updating mechanism and the total variation regularization, PgNN can flexibly reconstruct images with improved performance. In addition, the Zernike mode is incorporated to compensate for optical aberrations to enhance the robustness of FP reconstructions. As a demonstration, we show our method can reconstruct images with smooth performance and detailed information in both simulated and experimental datasets. In particular, when validated in an extension of a high-defocus, high-exposure tissue section dataset, PgNN outperforms traditional FP methods with fewer artifacts and distinguishable structures.

研究动机与目标

• 解决傅里叶叠层显微成像中标签数据稀缺与光学像差多变的问题。
• 通过将成像物理原理嵌入神经网络框架，减少对大规模监督训练数据的依赖。
• 实现复杂域图像（振幅与相位）的无监督、高保真重建，并提升对离焦与曝光伪影的鲁棒性。
• 在未知光学像差先验知识的前提下，同时恢复样品图像与物镜的孔径函数。

提出的方法

• 将傅里叶叠层成像的正向过程建模为可微分神经网络，将重建的复振幅图像视为可学习参数。
• 采用交替优化策略，迭代更新物面与孔径函数，最小化预测与捕获的强度图像之间的数据保真度损失。
• 引入总变差（TV）正则化以增强图像平滑性，并抑制振幅与相位分量中的噪声。
• 将泽尼克多项式作为可学习基函数，用于建模并补偿孔径函数中的光学像差。
• 仅使用低分辨率、角度变化的强度图像，在无真实标签或先验像差数据的情况下进行无监督训练。
• 通过可微分正向模型实现反向传播，支持图像与孔径函数的端到端联合优化。

实验结果

研究问题

• RQ1 物理引导的神经网络是否能在无需大规模标注数据集的情况下重建高分辨率傅里叶叠层显微图像？
• RQ2 引入总变差正则化在FP重建中如何提升图像质量并抑制伪影？
• RQ3 泽尼克模式表示在不同成像条件下，能在多大程度上增强对光学像差的鲁棒性？
• RQ4 在高离焦与高曝光等挑战性成像场景下，无监督PgNN框架与传统迭代方法（如ePIE）相比表现如何？

主要发现

• PgNN在高离焦与高曝光条件下，相比ePIE展现出更优的图像重建质量，伪影更少，细胞结构更清晰。
• 引入总变差正则化显著降低了噪声并提升了图像平滑性，尤其在细节丰富的区域表现更优。
• 泽尼克模式补偿能够准确建模光学像差，增强了在不同采集条件下的重建鲁棒性。
• PgNN在无真实标签或先验像差知识的情况下，成功恢复了高分辨率的振幅与相位图像，展现出在模拟与实验数据集中的强大泛化能力。
• 完整PgNN模型（含TV与泽尼克）的重建结果在视觉与定量指标上均更接近真实值，优于缺少这些组件的模型。