FPM-INR：基于隐式神经表示的傅里叶叠层显微图像栈重建
FPM-INR: Fourier ptychographic microscopy image stack reconstruction using implicit neural representations
AI总结：
本文提出 FPM-INR 框架，将物理光学模型与隐式神经表示结合，实现无需外部训练数据的高效 FPM 图像栈重建，速度提升最高 25 倍、内存减少 80 倍。
摘要：
图像栈在各种生物和病理成像应用中提供了宝贵的三维信息。傅里叶叠层显微术（FPM）无需 z 轴扫描即可重建高分辨率、宽视场的图像栈，从而显著加快图像采集速度。然而，现有的 FPM 方法重建一个高分辨率体积场景需要数十分钟，存储需要数 GB 内存，阻碍了快速千兆像素级远程数字病理学的发展。虽然已有深度学习方法来应对这一挑战，但现有方法对新数据集的泛化能力较差，并可能产生不可靠的幻觉。本工作提出了 FPM-INR，这是一个紧凑而高效的框架，它将基于物理的光学模型与隐式神经表示（INR）相结合，以表示和重建 FPM 图像栈。FPM-INR 不受系统设计或样本类型的限制，也不需要外部训练数据。在我们展示的实验中，FPM-INR 显著优于传统 FPM 算法，在连续图像栈表示方面速度提升最高达 25 倍，内存使用减少 80 倍。
英文摘要：
Image stacks provide invaluable 3D information in various biological and pathological imaging applications. Fourier ptychographic microscopy (FPM) enables reconstructing high-resolution, wide field-of-view image stacks without z-stack scanning, thus significantly accelerating image acquisition. However, existing FPM methods take tens of minutes to reconstruct and gigabytes of memory to store a high-resolution volumetric scene, impeding fast gigapixel-scale remote digital pathology. While deep learning approaches have been explored to address this challenge, existing methods poorly generalize to novel datasets and can produce unreliable hallucinations. This work presents FPM-INR, a compact and efficient framework that integrates physics-based optical models with implicit neural representations (INR) to represent and reconstruct FPM image stacks. FPM-INR is agnostic to system design or sample types and does not require external training data. In our demonstrated experiments, FPM-INR substantially outperforms traditional FPM algorithms with up to a 25-fold increase in speed and an 80-fold reduction in memory usage for continuous image stack representations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
