arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.17883physics.opticseess.SP
收藏

基于神经网络的光纤传输矩阵单端恢复

Single-ended Recovery of Optical fiber Transmission Matrices using Neural Networks

Yijie Zheng, George S. D. Gordon

AI总结:

针对超薄多模光纤成像中光纤校准易受环境影响且需单端体内重测的问题,提出基于神经网络的单端光纤传输矩阵重建方法,速度提升4500倍且鲁棒性更强。

摘要:

超薄多模光纤成像有望实现可对深层组织进行高分辨率成像的下一代医用内窥镜。但当前技术存在严重的光学畸变问题:光纤的校准对弯曲和温度敏感,因此需要在仅能接触单端的情况下进行体内重新测量。我们提出了一种基于神经网络(NN)的方法,可基于多波长反射模式测量重建光纤的传输矩阵(TM)。我们通过对全局相位简并不敏感的自定义损失函数,训练了两种不同的NN架构:全连接NN和卷积U-Net。我们通过模拟单端光纤重建了64×64的复数值光纤TM,误差≤4%,并在实验测量的TM上进行了交叉验证,证明了宽场和共聚焦扫描图像重建均具有较小误差。我们的TM恢复方法速度提升了4500倍,在表征过程中对光纤扰动更鲁棒,且支持非方形TM。

英文摘要:

Ultra-thin multimode optical fiber imaging promises next-generation medical endoscopes reaching high image resolution for deep tissues. However, current technology suffers from severe optical distortion, as the fiber's calibration is sensitive to bending and temperature and thus requires in vivo re-measurement with access to a single end only. We present a neural network (NN)-based approach to reconstruct the fiber's transmission matrix (TM) based on multi-wavelength reflection-mode measurements. We train two different NN architectures via a custom loss function insensitive to global phase-degeneracy: a fully connected NN and convolutional U-Net. We reconstruct the 64 $\times$ 64 complex-valued fiber TMs through a simulated single-ended optical fiber with $\leq$ 4\% error and cross-validate on experimentally measured TMs, demonstrating both wide-field and confocal scanning image reconstruction with small error. Our TM recovery approach is 4500 times faster, is more robust to fiber perturbation during characterization, and operates with non-square TMs.

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。

↑