中国光学（中英文）2024，Vol.17Issue(4)：842-851,10.DOI:10.37188/CO.2023-0168
基于贝叶斯神经网络的相位梯度计算方法
Phase gradient estimation using Bayesian neural network
摘要
Abstract
Strain reconstruction is a vital component in the characterization of mechanical properties of phase-contrast optical coherence tomography(PC-OCT).It requires an accurate calculation for gradient dis-tributions on the differential wrapped phase map.In order to address the challenge of low signal-to-noise ra-tio(SNR)in phase gradient calculation under severe noise interference,a Bayesian-neural-network-based phase gradient calculation is presented.Initially,wrapped phase maps with varying levels of speckle noise and their corresponding ideal phase gradient distributions are generated through a computer simulation.These wrapped phase maps and phase gradient distributions serve as the training datasets.Subsequently,the network learns the"end-to-end"relationship between the wrapped phase maps and phase gradient distribu-tions in a noisy environment by utilizing a Bayesian inference theory.Finally,the wrapped phase measured by PC-OCT is processed by Bayesian neural network(BNN),and the high-quality distribution of phase gradients is accurately predicted by inputting the measured wrapped phase-difference maps into the network.Additionally,the statistical process introduced by BNN allows for the utilization of model uncertainty in the quantitative assessment of the network predictions'reliability.Computer simulation and three-point bending mechanical loading experiment compare the performance of the BNN and the popular vector method.The results indicate that the BNN can enhance the SNR of estimated phase gradients by 8% in the presence of low noise levels.Importantly,the BNN successfully recovers the phase gradients that the vector method is unable to calculate due to the unresolved phase fringes in the presence of strong noise.Moreover,the BNN model uncertainty can be used to quantitatively analyze the prediction errors.It is expected that the contribution of this work can offer effective strain estimation for PC-OCT,enabling the internal mechanical property charac-terization to become high-quality and high-reliability.关键词
光学相干层析成像/相衬技术/相位梯度计算/贝叶斯神经网络/形变测量Key words
optical coherence tomography/phase contrast/phase gradient estimation/bayesian neural net-work/deformation measurement分类
信息技术与安全科学引用本文复制引用
张康洋,倪梓浩,董博,白玉磊..基于贝叶斯神经网络的相位梯度计算方法[J].中国光学（中英文）,2024,17(4):842-851,10.基金项目
国家自然科学基金(No.61705047,No.62171140) （No.61705047,No.62171140）
广东省自然科学基金(No.2021A1515011945,No.2021A1515012598,No.2021A1515011343)Supported by National Natural Science Foundation of China(No.61705047,No.62171140) （No.2021A1515011945,No.2021A1515012598,No.2021A1515011343）
Natural Science Foundation of Guangdong Province(No.2021A1515011945,No.2021A1515012598,No.2021A 1515011343) （No.2021A1515011945,No.2021A1515012598,No.2021A 1515011343）
