Jin Yuncheng, Zhang Yiye, Hu Lejia, Huang Haiyang, Xu Qiaoqi, Zhu Xinpei, Huang Limeng, Zheng Yao, Shen Hui-Liang, Gong Wei, Si Ke
Opt Express. 2018 Nov 12;26(23):30162-30171. doi: 10.1364/OE.26.030162.
Non-invasive, real-time imaging and deep focus into tissue are in high demand in biomedical research. However, the aberration that is introduced by the refractive index inhomogeneity of biological tissue hinders the way forward. A rapid focusing with sensor-less aberration corrections, based on machine learning, is demonstrated in this paper. The proposed method applies the Convolutional Neural Network (CNN), which can rapidly calculate the low-order aberrations from the point spread function images with Zernike modes after training. The results show that approximately 90 percent correction accuracy can be achieved. The average mean square error of each Zernike coefficient in 200 repetitions is 0.06. Furthermore, the aberration induced by 1-mm-thick phantom samples and 300-µm-thick mouse brain slices can be efficiently compensated through loading a compensation phase on an adaptive element placed at the back-pupil plane. The phase reconstruction requires less than 0.2 s. Therefore, this method offers great potential for in vivo real-time imaging in biological science.
在生物医学研究中，对无创、实时成像以及对组织进行深度聚焦的需求很高。然而，生物组织折射率不均匀所引入的像差阻碍了这一进程。本文展示了一种基于机器学习的无传感器像差校正快速聚焦方法。所提出的方法应用了卷积神经网络（CNN），经过训练后，它可以从带有泽尼克模式的点扩散函数图像中快速计算出低阶像差。结果表明，校正精度可达到约90%。在200次重复中，每个泽尼克系数的平均均方误差为0.06。此外，通过在置于后焦平面的自适应元件上加载补偿相位，可以有效补偿1毫米厚的模拟样本和300微米厚的小鼠脑切片所引起的像差。相位重建所需时间不到0.2秒。因此，该方法在生物科学的体内实时成像方面具有巨大潜力。
