Zuo Ruizhi, Wei Shuwen, Wang Yaning, Irsch Kristina, Kang Jin U
Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, USA.
CNRS, Vision Institute, Paris, France.
Biomed Opt Express. 2024 Aug 28;15(9):5533-5546. doi: 10.1364/BOE.532258. eCollection 2024 Sep 1.
Optical coherence tomography (OCT) allows high-resolution volumetric imaging of biological tissues However, 3D-image acquisition often suffers from motion artifacts due to slow frame rates and involuntary and physiological movements of living tissue. To solve these issues, we implement a real-time 4D-OCT system capable of reconstructing near-distortion-free volumetric images based on a deep learning-based reconstruction algorithm. The system initially collects undersampled volumetric images at a high speed and then upsamples the images in real-time by a convolutional neural network (CNN) that generates high-frequency features using a deep learning algorithm. We compare and analyze both dual-2D- and 3D-UNet-based networks for the OCT 3D high-resolution image reconstruction. We refine the network architecture by incorporating multi-level information to accelerate convergence and improve accuracy. The network is optimized by utilizing the 16-bit floating-point precision for network parameters to conserve GPU memory and enhance efficiency. The result shows that the refined and optimized 3D-network is capable of retrieving the tissue structure more precisely and enable real-time 4D-OCT imaging at a rate greater than 10 Hz with a root mean square error (RMSE) of ∼0.03.
光学相干断层扫描（OCT）可实现生物组织的高分辨率容积成像。然而，由于帧率较低以及活体组织的非自愿和生理运动，三维图像采集常常受到运动伪影的影响。为了解决这些问题，我们基于深度学习重建算法实现了一种能够重建近无失真容积图像的实时四维OCT系统。该系统最初以高速采集欠采样的容积图像，然后通过卷积神经网络（CNN）实时对图像进行上采样，该网络使用深度学习算法生成高频特征。我们对基于双二维和三维U-Net的网络进行了比较和分析，用于OCT三维高分辨率图像重建。我们通过合并多级信息来优化网络架构，以加速收敛并提高准确性。通过将网络参数设置为16位浮点精度来优化网络，以节省GPU内存并提高效率。结果表明，经过优化的三维网络能够更精确地恢复组织结构，并能够以大于10Hz的速率进行实时四维OCT成像，均方根误差（RMSE）约为0.03。
