Neural network-based image reconstruction in swept-source optical coherence tomography using undersampled spectral data.
Neural network-based image reconstruction in swept-source optical coherence tomography using undersampled spectral data.
复制标题
DOI：
10.1038/s41377-021-00594-7
复制
发表时间：
2021-07-29
期刊：
影响因子：
--
通讯作者：
Ozcan A
中科院分区：
文献类型：
--
作者：
Zhang Y;Liu T;Singh M;Çetintaş E;Luo Y;Rivenson Y;Larin KV;Ozcan A
光学相干断层扫描（OCT）是一种广泛使用的非侵入性生物医学成像模式，可以快速提供样品的体积图像。在这里，我们提出了一个基于深度学习的图像重建框架，可以使用欠采样的光谱数据生成扫频源OCT（SS-OCT）图像，而不会产生任何空间混叠伪影。这种基于神经网络的图像重建不需要对光学设置进行任何硬件更改，并且可以很容易地与现有的扫频源或谱域OCT系统集成，以减少要采集的原始光谱数据量。为了证明这个框架的有效性，我们使用SS-OCT系统成像的小鼠胚胎样本训练和盲测了一个深度神经网络。使用2倍欠采样光谱数据（即，每A线640个光谱点），训练的神经网络可以使用多个图形处理单元（GPU）在0.59 ms内盲重建512个A线，去除由于光谱欠采样引起的空间混叠伪影，还呈现与使用全光谱OCT数据重建的相同样本的图像的非常好的匹配（即，每A线1280个光谱点）。我们还成功地证明了该框架可以进一步扩展到处理每个A线的3倍欠采样光谱数据，与2倍光谱欠采样相比，重建图像质量会有所下降。在此基础上，提出了一种A线优化欠采样方法，通过联合优化光谱采样位置和相应的图像重建网络，与2倍或3倍的光谱欠采样结果相比，该方法使用更少的光谱数据点提高了整体成像性能。这种支持深度学习的图像重建方法可广泛用于各种形式的谱域OCT系统，有助于提高成像速度，而不会牺牲图像分辨率和信噪比。
Optical coherence tomography (OCT) is a widely used non-invasive biomedical imaging modality that can rapidly provide volumetric images of samples. Here, we present a deep learning-based image reconstruction framework that can generate swept-source OCT (SS-OCT) images using undersampled spectral data, without any spatial aliasing artifacts. This neural network-based image reconstruction does not require any hardware changes to the optical setup and can be easily integrated with existing swept-source or spectral-domain OCT systems to reduce the amount of raw spectral data to be acquired. To show the efficacy of this framework, we trained and blindly tested a deep neural network using mouse embryo samples imaged by an SS-OCT system. Using 2-fold undersampled spectral data (i.e., 640 spectral points per A-line), the trained neural network can blindly reconstruct 512 A-lines in 0.59 ms using multiple graphics-processing units (GPUs), removing spatial aliasing artifacts due to spectral undersampling, also presenting a very good match to the images of the same samples, reconstructed using the full spectral OCT data (i.e., 1280 spectral points per A-line). We also successfully demonstrate that this framework can be further extended to process 3× undersampled spectral data per A-line, with some performance degradation in the reconstructed image quality compared to 2× spectral undersampling. Furthermore, an A-line-optimized undersampling method is presented by jointly optimizing the spectral sampling locations and the corresponding image reconstruction network, which improved the overall imaging performance using less spectral data points per A-line compared to 2× or 3× spectral undersampling results. This deep learning-enabled image reconstruction approach can be broadly used in various forms of spectral-domain OCT systems, helping to increase their imaging speed without sacrificing image resolution and signal-to-noise ratio.
登录
查看更多内容
影响因子：
3.4
作者：
Baumann B;Potsaid B;Kraus MF;Liu JJ;Huang D;Hornegger J;Cable AE;Duker JS;Fujimoto JG
通讯作者：
Fujimoto JG
DOI：
10.1038/s41377-021-00506-9
发表时间：
2021-03-23
期刊：
Light, science & applications
影响因子：
--
作者：
Huang L;Chen H;Luo Y;Rivenson Y;Ozcan A
通讯作者：
Ozcan A
影响因子：
3.5
作者：
Blatter, Cedric;Klein, Thomas;Leitgeb, Rainer A.
通讯作者：
Leitgeb, Rainer A.
影响因子：
3.8
作者：
Hershko, Eran;Weiss, Lucien E.;Shechtman, Yoav
通讯作者：
Shechtman, Yoav
影响因子：
2.4
作者：
FERCHER, AF;HITZENBERGER, CK;ELZAIAT, SY
通讯作者：
ELZAIAT, SY