Synthetic polarization-sensitive optical coherence tomography by deep learning.

Synthetic polarization-sensitive optical coherence tomography by deep learning.
复制标题

DOI:
10.1038/s41746-021-00475-8
复制
发表时间:
2021-07-01
影响因子:
15.2
通讯作者:
Boppart SA
Boppart SA
中科院分区:
医学1区
文献类型:
--
作者:
Sun Y;Wang J;Shi J;Boppart SA

文献摘要

参考文献

相似文献

偏振敏感光学相干断层扫描(PS-OCT)是一种高分辨率的无标记光学生物医学成像模式,其对引起形成双折射的组织中的微结构架构(诸如胶原或肌肉纤维)敏感。然而,为了实现OCT系统中的偏振灵敏度,需要额外的硬件和复杂性。我们开发了一种深度学习方法,通过在OCT强度和PS-OCT图像上训练生成对抗网络(GAN)来合成PS-OCT图像。首先通过合成图像与真实的PS-OCT图像之间的结构相似性指数(SSIM)来评价合成精度。此外,通过使用用于癌症/正常分类的真实的和合成PS-OCT图像分别训练两个图像分类器来验证计算PS-OCT图像的有效性。两个训练分类器的相似分类结果表明,预测的PS-OCT图像可以在癌症诊断应用中潜在地互换使用。此外,我们将训练的GAN模型应用于从单独的OCT成像系统收集的OCT图像,并且合成的PS-OCT图像与使用PS-OCT成像系统从相同的样本部位收集的真实的PS-OCT图像相关性良好。这种计算PS-OCT成像方法具有降低成本、复杂性和对基于硬件的PS-OCT成像系统的需求的潜力。
Polarization-sensitive optical coherence tomography (PS-OCT) is a high-resolution label-free optical biomedical imaging modality that is sensitive to the microstructural architecture in tissue that gives rise to form birefringence, such as collagen or muscle fibers. To enable polarization sensitivity in an OCT system, however, requires additional hardware and complexity. We developed a deep-learning method to synthesize PS-OCT images by training a generative adversarial network (GAN) on OCT intensity and PS-OCT images. The synthesis accuracy was first evaluated by the structural similarity index (SSIM) between the synthetic and real PS-OCT images. Furthermore, the effectiveness of the computational PS-OCT images was validated by separately training two image classifiers using the real and synthetic PS-OCT images for cancer/normal classification. The similar classification results of the two trained classifiers demonstrate that the predicted PS-OCT images can be potentially used interchangeably in cancer diagnosis applications. In addition, we applied the trained GAN models on OCT images collected from a separate OCT imaging system, and the synthetic PS-OCT images correlate well with the real PS-OCT image collected from the same sample sites using the PS-OCT imaging system. This computational PS-OCT imaging method has the potential to reduce the cost, complexity, and need for hardware-based PS-OCT imaging systems.
DOI: 10.1109/tip.2011.2173206
发表时间: 2012-04-01
影响因子: 10.6
作者:
Brunet, Dominique;Vrscay, Edward R.;Wang, Zhou
通讯作者: Wang, Zhou
DOI: 10.1109/jbhi.2019.2912659
发表时间: 2020-01-01
影响因子: 7.7
作者:
Gao, Fei;Wu, Teresa;Patel, Bhavika
通讯作者: Patel, Bhavika
DOI: 10.1016/j.ajo.2012.12.017
发表时间: 2013-06-01
影响因子: 4.2
作者:
Lammer, Jan;Bolz, Matthias;Schmidt-Erfurth, Ursula
通讯作者: Schmidt-Erfurth, Ursula
DOI: 10.1002/lsm.21013
发表时间: 2010-12-01
影响因子: 2.4
作者:
Louie, Tiffany;Lee, Chulsung;Fried, Daniel
通讯作者: Fried, Daniel
DOI: 10.1364/josab.9.000903
发表时间: 1992-06-01
影响因子: 1.9
作者:
HEE, MR;HUANG, D;FUJIMOTO, JG
通讯作者: FUJIMOTO, JG