光学相干断层扫描中基于深度学习的数字重新聚焦。
Digital refocusing based on deep learning in optical coherence tomography.
作者信息
Yuan Zhuoqun, Yang Di, Yang Zihan, Zhao Jingzhu, Liang Yanmei
机构信息
Institute of Modern Optics, Nankai University, Tianjin Key Laboratory of Micro-scale Optical Information Science and Technology, Tianjin 300350, China.
Contributed equally.
出版信息
Biomed Opt Express. 2022 Apr 25;13(5):3005-3020. doi: 10.1364/BOE.453326. eCollection 2022 May 1.
Abstract
We present a deep learning-based digital refocusing approach to extend depth of focus for optical coherence tomography (OCT) in this paper. We built pixel-level registered pairs of low-resolution (LR) and high-resolution (HR) OCT images based on experimental data and introduced the receptive field block into the generative adversarial networks to learn the complex mapping relationship between LR-HR image pairs. It was demonstrated by results of phantom and biological samples that the lateral resolutions of OCT images were improved in a large imaging depth clearly. We firmly believe deep learning methods have broad prospects in optimizing OCT imaging.
摘要
在本文中，我们提出了一种基于深度学习的数字重聚焦方法，以扩展光学相干断层扫描（OCT）的焦深。我们基于实验数据构建了低分辨率（LR）和高分辨率（HR）OCT图像的像素级配准对，并将感受野模块引入生成对抗网络，以学习LR-HR图像对之间的复杂映射关系。体模和生物样本的结果表明，OCT图像的横向分辨率在较大成像深度上得到了显著提高。我们坚信深度学习方法在优化OCT成像方面具有广阔的前景。
相似文献
1
Digital refocusing based on deep learning in optical coherence tomography.光学相干断层扫描中基于深度学习的数字重新聚焦。
Biomed Opt Express. 2022 Apr 25;13(5):3005-3020. doi: 10.1364/BOE.453326. eCollection 2022 May 1.
2
Super-resolution technology to simultaneously improve optical & digital resolution of optical coherence tomography via deep learning.通过深度学习同时提高光学相干断层扫描的光学分辨率和数字分辨率的超分辨率技术。
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:1879-1882. doi: 10.1109/EMBC44109.2020.9175777.
3
Self super-resolution of optical coherence tomography images based on deep learning.基于深度学习的光学相干断层扫描图像自超分辨率
Opt Express. 2023 Aug 14;31(17):27566-27581. doi: 10.1364/OE.495530.
4
Retinal fundus image superresolution generated by optical coherence tomography based on a realistic mixed attention GAN.基于逼真混合注意力生成对抗网络的光学相干断层扫描生成的视网膜眼底图像超分辨率
Med Phys. 2022 May;49(5):3185-3198. doi: 10.1002/mp.15580. Epub 2022 Mar 30.
5
High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning.深度学习在低比特深度光学相干断层扫描中的高信噪比重建。
J Biomed Opt. 2020 Nov;25(12). doi: 10.1117/1.JBO.25.12.123702.
6
Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders.用于视网膜疾病合成光学相干断层扫描图像的生成对抗网络模型评估
Transl Vis Sci Technol. 2020 May 27;9(2):29. doi: 10.1167/tvst.9.2.29. eCollection 2020 May.
7
N2NSR-OCT: Simultaneous denoising and super-resolution in optical coherence tomography images using semisupervised deep learning.N2NSR-OCT：使用半监督深度学习在光学相干断层扫描图像中同时进行去噪和超分辨率处理
J Biophotonics. 2021 Jan;14(1):e202000282. doi: 10.1002/jbio.202000282. Epub 2020 Oct 19.
8
Combined in-depth, 3D, en face imaging of the optic disc, optic disc pits and optic disc pit maculopathy using swept-source megahertz OCT at 1050 nm.使用1050纳米扫频源兆赫兹光学相干断层扫描技术对视盘、视盘小凹和视盘小凹黄斑病变进行联合深度、三维、正面成像。
Graefes Arch Clin Exp Ophthalmol. 2018 Feb;256(2):289-298. doi: 10.1007/s00417-017-3857-9. Epub 2017 Dec 14.
9
Optical Coherence Tomography Angiography and En Face Optical Coherence Tomography Features of Paracentral Acute Middle Maculopathy.中心旁急性中黄斑病变的光学相干断层扫描血管造影及正面光学相干断层扫描特征
Am J Ophthalmol. 2015 Dec;160(6):1259-1268.e2. doi: 10.1016/j.ajo.2015.09.016. Epub 2015 Sep 18.
10
Super-resolution of real-world rock microcomputed tomography images using cycle-consistent generative adversarial networks.使用循环一致生成对抗网络对真实岩石微观计算机断层扫描图像进行超分辨率处理。
Phys Rev E. 2020 Feb;101(2-1):023305. doi: 10.1103/PhysRevE.101.023305.
引用本文的文献
1
Machine Learning-Assisted Short-Wave InfraRed (SWIR) Techniques for Biomedical Applications: Towards Personalized Medicine.用于生物医学应用的机器学习辅助短波红外（SWIR）技术：迈向个性化医疗
J Pers Med. 2023 Dec 26;14(1):33. doi: 10.3390/jpm14010033.
2
MAS-Net OCT: a deep-learning-based speckle-free multiple aperture synthetic optical coherence tomography.MAS-Net光学相干断层扫描：基于深度学习的无斑点多孔径合成光学相干断层扫描
Biomed Opt Express. 2023 May 10;14(6):2591-2607. doi: 10.1364/BOE.483740. eCollection 2023 Jun 1.
3
Optical coherence microscopy with a split-spectrum image reconstruction method for temporal-dynamics contrast-based imaging of intracellular motility.采用分裂光谱图像重建方法的光学相干显微镜用于基于时间动态对比度的细胞内运动成像。
Biomed Opt Express. 2023 Jan 4;14(2):577-592. doi: 10.1364/BOE.478264. eCollection 2023 Feb 1.
本文引用的文献
1
Deep learning-based point-scanning super-resolution imaging.基于深度学习的点扫描超分辨率成像。
Nat Methods. 2021 Apr;18(4):406-416. doi: 10.1038/s41592-021-01080-z. Epub 2021 Mar 8.
2
Resolution enhancement and realistic speckle recovery with generative adversarial modeling of micro-optical coherence tomography.基于微光学相干断层扫描的生成对抗模型实现分辨率增强与逼真散斑恢复
Biomed Opt Express. 2020 Nov 19;11(12):7236-7252. doi: 10.1364/BOE.402847. eCollection 2020 Dec 1.
3
Deep learning extended depth-of-field microscope for fast and slide-free histology.深度学习扩展景深显微镜，用于快速无载玻片组织学。
Proc Natl Acad Sci U S A. 2020 Dec 29;117(52):33051-33060. doi: 10.1073/pnas.2013571117. Epub 2020 Dec 14.
4
NanoJ: a high-performance open-source super-resolution microscopy toolbox.NanoJ：一个高性能的开源超分辨率显微镜工具箱。
J Phys D Appl Phys. 2019 Apr 17;52(16):163001. doi: 10.1088/1361-6463/ab0261. Epub 2019 Feb 18.
5
High-resolution polarization-sensitive optical coherence tomography for zebrafish muscle imaging.用于斑马鱼肌肉成像的高分辨率偏振敏感光学相干断层扫描技术
Biomed Opt Express. 2020 Sep 15;11(10):5618-5632. doi: 10.1364/BOE.402267. eCollection 2020 Oct 1.
6
Three-dimensional virtual refocusing of fluorescence microscopy images using deep learning.基于深度学习的荧光显微镜图像三维虚拟聚焦。
Nat Methods. 2019 Dec;16(12):1323-1331. doi: 10.1038/s41592-019-0622-5. Epub 2019 Nov 4.
7
Simultaneous denoising and super-resolution of optical coherence tomography images based on generative adversarial network.基于生成对抗网络的光学相干断层扫描图像的同步去噪与超分辨率
Opt Express. 2019 Apr 29;27(9):12289-12307. doi: 10.1364/OE.27.012289.
8
High-throughput, high-resolution deep learning microscopy based on registration-free generative adversarial network.基于无配准生成对抗网络的高通量、高分辨率深度学习显微镜技术。
Biomed Opt Express. 2019 Feb 4;10(3):1044-1063. doi: 10.1364/BOE.10.001044. eCollection 2019 Mar 1.
9
Nano-optic endoscope for high-resolution optical coherence tomography .用于高分辨率光学相干断层扫描的纳米光学内窥镜
Nat Photonics. 2018 Sep;12(9):540-547. doi: 10.1038/s41566-018-0224-2. Epub 2018 Jul 30.
10
Deep learning enables cross-modality super-resolution in fluorescence microscopy.深度学习可实现荧光显微镜的跨模态超分辨率。
Nat Methods. 2019 Jan;16(1):103-110. doi: 10.1038/s41592-018-0239-0. Epub 2018 Dec 17.
Zotero 插件