High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning

doi:10.1117/1.JBO.25.12.123702

	High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning
	Hao, Qiangjiang 1,2; Zhou, Kang1,3 ; Yang, Jianlong 1; Hu, Yan 4; Chai, Zhengjie1,3 ; Ma, Yuhui 1; Liu, Gangjun 5; Zhao, Yitian 1; Gao, Shenghua3 ; Liu, Jiang 1,4
	2020-12
发表期刊	JOURNAL OF BIOMEDICAL OPTICS
ISSN	1083-3668
EISSN	1560-2281
卷号	25 期号:12 页码:#VALUE!
DOI	10.1117/1.JBO.25.12.123702
摘要	Significance: Reducing the bit depth is an effective approach to lower the cost of an optical coherence tomography (OCT) imaging device and increase the transmission efficiency in data acquisition and telemedicine. However, a low bit depth will lead to the degradation of the detection sensitivity, thus reducing the signal-to-noise ratio (SNR) of OCT images. Aim: We propose using deep learning to reconstruct high SNR OCT images from low bit-depth acquisition. Approach: The feasibility of our approach is evaluated by applying this approach to the quantized 3- to 8-bit data from native 12-bit interference fringes. We employ a pixel-to-pixel generative adversarial network (pix2pixGAN) architecture in the low-to-high bit-depth OCT image transition. Results: Extensively, qualitative and quantitative results show our method could significantly improve the SNR of the low bit-depth OCT images. The adopted pix2pixGAN is superior to other possible deep learning and compressed sensing solutions. Conclusions: Our work demonstrates that the proper integration of OCT and deep learning could benefit the development of healthcare in low-resource settings. (C) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License.
关键词	optical coherence tomography image and signal reconstruction ophthalmic imaging computational imaging deep learning
URL	查看原文
收录类别	SCI ; SCIE ; EI
语种	英语
WOS研究方向	Biochemistry & Molecular Biology ; Optics ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Biochemical Research Methods ; Optics ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000605144900003
出版者	SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
WOS关键词	OCT ; ACQUISITION ; IMAGES ; PERFORMANCE
原始文献类型	Article
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/125967
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_高盛华组信息科学与技术学院_博士生
通讯作者	Yang, Jianlong
作者单位	1.Chinese Acad Sci, Cixi Inst Biomed Engn, Ningbo Inst Mat Technol & Engn, Ningbo, Peoples R China; 2.Univ Sci & Technol China, Nano Sci & Technol Inst, Suzhou, Peoples R China; 3.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China; 4.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China; 5.Shenzhen Bay Lab, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Hao, Qiangjiang,Zhou, Kang,Yang, Jianlong,et al. High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning[J]. JOURNAL OF BIOMEDICAL OPTICS,2020,25(12):#VALUE!.
APA	Hao, Qiangjiang.,Zhou, Kang.,Yang, Jianlong.,Hu, Yan.,Chai, Zhengjie.,...&Liu, Jiang.(2020).High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning.JOURNAL OF BIOMEDICAL OPTICS,25(12),#VALUE!.
MLA	Hao, Qiangjiang,et al."High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning".JOURNAL OF BIOMEDICAL OPTICS 25.12(2020):#VALUE!.