TY - JOUR
T1 - High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning
AU - Hao, Qiangjiang
AU - Zhou, Kang
AU - Yang, Jianlong
AU - Hu, Yan
AU - Chai, Zhengjie
AU - Ma, Yuhui
AU - Liu, Gangjun
AU - Zhao, Yitian
AU - Gao, Shenghua
AU - Liu, Jiang
N1 - Publisher Copyright:
© The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its.
PY - 2020/12/1
Y1 - 2020/12/1
N2 - 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.
AB - 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.
KW - computational imaging
KW - deep learning
KW - image and signal reconstruction
KW - ophthalmic imaging
KW - optical coherence tomography
UR - http://www.scopus.com/inward/record.url?scp=85096274613&partnerID=8YFLogxK
U2 - 10.1117/1.JBO.25.12.123702
DO - 10.1117/1.JBO.25.12.123702
M3 - Article
C2 - 33191687
AN - SCOPUS:85096274613
SN - 1083-3668
VL - 25
JO - Journal of Biomedical Optics
JF - Journal of Biomedical Optics
IS - 12
M1 - 123702
ER -
