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

Qiangjiang Hao, Kang Zhou, Jianlong Yang, Yan Hu, Zhengjie Chai, Yuhui Ma, Gangjun Liu, Yitian Zhao, Shenghua Gao, Jiang Liu

Research output: Journal PublicationArticlepeer-review

17 Citations (Scopus)


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.

Original languageEnglish
Article number123702
JournalJournal of Biomedical Optics
Issue number12
Publication statusPublished - 1 Dec 2020
Externally publishedYes


  • computational imaging
  • deep learning
  • image and signal reconstruction
  • ophthalmic imaging
  • optical coherence tomography

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Biomedical Engineering


Dive into the research topics of 'High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning'. Together they form a unique fingerprint.

Cite this