A deep learning based pipeline for optical coherence tomography angiography.

Journal: Journal of biophotonics
Published Date:

Abstract

Optical coherence tomography angiography (OCTA) is a relatively new imaging modality that generates microvasculature map. Meanwhile, deep learning has been recently attracting considerable attention in image-to-image translation, such as image denoising, super-resolution and prediction. In this paper, we propose a deep learning based pipeline for OCTA. This pipeline consists of three parts: training data preparation, model learning and OCTA predicting using the trained model. To be mentioned, the datasets used in this work were automatically generated by a conventional system setup without any expert labeling. Promising results have been validated by in-vivo animal experiments, which demonstrate that deep learning is able to outperform traditional OCTA methods. The image quality is improved in not only higher signal-to-noise ratio but also better vasculature connectivity by laser speckle eliminating, showing potential in clinical use. Schematic description of the deep learning based optical coherent tomography angiography pipeline.

Authors

  • Xi Liu
    Collaborative Innovation Center of Radiological Medicine of Jiangsu Higher Education Institutions, Suzhou Medical College, Soochow University, Suzhou, Jiangsu 215123, China.
  • Zhiyu Huang
    Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, China.
  • Zhenzhou Wang
    Department of Emergency Medicine, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Chenyao Wen
    Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, China.
  • Zhe Jiang
    Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, China.
  • Zekuan Yu
    Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, 100871, China.
  • Jingfeng Liu
    Department of Emergency Medicine, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Gangjun Liu
    Shenzhen Graduate School, Peking University, Shenzhen, China.
  • Xiaolin Huang
    Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, 200240, Shanghai, P.R. China.
  • Andreas Maier
    Pattern Recognition Lab, University Erlangen-Nürnberg, Erlangen, Germany.
  • Qiushi Ren
    Department of Biomedical Engineering, Peking University, 100871, Beijing, China.
  • Yanye Lu
    Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Martensstr. 3, 91058, Erlangen, Germany. yanye.lu@fau.de.