June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Deep-learning-based Projection Artifact Removal in Optical Coherence Tomography Angiography Volumes
Author Affiliations & Notes
  • Song Mei
    Topcon Advanced Biomedical Imaging Laboratory, Oakland, New Jersey, United States
  • Zaixing Mao
    Topcon Advanced Biomedical Imaging Laboratory, Oakland, New Jersey, United States
  • Zhenguo Wang
    Topcon Advanced Biomedical Imaging Laboratory, Oakland, New Jersey, United States
  • Kinpui Chan
    Topcon Advanced Biomedical Imaging Laboratory, Oakland, New Jersey, United States
  • Footnotes
    Commercial Relationships   Song Mei, Topcon Medical Systems (E); Zaixing Mao, Topcon Medical Systems (E); Zhenguo Wang, Topcon Medical Systems (E); Kinpui Chan, Topcon Medical Systems (E)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 4577. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Song Mei, Zaixing Mao, Zhenguo Wang, Kinpui Chan; Deep-learning-based Projection Artifact Removal in Optical Coherence Tomography Angiography Volumes. Invest. Ophthalmol. Vis. Sci. 2020;61(7):4577.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Projection artifact due to vessels within the superficial layers may adversely affect the interpretation of OCT-A. Conventional slab-subtraction-based projection artifact removal (PAR) methods that leverage the anatomic locations of retinal vascular plexuses are generally subject to segmentation errors, making their applications to eyes with retinal vascular diseases more difficult. Here we present a segmentation-independent deep-learning (DL)-based PAR algorithm for OCT-A.

Methods : A 3D-PAR algorithm inspired by the conventional 2D slab-subtraction method is firstly developed. While capable of removing the projection artifact, this 3D-PAR method yet requires an accurate layer segmentation to create the slabs, and the operation of PAR needs to be performed on the whole 3D volume at once. To overcome these technical limitations, a U-net based DL model is then trained to identify and remove the projection artifacts on a B-frame basis without the input requirement of layer segmentation. OCT-A volumes including healthy and diseased cases are manually inspected for segmentation accuracy and processed to serve as the teacher data. The present U-net based DL model is tested on both healthy eyes and diseased eyes that include the diabetic retinopathy and choroidal neovascularization cases.

Results : OCTA images of 3×3 mm2 (320×320 pixels) or 6×6 mm2 (512×512 pixels) sizes are acquired with a swept-source OCT (DRI-OCT Triton; Topcon, Tokyo). Fig 1 shows a B-frame of flow signal being overlaid on the structure OCT image of a healthy subject. It can be observed that the false flow signal has been minimized after PAR. A comparison of OCT-A images processed before and after PAR is shown in Fig.2.

Conclusions : Without the dependency on layer segmentation and the influences from other frames in the volume, the newly developed algorithm is shown to provide a practical advantage to minimize projection artifact in the interpretation of OCT-A.

This is a 2020 ARVO Annual Meeting abstract.

 

Figure 1. B-frame overlay of OCTA signal on OCT structure image for (A) before, and (B) after PAR. The effectiveness of PAR is readily observed across the retinal pigment epithelium layer.

Figure 1. B-frame overlay of OCTA signal on OCT structure image for (A) before, and (B) after PAR. The effectiveness of PAR is readily observed across the retinal pigment epithelium layer.

 

Figure 2. OCTA enface images of (from left to right) superficial plexus, deep plexus, outer retina layer, and choriocapillaris. Upper and lower rows correspond to images before and after PAR, respectively.

Figure 2. OCTA enface images of (from left to right) superficial plexus, deep plexus, outer retina layer, and choriocapillaris. Upper and lower rows correspond to images before and after PAR, respectively.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×