Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Utilizing classical image processing for ground truth in deep learning-based projection artifact removal
Author Affiliations & Notes
  • Ali Salehi
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Jan Henrik Fitschen
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Homayoun Bagherinia
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Warren Lewis
    Bayside Photonics, Yellow Springs, Ohio, United States
  • Footnotes
    Commercial Relationships   Ali Salehi Carl Zeiss Meditec, Inc., Code E (Employment); Jan Henrik Fitschen Carl Zeiss Meditec, Inc., Code E (Employment); Homayoun Bagherinia Carl Zeiss Meditec, Inc., Code E (Employment); Warren Lewis Carl Zeiss Meditec, Inc., Code C (Consultant/Contractor)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 2370. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ali Salehi, Jan Henrik Fitschen, Homayoun Bagherinia, Warren Lewis; Utilizing classical image processing for ground truth in deep learning-based projection artifact removal. Invest. Ophthalmol. Vis. Sci. 2024;65(7):2370.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Optical coherence tomography angiography (OCTA) scans offer 3D insights into retinal vasculature; however, deeper layers often exhibit projection artifacts that hamper accurate interpretation of the images. Classical projection artifact removal methods, despite their effectiveness, are slow and may rely on lower-level algorithms like layer-segmentation. We present an approach that leverages the output of classical methods as ground truth (GT) for training a deep learning (DL) model, encoding the principles of the classical method into the weights of a Convolutional Neural Network (CNN).

Methods : We employed a 2D U-Net architecture with a depth of 4, using flow and structure B-scans as inputs, with projection-removed flow B-scans generated using a classical image processing algorithm as GT. A dataset, obtained from PLEX® Elite 9000 (ZEISS, Dublin, CA) was split based on patient IDs and scan patterns. It consisted of 135 eyes for training and 15 eyes for testing. For network training, we used the Adam optimizer along with mean squared error (MSE) as the loss function.

Results : Our model effectively eliminated projection artifacts in unseen OCTA scans in the hold-out test set, MSE of 3.7±0.8, 5.8±2.1, and 3.7±1.2 for Deep, RPE, and full-retina slabs, with high normalized cross-correlation scores of 0.98, 0.96, and 0.99, respectively. The DL model processes scans 2 to 4 times faster than the classical method, depending on the scan sizes. This efficiency could be further enhanced with batch processing and network optimization. Figure 1 compares classical and DL methods with unprocessed data, highlighting red-overlay flow signals on structure B-scans. Figure 2 shows slabs processed by both, emphasizing the DL model's accuracy in mirroring classical results.

Conclusions : Our DL method, trained using GT data from a classical image processing method, demonstrates that hand-designed, classical methods can be instrumental in generating offline training data for DL models. This approach accelerates processing and enables selective B-scan processing while maintaining the accuracy of classical methods in removing projection artifacts in OCTA data.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Figure 1: Sample B-scan before and after artifact removal, showing overlaid flow information on structural images.

Figure 1: Sample B-scan before and after artifact removal, showing overlaid flow information on structural images.

 

Figure 2: En face views from a test scan, comparing results before and after application of DL and classical methods.

Figure 2: En face views from a test scan, comparing results before and after application of DL and classical methods.

×
×

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.

×