Skip to main content
construction release_alert
Scholars@Duke will be undergoing maintenance April 11-15. Some features may be unavailable during this time.
cancel

Detecting Retinal Nerve Fibre Layer Segmentation Errors on Spectral Domain-Optical Coherence Tomography with a Deep Learning Algorithm.

Publication ,  Journal Article
Jammal, AA; Thompson, AC; Ogata, NG; Mariottoni, EB; Urata, CN; Costa, VP; Medeiros, FA
Published in: Sci Rep
July 8, 2019

In this study we developed a deep learning (DL) algorithm that detects errors in retinal never fibre layer (RNFL) segmentation on spectral-domain optical coherence tomography (SDOCT) B-scans using human grades as the reference standard. A dataset of 25,250 SDOCT B-scans reviewed for segmentation errors by human graders was randomly divided into validation plus training (50%) and test (50%) sets. The performance of the DL algorithm was evaluated in the test sample by outputting a probability of having a segmentation error for each B-scan. The ability of the algorithm to detect segmentation errors was evaluated with the area under the receiver operating characteristic (ROC) curve. Mean DL probabilities of segmentation error in the test sample were 0.90 ± 0.17 vs. 0.12 ± 0.22 (P < 0.001) for scans with and without segmentation errors, respectively. The DL algorithm had an area under the ROC curve of 0.979 (95% CI: 0.974 to 0.984) and an overall accuracy of 92.4%. For the B-scans with severe segmentation errors in the test sample, the DL algorithm was 98.9% sensitive. This algorithm can help clinicians and researchers review images for artifacts in SDOCT tests in a timely manner and avoid inaccurate diagnostic interpretations.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Sci Rep

DOI

EISSN

2045-2322

Publication Date

July 8, 2019

Volume

9

Issue

1

Start / End Page

9836

Location

England

Related Subject Headings

  • Tomography, Optical Coherence
  • Retinal Neurons
  • Random Allocation
  • Nerve Fibers
  • Middle Aged
  • Male
  • Image Interpretation, Computer-Assisted
  • Humans
  • Glaucoma
  • Female
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Jammal, A. A., Thompson, A. C., Ogata, N. G., Mariottoni, E. B., Urata, C. N., Costa, V. P., & Medeiros, F. A. (2019). Detecting Retinal Nerve Fibre Layer Segmentation Errors on Spectral Domain-Optical Coherence Tomography with a Deep Learning Algorithm. Sci Rep, 9(1), 9836. https://doi.org/10.1038/s41598-019-46294-6
Jammal, Alessandro A., Atalie C. Thompson, Nara G. Ogata, Eduardo B. Mariottoni, Carla N. Urata, Vital P. Costa, and Felipe A. Medeiros. “Detecting Retinal Nerve Fibre Layer Segmentation Errors on Spectral Domain-Optical Coherence Tomography with a Deep Learning Algorithm.Sci Rep 9, no. 1 (July 8, 2019): 9836. https://doi.org/10.1038/s41598-019-46294-6.
Jammal AA, Thompson AC, Ogata NG, Mariottoni EB, Urata CN, Costa VP, et al. Detecting Retinal Nerve Fibre Layer Segmentation Errors on Spectral Domain-Optical Coherence Tomography with a Deep Learning Algorithm. Sci Rep. 2019 Jul 8;9(1):9836.
Jammal, Alessandro A., et al. “Detecting Retinal Nerve Fibre Layer Segmentation Errors on Spectral Domain-Optical Coherence Tomography with a Deep Learning Algorithm.Sci Rep, vol. 9, no. 1, July 2019, p. 9836. Pubmed, doi:10.1038/s41598-019-46294-6.
Jammal AA, Thompson AC, Ogata NG, Mariottoni EB, Urata CN, Costa VP, Medeiros FA. Detecting Retinal Nerve Fibre Layer Segmentation Errors on Spectral Domain-Optical Coherence Tomography with a Deep Learning Algorithm. Sci Rep. 2019 Jul 8;9(1):9836.

Published In

Sci Rep

DOI

EISSN

2045-2322

Publication Date

July 8, 2019

Volume

9

Issue

1

Start / End Page

9836

Location

England

Related Subject Headings

  • Tomography, Optical Coherence
  • Retinal Neurons
  • Random Allocation
  • Nerve Fibers
  • Middle Aged
  • Male
  • Image Interpretation, Computer-Assisted
  • Humans
  • Glaucoma
  • Female