Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture.

Purpose: In this study, an algorithm based on deep learning was presented to reduce the retinal nerve fiber layer (RNFL) segmentation errors in spectral domain optical coherence tomography (SD-OCT) scans using ophthalmologists' manual segmentation as a reference standard. Methods: In this study, we...

Full description

Bibliographic Details
Published in:Journal of Ophthalmic & Vision Research Vol. 18; no. 1; pp. 41 - 51
Main Authors: Razaghi, Ghazale, Fard, Masoud Aghsaei, Hejazi, Marjaneh
Format: equations & formulas pictorial research tables/charts Journal Article
Published: Knowledge E DMCC Jan-Mar2023
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=162044639&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 162044639
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        20082010
        AY5S
      jtl: Journal of Ophthalmic & Vision Research
      issn: 20082010
      maglogo: N
    pubinfo:
      dt: Jan-Mar2023
      vid: 18
      iid: 1
      pid: 35682
      pub: Knowledge E DMCC
    artinfo:
      ui:
        162044639
        162044639
        162044639
        10.18502/jovr.v18i1.12724
        162044639
      ppf: 41
      ppct: 10
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture.
      aug:
        au:
          Razaghi, Ghazale
          Fard, Masoud Aghsaei
          Hejazi, Marjaneh
        affil: Medical Physics and Biomedical Engineering Department, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
      sug:
        subj:
          Nerve Fibers Anatomy and Histology
          Optic Nerve Diseases Diagnosis
          Tomography, Optical Coherence
          Retinal Diseases Therapy
          Neural Networks (Computer)
          Image Processing, Computer Assisted
          Algorithms
          Deep Learning
          Ophthalmologists
          Artifacts
          Correlation Coefficient
          Prediction Models
          Human
          Male
          Female
          Young Adult
          Adult
          Middle Age
          Aged
          Aged, 80 and Over
          Data Analysis Software
          Descriptive Statistics
          Adult: 19-44 years
          Middle Aged: 45-64 years
          Aged: 65+ years
          Aged, 80 & over
          Male
          Female
      ab: Purpose: In this study, an algorithm based on deep learning was presented to reduce the retinal nerve fiber layer (RNFL) segmentation errors in spectral domain optical coherence tomography (SD-OCT) scans using ophthalmologists' manual segmentation as a reference standard. Methods: In this study, we developed an image segmentation network based on deep learning to automatically identify the RNFL thickness from B-scans obtained with SD-OCT. The scans were collected from Farabi Eye Hospital (500 B-scans were used for training, while 50 were used for testing). To remove the speckle noise from the images, preprocessing was applied before training, and postprocessing was performed to fill any discontinuities that might exist. Afterward, output masks were analyzed for their average thickness. Finally, the calculation of mean absolute error between predicted and ground truth RNFL thickness was performed. Results: Based on the testing database, SD-OCT segmentation had an average dice similarity coefficient of 0.91, and thickness estimation had a mean absolute error of 2.23 ± 2.1 |Jm. As compared to conventional OCT software algorithms, deep learning predictions were better correlated with the best available estimate during the test period (r² = 0.99 vs r² = 0.88, respectively; P < 0.001). Conclusion: Our experimental results demonstrate effective and precise segmentation of the RNFL layer with the coefficient of 0.91 and reliable thickness prediction with MAE 2.23 ± 2.1 jm in SD-OCT B-scans. Performance is comparable with human annotation of the RNFL layer and other algorithms according to the correlation coefficient of 0.99 and 0.88, respectively, while artifacts and errors are evident.
      pubtype: Academic Journal
      doctype:
        equations & formulas
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N