EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Segmentation-Free OCT-Volume-Based Deep Learning Model Improves Pointwise Visual Field Sensitivity Estimation

Zhiqi Chen, Eitan Shemuelian, Gadi Wollstein, Yao Wang, Hiroshi Ishikawa, Joel S Schuman

Translational Vision Science & Technology · 29.06.2023 · 12 (6) · 28

DOI: 10.1167/tvst.12.6.28 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Vision Science & Technology, erschienen am 29.06.2023. Verfasst von Zhiqi Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, NYU Tandon School of Engineering, Brooklyn, NY, USA. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NEI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The structural changes measured by optical coherence tomography (OCT) are related to functional changes in visual fields (VFs). This study aims to accurately assess the structure-function relationship and overcome the challenges brought by the minimal measurable level (floor effect) of segmentation-dependent OCT measurements commonly used in prior studies.

Methods

We developed a deep learning model to estimate the functional performance directly from three-dimensional (3D) OCT volumes and compared it to the model trained with segmentation-dependent two-dimensional (2D) OCT thickness maps. Moreover, we proposed a gradient loss to utilize the spatial information of VFs.

Results

Our 3D model was significantly better than the 2D model both globally and pointwise regarding both mean absolute error (MAE = 3.11 + 3.54 vs. 3.47 ± 3.75 dB, P < 0.001) and Pearson's correlation coefficient (0.80 vs. 0.75, P < 0.001). On a subset of test data with floor effects, the 3D model showed less influence from floor effects than the 2D model (MAE = 5.24 ± 3.99 vs. 6.34 ± 4.58 dB, P < 0.001, and correlation 0.83 vs. 0.74, P < 0.001). The gradient loss improved the estimation error for low-sensitivity values. Furthermore, our 3D model outperformed all prior studies.

Conclusions

By providing a better quantitative model to encapsulate the structure-function relationship more accurately, our method may help deriving VF test surrogates. Translational Relevance: DL-based VF surrogates not only benefit patients by reducing the testing time of VFs but also allow clinicians to make clinical judgments without the inherent limitations of VFs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansTomography, Optical CoherenceVisual Fields

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, NYU Tandon School of Engineering, Brooklyn, NY, USA.
  • Department of Ophthalmology, NYU Langone Health, NYU Grossman School of Medicine, New York, NY, USA.
  • Department of Biomedical Engineering, NYU Tandon School of Engineering, Brooklyn, NY, USA.
  • Center for Neural Science, NYU College of Arts and Sciences, New York, NY, USA.
  • Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, Portland, OR, USA.
  • Department of Medical Informatics and Clinical Epidemiology, Oregon Health and Science University, Portland, OR, USA.

Förderung

  • NEI NIH HHS

Zitieren

APA

Chen, Z., Shemuelian, E., Wollstein, G., Wang, Y., Ishikawa, H., & Schuman, J. S. (2023). Segmentation-Free OCT-Volume-Based Deep Learning Model Improves Pointwise Visual Field Sensitivity Estimation. Translational Vision Science & Technology, 12(6), 28. https://doi.org/10.1167/tvst.12.6.28

Vancouver

Chen Z, Shemuelian E, Wollstein G, Wang Y, Ishikawa H, Schuman JS. Segmentation-Free OCT-Volume-Based Deep Learning Model Improves Pointwise Visual Field Sensitivity Estimation. Translational Vision Science & Technology. 2023;12(6):28. doi:10.1167/tvst.12.6.28

BibTeX
@article{Chen2023,
  author = {Chen, Zhiqi and Shemuelian, Eitan and Wollstein, Gadi and Wang, Yao and Ishikawa, Hiroshi and Schuman, Joel S},
  title = {Segmentation-Free OCT-Volume-Based Deep Learning Model Improves Pointwise Visual Field Sensitivity Estimation},
  journal = {Translational Vision Science & Technology},
  year = {2023},
  volume = {12},
  number = {6},
  pages = {28},
  doi = {10.1167/tvst.12.6.28}
}
Kostenlos starten →