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

A Deep Learning Model for Automated Segmentation of Geographic Atrophy Imaged Using Swept-Source OCT

Varsha Pramil, Luis de Sisternes, Lars Omlor, Warren Lewis, Harris Sheikh, Zhongdi Chu, Niranchana Manivannan, Mary Durbin, Ruikang K Wang, Philip J Rosenfeld, Mengxi Shen, Robyn Guymer und 3 weitere

Ophthalmology Retina · 2023-02 · 7 (2) · 127-141

DOI: 10.1016/j.oret.2022.08.007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ophthalmology Retina, 2023-02. Verfasst von Varsha Pramil und 14 weiteren Autor:innen. Beteiligte Einrichtung: Tufts University School of Medicine, Boston, Massachusetts; New England Eye Center, Tufts New England Medical Center, Boston, Massachusetts. Hauptthemen laut MEDLINE: Geographic Atrophy, Deep Learning. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 40 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: To present a deep learning algorithm for segmentation of geographic atrophy (GA) using en face swept-source OCT (SS-OCT) images that is accurate and reproducible for the assessment of GA growth over time. DESIGN: Retrospective review of images obtained as part of a prospective natural history study. SUBJECTS: Patients with GA (n = 90), patients with early or intermediate age-related macular degeneration (n = 32), and healthy controls (n = 16). METHODS: An automated algorithm using scan volume data to generate 3 image inputs characterizing the main OCT features of GA-hypertransmission in subretinal pigment epithelium (sub-RPE) slab, regions of RPE loss, and loss of retinal thickness-was trained using 126 images (93 with GA and 33 without GA, from the same number of eyes) using a fivefold cross-validation method and data augmentation techniques. It was tested in an independent set of one hundred eighty 6 × 6-mm2 macular SS-OCT scans consisting of 3 repeated scans of 30 eyes with GA at baseline and follow-up as well as 45 images obtained from 42 eyes without GA. MAIN OUTCOME MEASURES: The GA area, enlargement rate of GA area, square root of GA area, and square root of the enlargement rate of GA area measurements were calculated using the automated algorithm and compared with ground truth calculations performed by 2 manual graders. The repeatability of these measurements was determined using intraclass coefficients (ICCs). RESULTS: There were no significant differences in the GA areas, enlargement rates of GA area, square roots of GA area, and square roots of the enlargement rates of GA area between the graders and the automated algorithm. The algorithm showed high repeatability, with ICCs of 0.99 and 0.94 for the GA area measurements and the enlargement rates of GA area, respectively. The repeatability limit for the GA area measurements made by grader 1, grader 2, and the automated algorithm was 0.28, 0.33, and 0.92 mm2, respectively. CONCLUSIONS: When compared with manual methods, this proposed deep learning-based automated algorithm for GA segmentation using en face SS-OCT images was able to accurately delineate GA and produce reproducible measurements of the enlargement rates of GA.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Geographic AtrophyDeep LearningHumansFluorescein AngiographyProspective StudiesTomography, Optical CoherenceRetinal Pigment Epithelium

Stichwörter der Autor:innen

Automated algorithmDeep learningGeographic atrophySS-OCTSwept-source OCT

Autor:innen und Institutionen

  • Tufts University School of Medicine, Boston, Massachusetts; New England Eye Center, Tufts New England Medical Center, Boston, Massachusetts.
  • Carl Zeiss Meditec, Inc, Dublin, California.
  • Carl Zeiss Meditec, Inc, Dublin, California; Bayside Photonics, Inc, Yellow Springs, Ohio.
  • New England Eye Center, Tufts New England Medical Center, Boston, Massachusetts.
  • Department of Biomedical Engineering, University of Washington Seattle, Seattle, Washington.
  • Heru, Inc., Miami, Florida.

Förderung

  • NEI NIH HHS

Zitieren

APA

Pramil, V., de Sisternes, L., Omlor, L., Lewis, W., Sheikh, H., Chu, Z., Manivannan, N., Durbin, M., Wang, R. K., Rosenfeld, P. J., Shen, M., Guymer, R., Liang, M. C., Gregori, G., & Waheed, N. K. (2023). A Deep Learning Model for Automated Segmentation of Geographic Atrophy Imaged Using Swept-Source OCT. Ophthalmology Retina, 7(2), 127-141. https://doi.org/10.1016/j.oret.2022.08.007

Vancouver

Pramil V, de Sisternes L, Omlor L, Lewis W, Sheikh H, Chu Z, et al. A Deep Learning Model for Automated Segmentation of Geographic Atrophy Imaged Using Swept-Source OCT. Ophthalmology Retina. 2023;7(2):127-141. doi:10.1016/j.oret.2022.08.007

BibTeX
@article{Pramil2023,
  author = {Pramil, Varsha and de Sisternes, Luis and Omlor, Lars and Lewis, Warren and Sheikh, Harris and Chu, Zhongdi and Manivannan, Niranchana and Durbin, Mary and Wang, Ruikang K and Rosenfeld, Philip J and Shen, Mengxi and Guymer, Robyn and Liang, Michelle C and Gregori, Giovanni and Waheed, Nadia K},
  title = {A Deep Learning Model for Automated Segmentation of Geographic Atrophy Imaged Using Swept-Source OCT},
  journal = {Ophthalmology Retina},
  year = {2023},
  volume = {7},
  number = {2},
  pages = {127--141},
  doi = {10.1016/j.oret.2022.08.007}
}
Kostenlos starten →