Skip to main content
main-content

26.08.2020 | Glaucoma | Ausgabe 11/2020

Graefe's Archive for Clinical and Experimental Ophthalmology 11/2020

Prediction of visual field from swept-source optical coherence tomography using deep learning algorithms

Zeitschrift:
Graefe's Archive for Clinical and Experimental Ophthalmology > Ausgabe 11/2020
Autoren:
Keunheung Park, Jinmi Kim, Sangyoon Kim, Jonghoon Shin
Wichtige Hinweise

Electronic supplementary material

The online version of this article (https://​doi.​org/​10.​1007/​s00417-020-04909-z) contains supplementary material, which is available to authorized users.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Abstract

Purpose

To develop a deep learning method to predict visual field (VF) from wide-angle swept-source optical coherence tomography (SS-OCT) and compare the performance of three Google Inception architectures.

Methods

Three deep learning models (with Inception-ResNet-v2, Inception-v3, and Inception-v4) were trained to predict 24-2 VF from the macular ganglion cell-inner plexiform layer and the peripapillary retinal nerve fibre layer map obtained by SS-OCT. The prediction performance of the three models was evaluated by using the root mean square error (RMSE) between the actual and predicted VF. The performance was also compared among different glaucoma severities and Garway-Heath sectorizations.

Results

The training dataset comprised images of 2220 eyes from 1120 subjects, and the test dataset was obtained from another 305 subjects (305 eyes). In all subjects, the global prediction errors (RMSEs) were 4.44 ± 2.09 dB, 4.78 ± 2.38 dB, and 4.85 ± 2.66 dB for the Inception-ResNet-v2, Inception-v3, and Inception-v4 architectures, respectively, and the prediction error of Inception-ResNet-v2 was significantly lower than the other two (P < 0.001). As glaucoma progressed, the prediction error of all three architectures significantly worsened to 6.59 dB, 7.33 dB, and 7.79 dB, respectively. In the analysis of sectors, the nasal sector had the lowest prediction error, followed by the superotemporal sector.

Conclusions

Inception-ResNet-v2 achieved the best performance, and the global prediction error (RMSE) was 4.44 dB. As glaucoma progressed, the prediction error became larger. This method may help clinicians determine VF, particularly for patients who are unable to undergo a physical VF test.

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

★ PREMIUM-INHALT
e.Med Interdisziplinär

Für Ihren Erfolg in Klinik und Praxis - Die beste Hilfe in Ihrem Arbeitsalltag als Mediziner

Mit e.Med Interdisziplinär erhalten Sie Zugang zu allen CME-Fortbildungen und Fachzeitschriften auf SpringerMedizin.de.

Alle e.Med Abos bis 30. April 2021 zum halben Preis!

Jetzt e.Med zum Sonderpreis bestellen!

Zusatzmaterial
Nur für berechtigte Nutzer zugänglich
Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 11/2020

Graefe's Archive for Clinical and Experimental Ophthalmology 11/2020 Zur Ausgabe

Neu im Fachgebiet Augenheilkunde

08.03.2021 | Video plus | Ausgabe 4/2021

„Simple limbal epithelial transplantation“ (SLET)

Eine einfache Technik zur Behandlung der kompletten, einseitigen Limbusstammzellinsuffizienz. Videobeitrag

10.02.2021 | Katarakt | Leitthema | Ausgabe 3/2021

Therapie der postoperativen Endophthalmitis

Operieren oder nur injizieren?