Prediction of visual field from swept-source optical coherence tomography using deep learning algorithms
- PDF / 1,720,566 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 20 Downloads / 116 Views
GLAUCOMA
Prediction of visual field from swept-source optical coherence tomography using deep learning algorithms Keunheung Park 1,2 & Jinmi Kim 3 & Sangyoon Kim 4 & Jonghoon Shin 4,5 Received: 20 May 2020 / Revised: 1 August 2020 / Accepted: 19 August 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
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. Keywords Deep learning . Swept-source optical coherence tomography . Visual field . Inception
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. * Jonghoon Shin [email protected] 1
Department of Ophthalmology, Pusan National University College of Medicine, Busan, South Korea
2
Department of Ophthalmology, Pusan Medical Center, Busan, South Korea
3
Department of Biostatistics, Clinical Trial Center, Biomedical Research Institute, Pusan National University Hospital, Busan, South Korea
4
Department of Ophthalmology, College of Medicine, Pusan National University Yangsan Hospital, Yangsan, South Korea
5
Department of Ophthalmology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, 20 Geumo-ro, Mulgeum-eup, Yangsan-si, Gyeongsangnam-do, South Korea
Introduction Glaucoma is an irreversible optic neuropathy cha
Data Loading...
