본문 바로가기

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

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q1
피인용
Web of Science 15Scopus 17
FWCI (Scopus)
0
JCR IF
JCR 2019 2.396
ISSN
0721-832X

저자

  1. 박건형제1저자Department of Ophthalmology, Pusan National University College of Medicine, Busan, South Korea
  2. 김진미Department of Biostatistics, Clinical Trial Center, Biomedical Research Institute, Pusan National University Hospital, Busan, South Korea
  3. 김상윤Department of Ophthalmology, College of Medicine, Pusan National University Yangsan Hospital, Yangsan, South Korea
  4. 신종훈교신저자Department of Ophthalmology, College of Medicine, Pusan National University Yangsan Hospital, Yangsan, South Korea

초록

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.

키워드

Deep learningSwept-source optical coherence tomographyVisual fieldInceptionLAYER THICKNESS MEASUREMENTSHD-OCTGLAUCOMAREPRODUCIBILITYSENSITIVITYPROGRESSIONHUMPHREYDISC

식별자

Scopus EID
2-s2.0-85089855720
WoS UID
000563169000002