Next Article in Journal
Continuous Subcutaneous Apomorphine Infusion in Parkinson’s Disease: A Single-Center, Long-Term Follow-Up Study of the Causes for Discontinuation
Previous Article in Journal
Prevalence and Characteristics of Psoriasis in Romania—First Study in Overall Population
Previous Article in Special Issue
Indicators of Visual Prognosis in Diabetic Macular Oedema
Article

Accuracy of a Machine-Learning Algorithm for Detecting and Classifying Choroidal Neovascularization on Spectral-Domain Optical Coherence Tomography

1
Pharma Research and Early Development, Roche Innovation Center, F. Hoffmann-La Roche Ltd., 4070 Basel, Switzerland
2
Department of Eye and Vision Science, University of Liverpool, Liverpool L7 8XP, UK
3
Liverpool Ophthalmic Reading Centre (NetwORC, UK), St. Paul’s Eye Unit, Royal Liverpool University Hospital, Liverpool L7 8XP, UK
*
Author to whom correspondence should be addressed.
Academic Editor: Margaret M. DeAngelis
J. Pers. Med. 2021, 11(6), 524; https://doi.org/10.3390/jpm11060524
Received: 21 April 2021 / Revised: 28 May 2021 / Accepted: 7 June 2021 / Published: 8 June 2021
(This article belongs to the Special Issue Age-Related Macular Degeneration and Diabetic Retinopathy)
Background: To evaluate the performance of a machine-learning (ML) algorithm to detect and classify choroidal neovascularization (CNV), secondary to age-related macular degeneration (AMD) on spectral-domain optical coherence tomography (SD-OCT) images. Methods: Baseline fluorescein angiography (FA) and SD-OCT images from 1037 treatment-naive study eyes and 531 fellow eyes, without advanced AMD from the phase 3 HARBOR trial (NCT00891735), were used to develop, train, and cross-validate an ML pipeline combining deep-learning–based segmentation of SD-OCT B-scans and CNV classification, based on features derived from the segmentations, in a five-fold setting. FA classification of the CNV phenotypes from HARBOR was used for generating the ground truth for model development. SD-OCT scans from the phase 2 AVENUE trial (NCT02484690) were used to externally validate the ML model. Results: The ML algorithm discriminated CNV absence from CNV presence, with a very high accuracy (area under the receiver operating characteristic [AUROC] = 0.99), and classified occult versus predominantly classic CNV types, per FA assessment, with a high accuracy (AUROC = 0.91) on HARBOR SD-OCT images. Minimally classic CNV was discriminated with significantly lower performance. Occult and predominantly classic CNV types could be discriminated with AUROC = 0.88 on baseline SD-OCT images of 165 study eyes, with CNV from AVENUE. Conclusions: Our ML model was able to detect CNV presence and CNV subtypes on SD-OCT images with high accuracy in patients with neovascular AMD. View Full-Text
Keywords: age-related macular degeneration; choroidal neovascularization; classification; machine learning; optical coherence tomography age-related macular degeneration; choroidal neovascularization; classification; machine learning; optical coherence tomography
Show Figures

Figure 1

MDPI and ACS Style

Maunz, A.; Benmansour, F.; Li, Y.; Albrecht, T.; Zhang, Y.-P.; Arcadu, F.; Zheng, Y.; Madhusudhan, S.; Sahni, J. Accuracy of a Machine-Learning Algorithm for Detecting and Classifying Choroidal Neovascularization on Spectral-Domain Optical Coherence Tomography. J. Pers. Med. 2021, 11, 524. https://doi.org/10.3390/jpm11060524

AMA Style

Maunz A, Benmansour F, Li Y, Albrecht T, Zhang Y-P, Arcadu F, Zheng Y, Madhusudhan S, Sahni J. Accuracy of a Machine-Learning Algorithm for Detecting and Classifying Choroidal Neovascularization on Spectral-Domain Optical Coherence Tomography. Journal of Personalized Medicine. 2021; 11(6):524. https://doi.org/10.3390/jpm11060524

Chicago/Turabian Style

Maunz, Andreas, Fethallah Benmansour, Yvonna Li, Thomas Albrecht, Yan-Ping Zhang, Filippo Arcadu, Yalin Zheng, Savita Madhusudhan, and Jayashree Sahni. 2021. "Accuracy of a Machine-Learning Algorithm for Detecting and Classifying Choroidal Neovascularization on Spectral-Domain Optical Coherence Tomography" Journal of Personalized Medicine 11, no. 6: 524. https://doi.org/10.3390/jpm11060524

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop