Imperial College London
Portrait Picture

Professor M Francesca Cordeiro

Faculty of Medicine, Department of Surgery & Cancer

Chair in Ophthalmology (Clinical)
 
 
 
//

Contact

 

m.cordeiro

 
 
//

Location

 

Norfolk PlaceSt Mary's Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Corazza:2020:10.1080/14737159.2020.1865806,
author = {Corazza, P and Maddison, J and Bonetti, P and Guo, L and Luong, V and Garfinkel, A and Younis, S and Cordeiro, MF},
doi = {10.1080/14737159.2020.1865806},
journal = {Expert Review of Molecular Diagnostics: new diagnostic technologies are set to revolutionise healthcare},
pages = {109--118},
title = {Predicting wet age-related macular degeneration (AMD) using DARC (detecting apoptosing retinal cells) AI (artificial intelligence) technology},
url = {http://dx.doi.org/10.1080/14737159.2020.1865806},
volume = {21},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - ObjectivesTo assess a recently described CNN (convolutional neural network) DARC (Detection of Apoptosing Retinal Cells) algorithm in predicting new Subretinal Fluid (SRF) formation in Age-related-Macular-Degeneration (AMD).MethodsAnonymized DARC, baseline and serial OCT images (n = 427) from 29 AMD eyes of Phase 2 clinical trial (ISRCTN10751859) were assessed with CNN algorithms, enabling the location of each DARC spot on corresponding OCT slices (n = 20,629). Assessment of DARC in a rabbit model of angiogenesis was performed in parallel.ResultsA CNN DARC count >5 at baseline was significantly (p = 0.0156) related to development of new SRF throughout 36 months. Prediction rate of eyes using unique DARC spots overlying new SRF had positive predictive values, sensitivities and specificities >70%, with DARC count significantly (p < 0.005) related to the magnitude of SRF accumulation at all time points. DARC identified earliest stages of angiogenesis in-vivo.ConclusionsDARC was able to predict new wet-AMD activity. Using only an OCT-CNN definition of new SRF, we demonstrate that DARC can identify early endothelial neovascular activity, as confirmed by rabbit studies. Although larger validation studies are required, this shows the potential of DARC as a biomarker of wet AMD, and potentially saving vision-loss.
AU  - Corazza,P
AU  - Maddison,J
AU  - Bonetti,P
AU  - Guo,L
AU  - Luong,V
AU  - Garfinkel,A
AU  - Younis,S
AU  - Cordeiro,MF
DO  - 10.1080/14737159.2020.1865806
EP  - 118
PY  - 2020///
SN  - 1473-7159
SP  - 109
TI  - Predicting wet age-related macular degeneration (AMD) using DARC (detecting apoptosing retinal cells) AI (artificial intelligence) technology
T2  - Expert Review of Molecular Diagnostics: new diagnostic technologies are set to revolutionise healthcare
UR  - http://dx.doi.org/10.1080/14737159.2020.1865806
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000603779000001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://www.tandfonline.com/doi/full/10.1080/14737159.2020.1865806
UR  - http://hdl.handle.net/10044/1/92053
VL  - 21
ER  -
Download