BACKGROUND: A key objective in glaucoma is to identify those at risk of rapid progression and blindness. Recently, a novel first-in-man method for visualising apoptotic retinal cells called DARC (Detection-of-Apoptosing-Retinal-Cells) was reported. The aim was to develop an automatic CNN-aided method of DARC spot detection to enable prediction of glaucoma progression. METHODS: Anonymised DARC images were acquired from healthy control (n=40) and glaucoma (n=20) Phase 2 clinical trial subjects (ISRCTN10751859) from which 5 observers manually counted spots. The CNN-aided algorithm was trained and validated using manual counts from control subjects, and then tested on glaucoma eyes. RESULTS: The algorithm had 97.0% accuracy, 91.1% sensitivity and 97.1% specificity to spot detection when compared to manual grading of 50% controls. It was next tested on glaucoma patient eyes defined as progressing or stable based on a significant (p<0.05) rate of progression using OCT-retinal nerve fibre layer measurements at 18 months. It demonstrated 85.7% sensitivity, 91.7% specificity with AUC of 0.89, and a significantly (p=0.0044) greater DARC count in those patients who later progressed. CONCLUSION: This CNN-enabled algorithm provides an automated and objective measure of DARC, promoting its use as an AI-aided biomarker for predicting glaucoma progression and testing new drugs.
BACKGROUND: A key objective in glaucoma is to identify those at risk of rapid progression and blindness. Recently, a novel first-in-man method for visualising apoptotic retinal cells called DARC (Detection-of-Apoptosing-Retinal-Cells) was reported. The aim was to develop an automatic CNN-aided method of DARC spot detection to enable prediction of glaucoma progression. METHODS: Anonymised DARC images were acquired from healthy control (n=40) and glaucoma (n=20) Phase 2 clinical trial subjects (ISRCTN10751859) from which 5 observers manually counted spots. The CNN-aided algorithm was trained and validated using manual counts from control subjects, and then tested on glaucoma eyes. RESULTS: The algorithm had 97.0% accuracy, 91.1% sensitivity and 97.1% specificity to spot detection when compared to manual grading of 50% controls. It was next tested on glaucomapatient eyes defined as progressing or stable based on a significant (p<0.05) rate of progression using OCT-retinal nerve fibre layer measurements at 18 months. It demonstrated 85.7% sensitivity, 91.7% specificity with AUC of 0.89, and a significantly (p=0.0044) greater DARC count in those patients who later progressed. CONCLUSION: This CNN-enabled algorithm provides an automated and objective measure of DARC, promoting its use as an AI-aided biomarker for predicting glaucoma progression and testing new drugs.
Authors: Sebastián A Banegas; Alfonso Antón; Antonio Morilla-Grasa; Marco Bogado; Eleonora M Ayala; Javier Moreno-Montañes Journal: Invest Ophthalmol Vis Sci Date: 2015-01-27 Impact factor: 4.799
Authors: Donald L Budenz; Douglas R Anderson; William J Feuer; Julia A Beiser; Joyce Schiffman; Richard K Parrish; Jody R Piltz-Seymour; Mae O Gordon; Michael A Kass Journal: Ophthalmology Date: 2006-09-25 Impact factor: 12.079
Authors: A C Viswanathan; D P Crabb; A I McNaught; M C Westcott; D Kamal; D F Garway-Heath; F W Fitzke; R A Hitchings Journal: Br J Ophthalmol Date: 2003-06 Impact factor: 4.638
Authors: Yih-Chung Tham; Xiang Li; Tien Y Wong; Harry A Quigley; Tin Aung; Ching-Yu Cheng Journal: Ophthalmology Date: 2014-06-26 Impact factor: 12.079
Authors: Ryan Poplin; Avinash V Varadarajan; Katy Blumer; Yun Liu; Michael V McConnell; Greg S Corrado; Lily Peng; Dale R Webster Journal: Nat Biomed Eng Date: 2018-02-19 Impact factor: 25.671
Authors: Ian J C MacCormick; Bryan M Williams; Yalin Zheng; Kun Li; Baidaa Al-Bander; Silvester Czanner; Rob Cheeseman; Colin E Willoughby; Emery N Brown; George L Spaeth; Gabriela Czanner Journal: PLoS One Date: 2019-01-10 Impact factor: 3.240
Authors: Po-Hsin Chou; Tsair-Wei Chien; Ting-Ya Yang; Yu-Tsen Yeh; Willy Chou; Chao-Hung Yeh Journal: Int J Environ Res Public Health Date: 2021-04-16 Impact factor: 3.390
Authors: Paolo Corazza; John Maddison; Paolo Bonetti; Li Guo; Vy Luong; Alan Garfinkel; Saad Younis; Maria Francesca Cordeiro Journal: Expert Rev Mol Diagn Date: 2020-12-28 Impact factor: 5.225
Authors: Peter J Snyder; Jessica Alber; Clemens Alt; Lisa J Bain; Brett E Bouma; Femke H Bouwman; Delia Cabrera DeBuc; Melanie C W Campbell; Maria C Carrillo; Emily Y Chew; M Francesca Cordeiro; Michael R Dueñas; Brian M Fernández; Maya Koronyo-Hamaoui; Chiara La Morgia; Roxana O' Carare; Srinivas R Sadda; Peter van Wijngaarden; Heather M Snyder Journal: Alzheimers Dement Date: 2020-10-08 Impact factor: 21.566