Zhichao Wu1, Hrvoje Bogunović2, Rhona Asgari2, Ursula Schmidt-Erfurth2, Robyn H Guymer3. 1. Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia; Ophthalmology, Department of Surgery, The University of Melbourne, Melbourne, Australia. Electronic address: wu.z@unimelb.edu.au. 2. Department of Ophthalmology and Optometry, Christian Doppler Laboratory for Ophthalmic Image Analyses, Medical University of Vienna, Vienna, Austria. 3. Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia; Ophthalmology, Department of Surgery, The University of Melbourne, Melbourne, Australia.
Abstract
PURPOSE: To compare the performance of automatically quantified OCT imaging biomarkers and conventional risk factors manually graded on color fundus photographs for predicting progression to late age-related macular degeneration (AMD). DESIGN: Longitudinal observational study. PARTICIPANTS: Two hundred eighty eyes from 140 participants with bilateral large drusen. METHODS: All participants underwent OCT and color fundus photography (CFP) at baseline and were then reviewed at 6-month intervals to determine progression to late AMD. Color fundus photographs were graded manually and OCT scans underwent automated image analyses to quantify risk factors and imaging biomarkers, respectively, based on drusen and AMD pigmentary abnormalities. Four predictive models for progression to late AMD or atrophic AMD were only developed (each including age) based on: (1) CFP only (2 parameters); (2) OCT biomarkers, minimal (3 parameters); (3) OCT biomarkers, extended (7 parameters); and (4) CFP and OCT combined (8 parameters). MAIN OUTCOME MEASURES: Predictive performance for progression to late AMD, examined based on the area under the receiver operating characteristic curve (AUC) for correctly predicting progression. RESULTS: The AUC for predicting late AMD development was similar for the models based on CFP alone (model 1; 0.80), OCT alone (models 2 and 3; 0.82 for both), and when using both methods together (model 4; 0.85). In addition, these models also performed similarly for predicting the end point of atrophic AMD only (AUC, 0.83, 0.84, 0.85, and 0.88 for models 1, 2, 3, and 4, respectively). CONCLUSIONS: OCT imaging biomarkers could provide an automatic method of risk stratification for progression to vision-threatening late AMD as well as manual grading of CFP.
PURPOSE: To compare the performance of automatically quantified OCT imaging biomarkers and conventional risk factors manually graded on color fundus photographs for predicting progression to late age-related macular degeneration (AMD). DESIGN: Longitudinal observational study. PARTICIPANTS: Two hundred eighty eyes from 140 participants with bilateral large drusen. METHODS: All participants underwent OCT and color fundus photography (CFP) at baseline and were then reviewed at 6-month intervals to determine progression to late AMD. Color fundus photographs were graded manually and OCT scans underwent automated image analyses to quantify risk factors and imaging biomarkers, respectively, based on drusen and AMD pigmentary abnormalities. Four predictive models for progression to late AMD or atrophic AMD were only developed (each including age) based on: (1) CFP only (2 parameters); (2) OCT biomarkers, minimal (3 parameters); (3) OCT biomarkers, extended (7 parameters); and (4) CFP and OCT combined (8 parameters). MAIN OUTCOME MEASURES: Predictive performance for progression to late AMD, examined based on the area under the receiver operating characteristic curve (AUC) for correctly predicting progression. RESULTS: The AUC for predicting late AMD development was similar for the models based on CFP alone (model 1; 0.80), OCT alone (models 2 and 3; 0.82 for both), and when using both methods together (model 4; 0.85). In addition, these models also performed similarly for predicting the end point of atrophic AMD only (AUC, 0.83, 0.84, 0.85, and 0.88 for models 1, 2, 3, and 4, respectively). CONCLUSIONS: OCT imaging biomarkers could provide an automatic method of risk stratification for progression to vision-threatening late AMD as well as manual grading of CFP.
Authors: Kathleen Romond; Minhaj Alam; Sasha Kravets; Luis de Sisternes; Theodore Leng; Jennifer I Lim; Daniel Rubin; Joelle A Hallak Journal: Exp Biol Med (Maywood) Date: 2021-08-18
Authors: Divya Narayanan; Garrick Wallstrom; John Rodriguez; Donna Welch; Matthew Chapin; Paul Arrigg; Rajkumar Patil; Mark Abelson Journal: Clin Ophthalmol Date: 2020-09-03