Sina Farsiu1, Stephanie J Chiu2, Rachelle V O'Connell3, Francisco A Folgar3, Eric Yuan3, Joseph A Izatt4, Cynthia A Toth4. 1. Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina; Department of Biomedical Engineering, Duke University, Durham, North Carolina; Department of Electrical & Computer Engineering, Duke University, Durham, North Carolina. Electronic address: sina.farsiu@duke.edu. 2. Department of Biomedical Engineering, Duke University, Durham, North Carolina. 3. Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina. 4. Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina; Department of Biomedical Engineering, Duke University, Durham, North Carolina.
Abstract
OBJECTIVE: To define quantitative indicators for the presence of intermediate age-related macular degeneration (AMD) via spectral-domain optical coherence tomography (SD-OCT) imaging of older adults. DESIGN: Evaluation of diagnostic test and technology. PARTICIPANTS AND CONTROLS: One eye from 115 elderly subjects without AMD and 269 subjects with intermediate AMD from the Age-Related Eye Disease Study 2 (AREDS2) Ancillary SD-OCT Study. METHODS: We semiautomatically delineated the retinal pigment epithelium (RPE) and RPE drusen complex (RPEDC, the axial distance from the apex of the drusen and RPE layer to Bruch's membrane) and total retina (TR, the axial distance between the inner limiting and Bruch's membranes) boundaries. We registered and averaged the thickness maps from control subjects to generate a map of "normal" non-AMD thickness. We considered RPEDC thicknesses larger or smaller than 3 standard deviations from the mean as abnormal, indicating drusen or geographic atrophy (GA), respectively. We measured TR volumes, RPEDC volumes, and abnormal RPEDC thickening and thinning volumes for each subject. By using different combinations of these 4 disease indicators, we designed 5 automated classifiers for the presence of AMD on the basis of the generalized linear model regression framework. We trained and evaluated the performance of these classifiers using the leave-one-out method. MAIN OUTCOME MEASURES: The range and topographic distribution of the RPEDC and TR thicknesses in a 5-mm diameter cylinder centered at the fovea. RESULTS: The most efficient method for separating AMD and control eyes required all 4 disease indicators. The area under the curve (AUC) of the receiver operating characteristic (ROC) for this classifier was >0.99. Overall neurosensory retinal thickening in eyes with AMD versus control eyes in our study contrasts with previous smaller studies. CONCLUSIONS: We identified and validated efficient biometrics to distinguish AMD from normal eyes by analyzing the topographic distribution of normal and abnormal RPEDC thicknesses across a large atlas of eyes. We created an online atlas to share the 38 400 SD-OCT images in this study, their corresponding segmentations, and quantitative measurements.
OBJECTIVE: To define quantitative indicators for the presence of intermediate age-related macular degeneration (AMD) via spectral-domain optical coherence tomography (SD-OCT) imaging of older adults. DESIGN: Evaluation of diagnostic test and technology. PARTICIPANTS AND CONTROLS: One eye from 115 elderly subjects without AMD and 269 subjects with intermediate AMD from the Age-Related Eye Disease Study 2 (AREDS2) Ancillary SD-OCT Study. METHODS: We semiautomatically delineated the retinal pigment epithelium (RPE) and RPE drusen complex (RPEDC, the axial distance from the apex of the drusen and RPE layer to Bruch's membrane) and total retina (TR, the axial distance between the inner limiting and Bruch's membranes) boundaries. We registered and averaged the thickness maps from control subjects to generate a map of "normal" non-AMD thickness. We considered RPEDC thicknesses larger or smaller than 3 standard deviations from the mean as abnormal, indicating drusen or geographic atrophy (GA), respectively. We measured TR volumes, RPEDC volumes, and abnormal RPEDC thickening and thinning volumes for each subject. By using different combinations of these 4 disease indicators, we designed 5 automated classifiers for the presence of AMD on the basis of the generalized linear model regression framework. We trained and evaluated the performance of these classifiers using the leave-one-out method. MAIN OUTCOME MEASURES: The range and topographic distribution of the RPEDC and TR thicknesses in a 5-mm diameter cylinder centered at the fovea. RESULTS: The most efficient method for separating AMD and control eyes required all 4 disease indicators. The area under the curve (AUC) of the receiver operating characteristic (ROC) for this classifier was >0.99. Overall neurosensory retinal thickening in eyes with AMD versus control eyes in our study contrasts with previous smaller studies. CONCLUSIONS: We identified and validated efficient biometrics to distinguish AMD from normal eyes by analyzing the topographic distribution of normal and abnormal RPEDC thicknesses across a large atlas of eyes. We created an online atlas to share the 38 400 SD-OCT images in this study, their corresponding segmentations, and quantitative measurements.
Authors: Roy de Kinkelder; Daniel M de Bruin; Frank D Verbraak; Ton G van Leeuwen; Dirk J Faber Journal: J Biophotonics Date: 2012-07-19 Impact factor: 3.207
Authors: Tomas R Burke; David W Rhee; R Theodore Smith; Stephen H Tsang; Rando Allikmets; Stanley Chang; Margot A Lazow; Donald C Hood; Vivienne C Greenstein Journal: Invest Ophthalmol Vis Sci Date: 2011-10-10 Impact factor: 4.799
Authors: Giovanni Gregori; Fenghua Wang; Philip J Rosenfeld; Zohar Yehoshua; Ninel Z Gregori; Brandon J Lujan; Carmen A Puliafito; William J Feuer Journal: Ophthalmology Date: 2011-03-09 Impact factor: 12.079
Authors: Kathrin I Hartmann; Maria L Gomez; Dirk-Uwe G Bartsch; Alexander K Schuster; William R Freeman Journal: Retina Date: 2012-09 Impact factor: 4.256
Authors: Donald C Hood; Christine E Lin; Margot A Lazow; Kirsten G Locke; Xian Zhang; David G Birch Journal: Invest Ophthalmol Vis Sci Date: 2008-11-14 Impact factor: 4.799
Authors: Miao Zhang; Jie Wang; Alex D Pechauer; Thomas S Hwang; Simon S Gao; Liang Liu; Li Liu; Steven T Bailey; David J Wilson; David Huang; Yali Jia Journal: Biomed Opt Express Date: 2015-11-02 Impact factor: 3.732
Authors: Arno P Göbel; Monika Fleckenstein; Tjebo F C Heeren; Frank G Holz; Steffen Schmitz-Valckenberg Journal: Graefes Arch Clin Exp Ophthalmol Date: 2015-04-24 Impact factor: 3.117
Authors: Pratul P Srinivasan; Leo A Kim; Priyatham S Mettu; Scott W Cousins; Grant M Comer; Joseph A Izatt; Sina Farsiu Journal: Biomed Opt Express Date: 2014-09-12 Impact factor: 3.732
Authors: Kerry J Halupka; Bhavna J Antony; Matthew H Lee; Katie A Lucy; Ravneet S Rai; Hiroshi Ishikawa; Gadi Wollstein; Joel S Schuman; Rahil Garnavi Journal: Biomed Opt Express Date: 2018-11-13 Impact factor: 3.732