Purchase this article with an account.
Hrvoje Bogunovic, Alessio Montuoro, Magdalena Baratsits, Maria Karantonis, Sebastian M Waldstein, Ferdinand Georg Schlanitz, Ursula Schmidt-Erfurth; Personalized Prognosis in Early/Intermediate Age-Related Macular Degeneration based on Drusen Regression. Invest. Ophthalmol. Vis. Sci. 2017;58(8):15.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
The presence of drusen is the hallmark of early/intermediate age-related macular degeneration (AMD), and their sudden regression is strongly associated with the onset of late AMD. In this work, we develop and evaluate a machine learning algorithm to predict individual drusen regression using optical coherence tomography (OCT) based biomarkers.
Patients with early/intermediate AMD were followed in a standardized manner every 3 months for a minimum of 15 months. Imaging was performed using Spectralis OCT (scanning area 20°x20°, volume scan 1024x97x496 voxels). Segmentation of retinal layers was obtained using a graph-theoretic approach (Iowa Reference Algorithms). Layer segmentation errors in the outer retina were corrected by an expert reader. In addition, hyperreflective foci (HRF) were segmented by voxel classification. Then a series of automated image analysis steps were applied to identify and characterize individual drusen and their development from baseline to the next follow-up (month 3). The point of regression of each druse was determined algorithmically as a time-point when its volume fell below 10% of the baseline value. Finally, a machine learning algorithm based on random forest was employed to predict the occurrence of drusen regression within the subsequent 12 months (Figure 1).
The predictive model was trained and evaluated on a longitudinal OCT dataset of 61 eyes from 38 patients using leave-one-patient-out cross-validation. A total of 938 drusen were identified, out of which 71 regressed (7.6%) during follow-up. The prediction performance was quantitatively evaluated as area under the curve (AUC). Detection of individual drusen regression within 12 months achieved an AUC = 0.76, corresponding to a sensitivity of 0.73 and a specificity of 0.70. The presence of HRF was found to be an important biomarker for incoming drusen regression.
The predictive model proposed in this pilot study represents a promising step toward image-guided prediction of AMD progression. Machine learning will substantially contribute to the development of new therapeutics that target slowing the progression of early/intermediate AMD.
This is an abstract that was submitted for the 2017 ARVO Annual Meeting, held in Baltimore, MD, May 7-11, 2017.
Example case. (a) Maps of drusen thickness measured across time. (b) Drusen map at baseline with the drusen found to be regressing within 15 months marked in red, with the prediction error in blue.
This PDF is available to Subscribers Only