Multi-modal, multi-task, multi-attention (M3) deep learning detection of reticular pseudodrusen: towards automated and accessible classification of age-related macular degeneration Qingyu Chen, PhD 1 *, Tiarnan D. L. Keenan, BM BCh, PhD 2 *, Alexis Allot, PhD 1 , Yifan Peng, PhD 1 , Elvira Agrón, MA 2 , Amitha Domalpally, MD, PhD 3 , Caroline C. W. Klaver, MD, PhD 4 , Daniel T. Luttikhuizen 4 , Marcus H. Colyer, MD 5 , Catherine A. Cukras, MD, PhD 2 , Henry E. Wiley, MD 2 , M. Teresa Magone, MD 2 , Chantal Cousineau-Krieger, MD 2 , Wai T. Wong MD, PhD 2,6 , Yingying Zhu 7,8 , PhD Emily Y. Chew, MD 2† , Zhiyong Lu, PhD 1† , for the AREDS2 Deep Learning Research Group 9 1. National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health (NIH), Bethesda, MD, USA 2. Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, MD, USA 3. Fundus Photograph Reading Center, University of Wisconsin, Madison, WI, USA 4. Department of Ophthalmology, Erasmus Medical Center, Rotterdam, Netherlands 5. Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD, USA 6. Section on Neuron-Glia Interactions in Retinal Disease, Laboratory of Retinal Cell and Molecular Biology, National Eye Institute, National Institutes of Health, Bethesda, MD, USA 7. Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, USA 8. Department of Radiology, Clinical Center, National Institutes of Health, Bethesda, MD, USA 9. See appendix * These authors contributed equally to this work † To whom correspondence should be addressed: echew@nei.nih.gov; zhiyong.lu@nih.gov