Pioneering scientist, physician, and entrepreneur on a mission to end blindness with artificial intelligence
- The Robert C. Watzke, MD Professor in Retina Research
- Professor of Ophthalmology and Visual Sciences
- Professor of Electrical and Computer Engineering (ECE)
- Professor of Biomedical Engineering (BME)
Dr. Michael Abramoff, MD, PhD, (FARVO) is the Robert C. Watzke, MD Professor of Ophthalmology and Visual Sciences at the University of Iowa, with a joint appointment in the College of Engineering, a fellowship-trained retina specialist, computer scientist, and entrepreneur. He is an IEEE Fellow, and an ARVO Gold Fellow. In 1989-1990, he did a postdoc at the RIKEN neural networks research lab in Japan. As an expert in machine learning and image analysis, Dr. Abramoff was one of the original developers of a widely-used open-source image analysis app, ImageJ. His research has been continuously funded since 2004 by National Eye Institute, the Veterans Administration, the Beckman Foundation and other federal, state and philanthropic funding agencies in the U.S. and Europe.
Dr. Abramoff is the Founder and Executive Chairman of Digital Diagnostics, the Autonomous AI diagnostics company that was the first in any field of medicine to get FDA clearance for an autonomous AI. In primary care, the AI system can instantaneously diagnose diabetic retinopathy and diabetic macular edema at the point of care. This device, IDX-DR, is now part of ADA’s Standard Diabetes Care and Dr. Abramoff has also developed an ethical foundation for autonomous AI that was used during the design, validation, and regulatory and payment pathways for autonomous AI. As the author of over 300 peer-reviewed publications in this field, he has been cited over 35,000 times, and is the inventor on 17 issued patents and many patent applications. Dr. Abramoff has mentored dozens of engineering graduate students, ophthalmology residents, and retina fellows. His passion is to use AI to improve the affordability, accessibility and quality of care.
RELATED WEBSITES
PRESENTATIONS
MEDIA COVERAGE
PUBLICATIONS
- Researcher ID
- Google Scholar
- ResearchGate
- Spotlighted Publications
- Abràmoff, MD, Lavin, P. T., Birch, M., Shah, N., & Folk, J. C. (2018). Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. Nature Digital Medicine, 1(1), 39. doi:10.1038/s41746-018-0040-6 PMID: 31304320.
- Char DS, Abràmoff MD, Feudtner C. Identifying Ethical Considerations for Machine Learning Healthcare Applications, The American Journal of Bioethics, Oct 2020;20:11, 7-17, DOI: 10.1080/15265161.2020.1819469
- Ting DSW, Carin L, Abràmoff, MD. Observations and Lessons Learned From the Artificial Intelligence Studies for Diabetic Retinopathy Screening. JAMA Ophthalmol. 2019 Jun 13; 137(9):994–995. doi: 10.1001/jamaophthalmol.2019.1997. [Epub ahead of print] PMID: 31194219.
- Worley, S. Big Data, Analytics, and AI in Retina Practice: New tools are harnessing data to increase efficiency, enhance workflow, and ultimately improve patient outcomes. Retinal physician. [Epub] Retinal Physician, Volume: 16, Issue: November/December 2019, page(s): E1-E8. https://www.retinalphysician.com/issues/2019/november-2019/big-data,-analytics,-and-ai-in-retina-practice
- Glaucoma: Building a New Future with AI. The Ophthalmologist. April 22, 2020. https://theophthalmologist.com/subspecialties/glaucoma-building-a-new-future-with-ai
- Artificial Intelligence for Automated Detection of Diabetic Retinopathy in Primary Care [meeting abstract, pdf]. Presented at the meeting of the Macula Society, Thursday, February 22, 2018.
- Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest Ophthalmol Vis Sci. 2016; 57:5200-5206. One of the Top 10 articles cited in IOVS in 2017.
- Diabetic retinopathy is a neurodegenerative disorder. Vision Res 2017;139:101-107. PMID 28408138. DOI: 10.1016/j.visres.2017.03.003
- Simultaneous Multiple Surface Segmentation Using Deep Learning [pdf]. Paper Prepared for the MICCAI conference, 3rd Workshop on Deep Learning in Medical Image Analysis, September 10-14, 2017 in Québec City.
- Optical Coherence Tomography Analysis Based Prediction of Humphrey 24-2 Visual Field Thresholds in Patients with Glaucoma [preprint available]. Invest Ophthalmol Vis Sci. 2017 Aug; 58(10): 3975–3985. doi: 10.1167/iovs.17-21832
- Catastrophic Failure in Image-Based Convolutional Neural Network Algorithms for Detecting Diabetic Retinopathy [ARVO 2017 presentation abstract]
- Hard to find publications
- M.D. Abràmoff, P.J. Magelhaes, S.J. Ram, Image Processing with ImageJ. Biophotonics International, 11(7):36-42, 2004; over 12000 citations!
- The still hard-to-find ultimate review on retinal image analysis: Abràmoff MD, Garvin M, Sonka M., Retinal Imaging and Image Analysis. IEEE Reviews in Biomedical Engineering 3:169-208, 2010
- more publications available on Abramoff's academic profile
Selected Honors and Awards
- Gold Fellow, Association for Research in Vision and Ophthalmology (ARVO)
- University of Iowa Faculty/Staff Start Up of the Year Award
- MedTech Breakthrough Award: Best New Technology Solution - Diabetes Management
- Fellow, Institute of Electrical and Electronics Engineers (IEEE)
- Top 150 Digital Health Companies, CB Insights
- Iowa Biotech Leader Award, America’s Cultivation Corridor
- UI Carver College of Medicine Wall of Scholarship
- Ophthalmologist Top 10 Power list of Inventors
- University of Iowa Research Foundation Discovery and Innovation Award
- Charles D. Phelps Memorial Award for Glaucoma Research, 2016
- Young Investigator Award, Macula Society, 2013
- President’s Innovation Award, American Telemedicine Association, 2011
- PG Binkhorst Award, “Objective Measurement of Motion in the Orbit”, 2013
- McKinsey Inc. for Best Business plan in the Netherlands, 2001
- 3M-Jonkers Award, 2002
- Peter Reichertz Prize for best young researcher, European Federation for Medical Informatics, 1990
Editorials on Abramoff's Work
- The Retinator, Ophthalmology Times 35(13), July 1, 2010
- And the Sequel: Retinator II: Judgment Day? Ophthalmology Times., May 1, 2017
Comments by Residents regarding Dr. Abramoff
- "Excellent teacher."
- "He makes a point to enforce with residents that teaching is his first priority and this shows in how he operates his clinic. He listens to the residents assessments and pushes them to generate their own clinical plan. He integrates evidence and experience in his teaching effortlessly. He is one of the most supportive faculty of the residents, encouraging them to become involved in research and takes time to mentor them along their career path."
- "We are very lucky to have him as a faculty."
- "Great working with Dr. Abramoff. I learned a lot from his guidance in clinic. He has a very good systematic approach to retina that I hope to be able to adopt. I look forward to working with him again next year."
- "It is truly an honor to work with and learn from Dr. Abramoff. I have so enjoyed my time at the VA in the Retina Clinic with him. He provides excellent guidance but also pushes residents to develop our own assessments and plans. He has also been a fabulous instructor for me with lasers."
- "He clearly is dedicated to furthering the field of ophthalmology through all aspects of medicine - research, teaching, and clinical care. I look forward to continue working with him."
- "We're lucky to have him teaching residents and helping to care for our patients."
- "Fun to work with and very knowledgeable."
Datasets and Algorithms
ImageJ
- M.D. Abràmoff, P.J. Magelhaes, S.J. Ram, Image Processing with ImageJ. Biophotonics International, 11(7):36-42, 2004; over 7500 citations!
Messidor
- Messidor-2 dataset as used in Abramoff et al, Automated analysis of retinal images for detection of referable diabetic retinopathy, JAMA Ophthalmol. 2013;131:351-7, and in Abramoff et al, Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning, IOVS. 57:5200-06. One of the Top 10 articles cited in IOVS in 2017.
Retinal Image Analysis
- ROC: Retina Online Challenge – Online competition for the best microaneurysm detection algorithm, with a standardized set of 100 de-identified color images and reference standard. (server problems have disabled some functionality. Datasets may be downloaded from links below.)
- Training images & ground truth (zipped archive ~13Mb)
- Testing Images (zipped archive ~13Mb)
- DRIVE: Digital Retinal Images for Vessel Extraction – Online comparison retinal vessel detection algorithms, with a standardized set of 40 de-identified fovea centered retinal color images and reference standard
- RITE: Retinal Images vessel Tree Extraction – A database that enables comparative studies on segmentation or classification of arteries and veins on retinal images, which is established based on the public available DRIVE database (Digital Retinal Images for Vessel Extraction) (Download RITE datasets)
- DERIVA: Digital Extraction from Retinal Images of Veins and Arteries – Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks. Vinayak S. Joshi, Joseph M. Reinhardt, Mona K. Garvin, Michael D. Abramoff. PlosONE, Nov 2013
- INSPIRE - Iowa Normative Set for Processing Images of the Retina - online set of 30 pairs of de-identified stereo color images of the optic nerve head, with reference standard, based on 3D OCT (INSPIRE DATASETS)
- Associated with our article: Li Tang, Mona K. Garvin, Kyungmoo Lee, Wallace L. M. Alward, Young H. Kwon, Michael D. Abràmoff. Robust Multi-Scale Stereo Matching from Fundus Images with Radiometric Differences. IEEE Transactions on Pattern Analysis and Machine Intelligence (Preprint available here)
- Iowa Reference Algorithm – Analysis and segmentation of retinal and optic nerve head SD-OCT images is now freely available to researchers in the form of the Iowa Reference Algorithm that we developed.
OTHER RESOURCES
PATENTS
- Abramoff, M. D., van Ginneken, B., Niemeijer, M. 7,474,775, "Automatic Detection of Red Lesions in Digital Color Fundus Photographs."
- Abramoff, M. D., Kwon, Y. H. 7,712,898, "Methods and Systems for Optic Nerve Head Segmentation."
- Abramoff, M. D., Quellec, G. U.S. Patent Application Number US 13/992,552, "Optimal, User-Friendly, Object Background Separation in Images."
- Abramoff, M. D., Niemeijer, M., Xu, X., Sonka, M. U.S. Patent Application number US 13/355,386, "Automated determination of arteriovenous ratio in images of blood vessels."
- Abràmoff, M., Tang, L. US Patent Application number 13/980,804, "Systems and Methods for Generating a Three-Dimensional Shape from Stereo Color Images."
- Lee, S., Niemeijer, M., Reinhardt, J., Abramoff, M. D. US Patent number 8,194,936, "Optimal Registration of Multiple Deformed Images Using a Physical Model of the Imaging Distortion."
- Abramoff, M. D., Soliz, P., Russell, S. R. US Patent number 8,340,437, "Methods and Systems for Determining Optimal Features for Classifying Patterns or Objects in Images."
- Wu, X., Garvin, M., Abramoff, M., Sonka, M. US Patent number 8,358,819, "System and methods for image segmentation in N-dimensional space."
- Abràmoff, M. US Patent number 8,616,702, "Hybrid Laser Ophthalmoscope."
- Abràmoff, M., Tang, L., Wu, X. US Provisional Patent Application number 61/968,713, "Graph Search Using Non-Euclidean Deformed Graph."
- Abramoff, M. D., DeHoog, E. US Patent number 9,155,465, "Snapshot spectral domain optical coherence tomographer."
- Abramoff, M. D., Sonka, M. US Patent number 9,545,196, "Automated assessment of glaucoma loss from optical coherence tomography."
- Abramoff, M.D., DeHoog E. US Patent number 9,782,065, "Parallel optical coherence tomography apparatuses, systems, and related methods."
- Abramoff, M.D., Niemeijer, M., Xu, X., Sonka, M., Reinhardt, J.M. US Patent number 9,924,867, "Automated determination of arteriovenous ratio in images of blood vessels."
- Abramoff, M.D., Lee, S., Niemeijer, M., Reinhardt, J.M. US Patent number 8,194,936 B2, "Optimal Registration of Multiple Deformed Images Using a Physical Model of the Imaging Distortion."
- Abramoff, M.D. US Patent number 8.616.702, "Hybrid Laser Ophthalmoscope."
- Abramoff, M.D., Talmage, E., Clark, B., DeHoog, E., Chung, T. US Patent number 9,814,386B2, "Systems and Methods for Alignment of the Eye for Ocular Imaging."
- Abramoff, M.D., Tang, L., Wu, X. US Patent number 10,410,355, "Methods and systems for image analysis using non-Euclidean deformed graphs."
- Niemeijer, M., Amelon, R., Clarida, W., Abramoff, M.D. US Patent number 10,115,194, "Systems and Methods for Feature Detection in retinal Images."
- Abramoff, M.D., Quellec, G. US Patent number 10,140,699, "Optimal, User-Friendly, Object Background Separation in Images."
- Abramoff, M.D., Garvin, M.K., Qiao, H. US Patent number 10,360,672, "Automated Separation of Binary Overlapping Trees."
- Abramoff, M.D., Wu, X. US Patent number 10,783,639, "System and methods for n-dimensional image segmentation using convolutional neural networks."
- Abramoff, M.D., et al. US Patent number 10,694,945, "Systems and methods for alignment of the eye for ocular imaging."