Michael D. Abramoff, MD, PhD

Pioneering scientist, physician, and entrepreneur on a mission to end blindness with artificial intelligence

 

Dr. Michael Abramoff, MD, PhD, is an internationally renowned physician scientist and fellowship-trained retina specialist. For the past 20 years, Dr. Abramoff has studied how Artificial Intelligence (AI) can be used to detect disease in medical images. He is the author of over 300 peer-reviewed publications that have been cited over 22,000 times, and the inventor of over 16 issued patents and patent applications.

Dr. Abramoff’s research has largely focused on assessing the performance of smart cameras enhanced with AI algorithms to detect signs of diabetic retinopathy. His findings led him to patent this technology and found a company, IDx, to bring patients a more accessible and affordable solution for the early detection of diabetic retinopathy.

"I am a retinal specialist" – a physician who specialized in ophthalmology and who then did a fellowship in vitreoretinal surgery – who still treats patients with retinal diseases one day a week. He is also a machine learning and image analysis expert, with a Master’s in information technology with minor in Artificial Intelligence, and a PhD in image analysis – both Jan Koenderink and Max Viergever were advisors. Between 1989-1990 he did a postdoc in Tokyo Japan at the RIKEN neural networks research lab. He has published over 300 peer-reviewed publications (h-index 53) on AI, image analysis, and the retina, is past Editor of IEEE TMI and IOVS, and editor of Nature Scientific Reports.

RELATED WEB SITES

Discussing 3-dimensional organization of the retina

PRESENTATIONS

MEDIA COVERAGE

PUBLICATIONS


Selected Honors and Awards

  • 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

Comments by Residents regarding Dr. Abramoff

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."
Evolution of a physician-scientist

Datasets and Algorithms

Locations of where the Iowa Reference Algorithms are being usedImageJ

  • M.D. Abràmoff, P.J. Magelhaes, S.J. Ram, Image Processing with ImageJ. Biophotonics International, 11(7):36-42, 2004; over 7500 citations!

Messidor

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.)
  • 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

  • Dr. AbramoffAbramoff, 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."