SPIE Membership Get updates from SPIE Newsroom
  • Newsroom Home
  • Astronomy
  • Biomedical Optics & Medical Imaging
  • Defense & Security
  • Electronic Imaging & Signal Processing
  • Illumination & Displays
  • Lasers & Sources
  • Micro/Nano Lithography
  • Nanotechnology
  • Optical Design & Engineering
  • Optoelectronics & Communications
  • Remote Sensing
  • Sensing & Measurement
  • Solar & Alternative Energy
  • Sign up for Newsroom E-Alerts
  • Information for:
SPIE Photonics West 2019 | Call for Papers

2018 SPIE Optics + Photonics | Register Today



Print PageEmail Page

Biomedical Optics & Medical Imaging

Automated detection of retinal disease: when Moore's law meets Baumol's cost disease

Presented by Michael Abramoff at SPIE Medical Imaging 2012

1 March 2012, SPIE Newsroom. DOI: 10.1117/2.3201202.17

Michael AbramoffOver the last 40 years, health-care expenditures have been outpacing wage increases in all other areas of the economy, around the developed world. While all other sectors of the economy showed consistent productivity gains since at least 1900, physicians' and nurses' productivity has been generally flat. This paradox was first described by W.J. Baumol in 1966, and has since been called Baumol's cost disease.

You are probably more familiar with Moore's law, the doubling of transistor density on integrated circuits every two years, which has led to sustained increases in processing power and memory capacity. Moore's law has resulted in cost-effective productivity increases in most areas of the economy through automation. In health care, however, the introduction of Electronic Health Records, though potentially improving quality of health care, is resulting in lower physician productivity. Computer-aided diagnosis, where the physician is assisted by a computer, may suffer from the same problem. In other words, health-care automation has made physicians maybe do better but not more.

Automated detection of retinal diseases, leveraging Moore's law and sophisticated image-analysis algorithms, can be employed in real time, at the point of care, without requiring a physician, and has been shown to outperform retinal specialists on several measures. Thus, for example to prevent blindness in the 300 million people with diabetes around the world at risk for diabetic retinopathy, automated detection seems an obvious choice.

Michael D. Abramoff, M.D., is Associate Professor of Ophthalmology and Visual Sciences with joint appointments in Electrical and Computer Engineering and Biomedical Engineering at the University of Iowa, Iowa City. He is a fellowship trained retinal specialist (MD, University of Amsterdam, Netherlands) with a PhD in image analysis in ophthalmology (University of Utrecht, The Netherlands). He serves on the American Academy of Ophthalmology and the Iowa Medical Society, and is Associate Editor of IEEE TMI. When he is not seeing patients with retinal disease or teaching medical students, graduate students, postdocs, residents and fellows, he oversees a highly successful retinal image analysis research program. His focus is on automated early detection of retinal diseases, image-guided therapy of retinal disease, and computational phenotype-genotype association discovery. He has over 130 publications, seven patents and patent applications in this field, and is founder of the EyeCheck and Iowa Retinal Telediagnosis projects, as well as IDx LLC.