Share Email Print

Proceedings Paper

Transfer learning for diabetic retinopathy
Author(s): Jeremy Benson; Hector Carrillo; Jeff Wigdahl; Sheila Nemeth; John Maynard; Gilberto Zamora; Simon Barriga; Trilce Estrada; Peter Soliz
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Diabetic Retinopathy (DR)1, 2 is a leading cause of blindness worldwide and is estimated to threaten the vision of nearly 200 million by 2030.3 To work with the ever-increasing population, the use of image processing algorithms to screen for those at risk has been on the rise. Research-oriented solutions have proven effective in classifying images with or without DR, but often fail to address the true need of the clinic - referring only those who need to be seen by a specialist, and reading every single case. In this work, we leverage an array of image pre-preprocessing techniques, as well as Transfer Learning to re-purpose an existing deep network for our tasks in DR. We train, test, and validate our system on 979 clinical cases, achieving a 95% Area Under the Curve (AUC) for referring Severe DR with an equal error Sensitivity and Specificity of 90%. Our system does not reject any images based on their quality, and is agnostic in terms of eye side and field. These results show that general purpose classifiers can, with the right type of input, have a major impact in clinical environments or for teams lacking access to large volumes of data or high-throughput supercomputers.

Paper Details

Date Published: 2 March 2018
PDF: 9 pages
Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105741Z (2 March 2018); doi: 10.1117/12.2293378
Show Author Affiliations
Jeremy Benson, VisionQuest Biomedical LLC (United States)
The Univ. of New Mexico (United States)
Hector Carrillo, VisionQuest Biomedical LLC (United States)
The Univ. of New Mexico (United States)
Jeff Wigdahl, VisionQuest Biomedical LLC (United States)
Sheila Nemeth, VisionQuest Biomedical LLC (United States)
John Maynard, VisionQuest Biomedical LLC (United States)
Gilberto Zamora, VisionQuest Biomedical LLC (United States)
Simon Barriga, VisionQuest Biomedical LLC (United States)
Trilce Estrada, The Univ. of New Mexico (United States)
Peter Soliz, VisionQuest Biomedical LLC (United States)

Published in SPIE Proceedings Vol. 10574:
Medical Imaging 2018: Image Processing
Elsa D. Angelini; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top