Share Email Print
cover

Proceedings Paper

Fully automated disease severity assessment and treatment monitoring in retinopathy of prematurity using deep learning
Author(s): James M. Brown; J. Peter Campbell; Andrew Beers; Ken Chang; Kyra Donohue; Susan Ostmo; R. V. Paul Chan; Jennifer Dy; Deniz Erdogmus; Stratis Ioannidis; Michael F. Chiang; Jayashree Kalpathy-Cramer
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Retinopathy of prematurity (ROP) is a disease that affects premature infants, where abnormal growth of the retinal blood vessels can lead to blindness unless treated accordingly. Infants considered at risk of severe ROP are monitored for symptoms of plus disease, characterized by arterial tortuosity and venous dilation at the posterior pole, with a standard photographic definition. Disagreement among ROP experts in diagnosing plus disease has driven the development of computer-based methods that classify images based on hand-crafted features extracted from the vasculature. However, most of these approaches are semi-automated, which are time-consuming and subject to variability. In contrast, deep learning is a fully automated approach that has shown great promise in a wide variety of domains, including medical genetics, informatics and imaging. Convolutional neural networks (CNNs) are deep networks which learn rich representations of disease features that are highly robust to variations in acquisition and image quality. In this study, we utilized a U-Net architecture to perform vessel segmentation and then a GoogLeNet to perform disease classification. The classifier was trained on 3,000 retinal images and validated on an independent test set of patients with different observed progressions and treatments. We show that our fully automated algorithm can be used to monitor the progression of plus disease over multiple patient visits with results that are consistent with the experts’ consensus diagnosis. Future work will aim to further validate the method on larger cohorts of patients to assess its applicability within the clinic as a treatment monitoring tool.

Paper Details

Date Published: 6 March 2018
PDF: 7 pages
Proc. SPIE 10579, Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, 105790Q (6 March 2018); doi: 10.1117/12.2295942
Show Author Affiliations
James M. Brown, Athinoula A. Martinos Ctr. for Biomedical Imaging (United States)
J. Peter Campbell, Oregon Health & Science Univ. (United States)
Andrew Beers, Athinoula A. Martinos Ctr. for Biomedical Imaging (United States)
Ken Chang, Athinoula A. Martinos Ctr. for Biomedical Imaging (United States)
Kyra Donohue, Athinoula A. Martinos Ctr. for Biomedical Imaging (United States)
Susan Ostmo, Oregon Health & Science Univ. (United States)
R. V. Paul Chan, Univ. of Illinois at Chicago (United States)
Jennifer Dy, Northeastern Univ. (United States)
Deniz Erdogmus, Northeastern Univ. (United States)
Stratis Ioannidis, Northeastern Univ. (United States)
Michael F. Chiang, Oregon Health & Science Univ. (United States)
Jayashree Kalpathy-Cramer, Athinoula A. Martinos Ctr. for Biomedical Imaging (United States)
Massachusetts General Hospital & Brigham and Women's Hospital Ctr. for Clinical Data Science (United States)


Published in SPIE Proceedings Vol. 10579:
Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications
Jianguo Zhang; Po-Hao Chen, Editor(s)

© SPIE. Terms of Use
Back to Top