Toward a severity index for ROP

An unsupervised approach

Peng Tian, Esra Ataer-Cansizoglu, Jayashree Kalpathy-Cramer, Susan Ostmo, Karyn Jonas, R. V Paul Chan, John Campbell, Michael Chiang, Deniz Erdogmus

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Retinopathy of prematurity (ROP) is a disease affecting low birth-weight infants and is the major cause of childhood blindness. Although accurate diagnosis is important, there is a high variability among expert decisions mostly due to subjective thresholds. Existing work focused on automated diagnosis of ROP. In this study, we construct a continuous severity index as an alternative to discrete classification. We follow an unsupervised approach by performing nonlinear dimensionality reduction. Instead of extracting several statistics of image features, each image is represented by the probability distribution of its features. The distance between distributions are then used in manifold learning methods as the distance between samples. The experiments are carried out on a dataset of 104 wide-angle retinal images. The results are promising and they reflect the challenges of the discrete classification.

Original languageEnglish (US)
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1312-1315
Number of pages4
Volume2016-October
ISBN (Electronic)9781457702204
DOIs
StatePublished - Oct 13 2016
Event38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States
Duration: Aug 16 2016Aug 20 2016

Other

Other38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
CountryUnited States
CityOrlando
Period8/16/168/20/16

Fingerprint

Retinopathy of Prematurity
Low Birth Weight Infant
Blindness
Probability distributions
Statistics
Learning
Experiments
Datasets

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Tian, P., Ataer-Cansizoglu, E., Kalpathy-Cramer, J., Ostmo, S., Jonas, K., Chan, R. V. P., ... Erdogmus, D. (2016). Toward a severity index for ROP: An unsupervised approach. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 (Vol. 2016-October, pp. 1312-1315). [7590948] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2016.7590948

Toward a severity index for ROP : An unsupervised approach. / Tian, Peng; Ataer-Cansizoglu, Esra; Kalpathy-Cramer, Jayashree; Ostmo, Susan; Jonas, Karyn; Chan, R. V Paul; Campbell, John; Chiang, Michael; Erdogmus, Deniz.

2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 1312-1315 7590948.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tian, P, Ataer-Cansizoglu, E, Kalpathy-Cramer, J, Ostmo, S, Jonas, K, Chan, RVP, Campbell, J, Chiang, M & Erdogmus, D 2016, Toward a severity index for ROP: An unsupervised approach. in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. vol. 2016-October, 7590948, Institute of Electrical and Electronics Engineers Inc., pp. 1312-1315, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016, Orlando, United States, 8/16/16. https://doi.org/10.1109/EMBC.2016.7590948
Tian P, Ataer-Cansizoglu E, Kalpathy-Cramer J, Ostmo S, Jonas K, Chan RVP et al. Toward a severity index for ROP: An unsupervised approach. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1312-1315. 7590948 https://doi.org/10.1109/EMBC.2016.7590948
Tian, Peng ; Ataer-Cansizoglu, Esra ; Kalpathy-Cramer, Jayashree ; Ostmo, Susan ; Jonas, Karyn ; Chan, R. V Paul ; Campbell, John ; Chiang, Michael ; Erdogmus, Deniz. / Toward a severity index for ROP : An unsupervised approach. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1312-1315
@inproceedings{3da03bbab0ce4f5098166c02af9ea94a,
title = "Toward a severity index for ROP: An unsupervised approach",
abstract = "Retinopathy of prematurity (ROP) is a disease affecting low birth-weight infants and is the major cause of childhood blindness. Although accurate diagnosis is important, there is a high variability among expert decisions mostly due to subjective thresholds. Existing work focused on automated diagnosis of ROP. In this study, we construct a continuous severity index as an alternative to discrete classification. We follow an unsupervised approach by performing nonlinear dimensionality reduction. Instead of extracting several statistics of image features, each image is represented by the probability distribution of its features. The distance between distributions are then used in manifold learning methods as the distance between samples. The experiments are carried out on a dataset of 104 wide-angle retinal images. The results are promising and they reflect the challenges of the discrete classification.",
author = "Peng Tian and Esra Ataer-Cansizoglu and Jayashree Kalpathy-Cramer and Susan Ostmo and Karyn Jonas and Chan, {R. V Paul} and John Campbell and Michael Chiang and Deniz Erdogmus",
year = "2016",
month = "10",
day = "13",
doi = "10.1109/EMBC.2016.7590948",
language = "English (US)",
volume = "2016-October",
pages = "1312--1315",
booktitle = "2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Toward a severity index for ROP

T2 - An unsupervised approach

AU - Tian, Peng

AU - Ataer-Cansizoglu, Esra

AU - Kalpathy-Cramer, Jayashree

AU - Ostmo, Susan

AU - Jonas, Karyn

AU - Chan, R. V Paul

AU - Campbell, John

AU - Chiang, Michael

AU - Erdogmus, Deniz

PY - 2016/10/13

Y1 - 2016/10/13

N2 - Retinopathy of prematurity (ROP) is a disease affecting low birth-weight infants and is the major cause of childhood blindness. Although accurate diagnosis is important, there is a high variability among expert decisions mostly due to subjective thresholds. Existing work focused on automated diagnosis of ROP. In this study, we construct a continuous severity index as an alternative to discrete classification. We follow an unsupervised approach by performing nonlinear dimensionality reduction. Instead of extracting several statistics of image features, each image is represented by the probability distribution of its features. The distance between distributions are then used in manifold learning methods as the distance between samples. The experiments are carried out on a dataset of 104 wide-angle retinal images. The results are promising and they reflect the challenges of the discrete classification.

AB - Retinopathy of prematurity (ROP) is a disease affecting low birth-weight infants and is the major cause of childhood blindness. Although accurate diagnosis is important, there is a high variability among expert decisions mostly due to subjective thresholds. Existing work focused on automated diagnosis of ROP. In this study, we construct a continuous severity index as an alternative to discrete classification. We follow an unsupervised approach by performing nonlinear dimensionality reduction. Instead of extracting several statistics of image features, each image is represented by the probability distribution of its features. The distance between distributions are then used in manifold learning methods as the distance between samples. The experiments are carried out on a dataset of 104 wide-angle retinal images. The results are promising and they reflect the challenges of the discrete classification.

UR - http://www.scopus.com/inward/record.url?scp=85009152936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009152936&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2016.7590948

DO - 10.1109/EMBC.2016.7590948

M3 - Conference contribution

VL - 2016-October

SP - 1312

EP - 1315

BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -