Abstract
Retinopathy of prematurity (ROP) is a disease affecting low-birth weight infants and is a major cause of childhood blindness. However, human diagnoses is often subjective and qualitative. We propose a method to analyze the variability of expert decisions and the relationship between the expert diagnoses and features. The analysis is based on Mutual Information and Kernel Density Estimation on features. The experiments are carried out on a dataset of 34 retinal images diagnosed by 22 experts. The results show that a group of observers decide consistently with each other and there are popular features that have a high correlation with labels.
| Original language | English (US) |
|---|---|
| Title of host publication | IEEE International Workshop on Machine Learning for Signal Processing, MLSP |
| DOIs | |
| State | Published - 2012 |
| Event | 2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012 - Santander, Spain Duration: Sep 23 2012 → Sep 26 2012 |
Other
| Other | 2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012 |
|---|---|
| Country | Spain |
| City | Santander |
| Period | 9/23/12 → 9/26/12 |
Fingerprint
Keywords
- feature selection
- observer analysis
- retinal image analysis
ASJC Scopus subject areas
- Human-Computer Interaction
- Signal Processing
Cite this
Observer and feature analysis on diagnosis of retinopathy of prematurity. / Ataer-Cansizoglu, E.; You, S.; Kalpathy-Cramer, Jayashree; Keck, K.; Chiang, Michael; Erdogmus, D.
IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2012. 6349809.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Observer and feature analysis on diagnosis of retinopathy of prematurity
AU - Ataer-Cansizoglu, E.
AU - You, S.
AU - Kalpathy-Cramer, Jayashree
AU - Keck, K.
AU - Chiang, Michael
AU - Erdogmus, D.
PY - 2012
Y1 - 2012
N2 - Retinopathy of prematurity (ROP) is a disease affecting low-birth weight infants and is a major cause of childhood blindness. However, human diagnoses is often subjective and qualitative. We propose a method to analyze the variability of expert decisions and the relationship between the expert diagnoses and features. The analysis is based on Mutual Information and Kernel Density Estimation on features. The experiments are carried out on a dataset of 34 retinal images diagnosed by 22 experts. The results show that a group of observers decide consistently with each other and there are popular features that have a high correlation with labels.
AB - Retinopathy of prematurity (ROP) is a disease affecting low-birth weight infants and is a major cause of childhood blindness. However, human diagnoses is often subjective and qualitative. We propose a method to analyze the variability of expert decisions and the relationship between the expert diagnoses and features. The analysis is based on Mutual Information and Kernel Density Estimation on features. The experiments are carried out on a dataset of 34 retinal images diagnosed by 22 experts. The results show that a group of observers decide consistently with each other and there are popular features that have a high correlation with labels.
KW - feature selection
KW - observer analysis
KW - retinal image analysis
UR - http://www.scopus.com/inward/record.url?scp=84870678072&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84870678072&partnerID=8YFLogxK
U2 - 10.1109/MLSP.2012.6349809
DO - 10.1109/MLSP.2012.6349809
M3 - Conference contribution
AN - SCOPUS:84870678072
SN - 9781467310260
BT - IEEE International Workshop on Machine Learning for Signal Processing, MLSP
ER -