Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation

Peng Tian; Jennifer Dy; Deniz Erdogmus; Susan Ostmo; J. Peter Peter Campbell; Michael F.F. Chiang; Stratis Ioannidis

doi:10.1145/3453892.3454002

Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation

Peng Tian, Jennifer Dy, Deniz Erdogmus, Susan Ostmo, J. Peter Peter Campbell, Michael F.F. Chiang, Stratis Ioannidis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Retinopathy of Prematurity (ROP) is a disease affecting premature infants and may lead to childhood blindness. Due to lack of trained ophthalmologists, developing a fully automated ROP diagnostic system can significantly benefit the infants affected by ROP. Based on manually segmented features, previous work produces severity scores for ROP with excellent prediction accuracy. However, when automated segmentation employed, a significant accuracy drop is observed. In this paper, we show that U-Net segmentation, which is automated, comes at no accuracy loss.

Original language	English (US)
Title of host publication	14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021
Publisher	Association for Computing Machinery
Pages	33-36
Number of pages	4
ISBN (Electronic)	9781450387927
DOIs	https://doi.org/10.1145/3453892.3454002
State	Published - Jun 29 2021
Externally published	Yes
Event	14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021 - Virtual, Online, Greece Duration: Jun 29 2021 → Jul 1 2021

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021
Country/Territory	Greece
City	Virtual, Online
Period	6/29/21 → 7/1/21

Keywords

Retinopathy of Prematurity
U-Net
learning from comparisons

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3453892.3454002

Cite this

Tian, P., Dy, J., Erdogmus, D., Ostmo, S., Campbell, J. P. P., Chiang, M. F. F., & Ioannidis, S. (2021). Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation. In 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021 (pp. 33-36). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3453892.3454002

Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation. / Tian, Peng; Dy, Jennifer; Erdogmus, Deniz et al.
14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021. Association for Computing Machinery, 2021. p. 33-36 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Tian, P, Dy, J, Erdogmus, D, Ostmo, S, Campbell, JPP, Chiang, MFF & Ioannidis, S 2021, Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation. in 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 33-36, 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021, Virtual, Online, Greece, 6/29/21. https://doi.org/10.1145/3453892.3454002

Tian P, Dy J, Erdogmus D, Ostmo S, Campbell JPP, Chiang MFF et al. Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation. In 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021. Association for Computing Machinery. 2021. p. 33-36. (ACM International Conference Proceeding Series). doi: 10.1145/3453892.3454002

@inproceedings{cad5069380884ca5a9f51075417b58ec,

title = "Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation",

abstract = "Retinopathy of Prematurity (ROP) is a disease affecting premature infants and may lead to childhood blindness. Due to lack of trained ophthalmologists, developing a fully automated ROP diagnostic system can significantly benefit the infants affected by ROP. Based on manually segmented features, previous work produces severity scores for ROP with excellent prediction accuracy. However, when automated segmentation employed, a significant accuracy drop is observed. In this paper, we show that U-Net segmentation, which is automated, comes at no accuracy loss.",

keywords = "Retinopathy of Prematurity, U-Net, learning from comparisons",

author = "Peng Tian and Jennifer Dy and Deniz Erdogmus and Susan Ostmo and Campbell, {J. Peter Peter} and Chiang, {Michael F.F.} and Stratis Ioannidis",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021 ; Conference date: 29-06-2021 Through 01-07-2021",

year = "2021",

month = jun,

day = "29",

doi = "10.1145/3453892.3454002",

language = "English (US)",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "33--36",

booktitle = "14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021",

}

TY - GEN

T1 - Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation

AU - Tian, Peng

AU - Dy, Jennifer

AU - Erdogmus, Deniz

AU - Ostmo, Susan

AU - Campbell, J. Peter Peter

AU - Chiang, Michael F.F.

AU - Ioannidis, Stratis

PY - 2021/6/29

Y1 - 2021/6/29

N2 - Retinopathy of Prematurity (ROP) is a disease affecting premature infants and may lead to childhood blindness. Due to lack of trained ophthalmologists, developing a fully automated ROP diagnostic system can significantly benefit the infants affected by ROP. Based on manually segmented features, previous work produces severity scores for ROP with excellent prediction accuracy. However, when automated segmentation employed, a significant accuracy drop is observed. In this paper, we show that U-Net segmentation, which is automated, comes at no accuracy loss.

AB - Retinopathy of Prematurity (ROP) is a disease affecting premature infants and may lead to childhood blindness. Due to lack of trained ophthalmologists, developing a fully automated ROP diagnostic system can significantly benefit the infants affected by ROP. Based on manually segmented features, previous work produces severity scores for ROP with excellent prediction accuracy. However, when automated segmentation employed, a significant accuracy drop is observed. In this paper, we show that U-Net segmentation, which is automated, comes at no accuracy loss.

KW - Retinopathy of Prematurity

KW - U-Net

KW - learning from comparisons

UR - http://www.scopus.com/inward/record.url?scp=85109307480&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85109307480&partnerID=8YFLogxK

U2 - 10.1145/3453892.3454002

DO - 10.1145/3453892.3454002

M3 - Conference contribution

AN - SCOPUS:85109307480

T3 - ACM International Conference Proceeding Series

SP - 33

EP - 36

BT - 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021

PB - Association for Computing Machinery

T2 - 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2021

Y2 - 29 June 2021 through 1 July 2021

ER -

Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this