Automated OCT segmentation for images with DME

Sohini Roychowdhury, Dara Koozekanani, Michael Reinsbach, Keshab K Parhi

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. The World Health Organization estimates that by the year 2020, there will be 75 million blind people and 314 million partially blind people in the world [1]. While treatments are available, including intravitreal injections and macular laser therapy, not all patients respond to these. Currently, there are no reliable methods for predicting patient response to therapy. Therefore, analysis of the patient images prior to treatment may allow the development of measures to predict patient response. Computer-aided diagnostic (CAD) systems enable automated detection of ophthalmic pathological sites, monitoring the progression of pathology, and can guide follow-up treatment processes. Optical Coherence Tomography (OCT) images have been widely used to assess macular diseases, and they have enabled analysis of the extent of disorganization in the sub-retinal layers due to DME [2,3]. Sub-retinal layer disorganization refers to the variation in the underlying retinal microstructure due to the presence of cystoid regions or to disruptions in the cellular architecture of the sub-retinal layers due to pathology [4]. For each patient’s eye under analysis, a stack of images centered at the macula are acquired, such that reconstruction of the sub-retinal surfaces from the OCT image stacks aid localization of disease-related abnormalities in the retinal microstructure. In this work, a CAD system is presented that automatically segments sub-retinal surfaces and layers in OCT image stacks from normal patients and abnormal ones with DME, such that thickness maps corresponding to the sub-retinal layers can be further analyzed for their clinical relevance to the severity of DME.

Original languageEnglish (US)
Title of host publicationMedical Image Analysis and Informatics
Subtitle of host publicationComputer-Aided Diagnosis and Therapy
PublisherCRC Press
Pages85-101
Number of pages17
ISBN (Electronic)9781498753203
ISBN (Print)9781498753197
DOIs
StatePublished - Jan 1 2017

Fingerprint

edema
Macular Edema
Optical tomography
Optical Coherence Tomography
tomography
Pathology
Microstructure
Medical problems
pathology
Health
therapy
Lasers
Monitoring
microstructure
Intravitreal Injections
abnormalities
Laser Therapy
Therapeutics
progressions
health

Cite this

Roychowdhury, S., Koozekanani, D., Reinsbach, M., & Parhi, K. K. (2017). Automated OCT segmentation for images with DME. In Medical Image Analysis and Informatics: Computer-Aided Diagnosis and Therapy (pp. 85-101). CRC Press. https://doi.org/10.1201/9781351228343

Automated OCT segmentation for images with DME. / Roychowdhury, Sohini; Koozekanani, Dara; Reinsbach, Michael; Parhi, Keshab K.

Medical Image Analysis and Informatics: Computer-Aided Diagnosis and Therapy. CRC Press, 2017. p. 85-101.

Research output: Chapter in Book/Report/Conference proceedingChapter

Roychowdhury, S, Koozekanani, D, Reinsbach, M & Parhi, KK 2017, Automated OCT segmentation for images with DME. in Medical Image Analysis and Informatics: Computer-Aided Diagnosis and Therapy. CRC Press, pp. 85-101. https://doi.org/10.1201/9781351228343
Roychowdhury S, Koozekanani D, Reinsbach M, Parhi KK. Automated OCT segmentation for images with DME. In Medical Image Analysis and Informatics: Computer-Aided Diagnosis and Therapy. CRC Press. 2017. p. 85-101 https://doi.org/10.1201/9781351228343
Roychowdhury, Sohini ; Koozekanani, Dara ; Reinsbach, Michael ; Parhi, Keshab K. / Automated OCT segmentation for images with DME. Medical Image Analysis and Informatics: Computer-Aided Diagnosis and Therapy. CRC Press, 2017. pp. 85-101
@inbook{a50b1488fc1b4928ae530c0b775a8012,
title = "Automated OCT segmentation for images with DME",
abstract = "Diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. The World Health Organization estimates that by the year 2020, there will be 75 million blind people and 314 million partially blind people in the world [1]. While treatments are available, including intravitreal injections and macular laser therapy, not all patients respond to these. Currently, there are no reliable methods for predicting patient response to therapy. Therefore, analysis of the patient images prior to treatment may allow the development of measures to predict patient response. Computer-aided diagnostic (CAD) systems enable automated detection of ophthalmic pathological sites, monitoring the progression of pathology, and can guide follow-up treatment processes. Optical Coherence Tomography (OCT) images have been widely used to assess macular diseases, and they have enabled analysis of the extent of disorganization in the sub-retinal layers due to DME [2,3]. Sub-retinal layer disorganization refers to the variation in the underlying retinal microstructure due to the presence of cystoid regions or to disruptions in the cellular architecture of the sub-retinal layers due to pathology [4]. For each patient’s eye under analysis, a stack of images centered at the macula are acquired, such that reconstruction of the sub-retinal surfaces from the OCT image stacks aid localization of disease-related abnormalities in the retinal microstructure. In this work, a CAD system is presented that automatically segments sub-retinal surfaces and layers in OCT image stacks from normal patients and abnormal ones with DME, such that thickness maps corresponding to the sub-retinal layers can be further analyzed for their clinical relevance to the severity of DME.",
author = "Sohini Roychowdhury and Dara Koozekanani and Michael Reinsbach and Parhi, {Keshab K}",
year = "2017",
month = "1",
day = "1",
doi = "10.1201/9781351228343",
language = "English (US)",
isbn = "9781498753197",
pages = "85--101",
booktitle = "Medical Image Analysis and Informatics",
publisher = "CRC Press",
address = "United States",

}

TY - CHAP

T1 - Automated OCT segmentation for images with DME

AU - Roychowdhury, Sohini

AU - Koozekanani, Dara

AU - Reinsbach, Michael

AU - Parhi, Keshab K

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. The World Health Organization estimates that by the year 2020, there will be 75 million blind people and 314 million partially blind people in the world [1]. While treatments are available, including intravitreal injections and macular laser therapy, not all patients respond to these. Currently, there are no reliable methods for predicting patient response to therapy. Therefore, analysis of the patient images prior to treatment may allow the development of measures to predict patient response. Computer-aided diagnostic (CAD) systems enable automated detection of ophthalmic pathological sites, monitoring the progression of pathology, and can guide follow-up treatment processes. Optical Coherence Tomography (OCT) images have been widely used to assess macular diseases, and they have enabled analysis of the extent of disorganization in the sub-retinal layers due to DME [2,3]. Sub-retinal layer disorganization refers to the variation in the underlying retinal microstructure due to the presence of cystoid regions or to disruptions in the cellular architecture of the sub-retinal layers due to pathology [4]. For each patient’s eye under analysis, a stack of images centered at the macula are acquired, such that reconstruction of the sub-retinal surfaces from the OCT image stacks aid localization of disease-related abnormalities in the retinal microstructure. In this work, a CAD system is presented that automatically segments sub-retinal surfaces and layers in OCT image stacks from normal patients and abnormal ones with DME, such that thickness maps corresponding to the sub-retinal layers can be further analyzed for their clinical relevance to the severity of DME.

AB - Diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. The World Health Organization estimates that by the year 2020, there will be 75 million blind people and 314 million partially blind people in the world [1]. While treatments are available, including intravitreal injections and macular laser therapy, not all patients respond to these. Currently, there are no reliable methods for predicting patient response to therapy. Therefore, analysis of the patient images prior to treatment may allow the development of measures to predict patient response. Computer-aided diagnostic (CAD) systems enable automated detection of ophthalmic pathological sites, monitoring the progression of pathology, and can guide follow-up treatment processes. Optical Coherence Tomography (OCT) images have been widely used to assess macular diseases, and they have enabled analysis of the extent of disorganization in the sub-retinal layers due to DME [2,3]. Sub-retinal layer disorganization refers to the variation in the underlying retinal microstructure due to the presence of cystoid regions or to disruptions in the cellular architecture of the sub-retinal layers due to pathology [4]. For each patient’s eye under analysis, a stack of images centered at the macula are acquired, such that reconstruction of the sub-retinal surfaces from the OCT image stacks aid localization of disease-related abnormalities in the retinal microstructure. In this work, a CAD system is presented that automatically segments sub-retinal surfaces and layers in OCT image stacks from normal patients and abnormal ones with DME, such that thickness maps corresponding to the sub-retinal layers can be further analyzed for their clinical relevance to the severity of DME.

UR - http://www.scopus.com/inward/record.url?scp=85053314731&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053314731&partnerID=8YFLogxK

U2 - 10.1201/9781351228343

DO - 10.1201/9781351228343

M3 - Chapter

AN - SCOPUS:85053314731

SN - 9781498753197

SP - 85

EP - 101

BT - Medical Image Analysis and Informatics

PB - CRC Press

ER -