Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study

Emily K. Swingle, Andrew Lang, Aaron Carass, Omar Al-Louzi, Shiv Saidha, Jerry Ladd Prince, Peter Calabresi

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

Abstract

Microcystic macular edema (MME) is a term used to describe pseudocystic spaces in the inner nuclear layer (INL) of the human retina. It has been noted in multiple sclerosis (MS) as well as a variety of other diseases. The processes that lead to MME formation and their change over time have yet to be explained sufficiently. The low rate at which MME occurs within such diverse patient groups makes the identification and consistent quantification of this pathology important for developing patient-specific prognoses. MME is observed in optical coherence tomography (OCT) scans of the retina as changes in light reflectivity in a pattern suggestive of fluid accumulations called pseudocysts. Pseudocysts can be readily identified in higher signal-to-noise ratio (SNR) images, however pseudocysts can be indistinguishable from noise in lower SNR scans. In this work, we expand upon our earlier MME identification methods on Spectralis OCT scans to handle lower quality Cirrus OCT scans. Our approach uses a random forest classifier, trained on manual segmentation of ten subjects, to automatically detect MME. The algorithm has a true positive rate for MME identification of 0.95 and a Dice score of 0.79. We include a preliminary longitudinal study of three patients over four to five years to explore the longitudinal changes of MME. The patients with relapsing-remitting MS and neuromyelitis optica appear to have dynamic pseudocyst volumes, while the MME volume appears stable in the one patient with primary progressive MS.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging
PublisherSPIE
Volume9417
ISBN (Print)9781628415070
DOIs
StatePublished - 2015
EventMedical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging - Orlando, United States
Duration: Feb 24 2015Feb 26 2015

Other

OtherMedical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging
CountryUnited States
CityOrlando
Period2/24/152/26/15

Fingerprint

edema
Macular Edema
Optical tomography
Optical Coherence Tomography
Longitudinal Studies
tomography
Signal to noise ratio
Pathology
Classifiers
retina
Signal-To-Noise Ratio
Fluids
Retina
signal to noise ratios
Neuromyelitis Optica
Chronic Progressive Multiple Sclerosis
Relapsing-Remitting Multiple Sclerosis
Social Identification
prognosis
pathology

Keywords

  • Microcystic macular edema
  • OCT
  • Retina
  • Segmentation

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Swingle, E. K., Lang, A., Carass, A., Al-Louzi, O., Saidha, S., Prince, J. L., & Calabresi, P. (2015). Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study. In Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging (Vol. 9417). [94170P] SPIE. https://doi.org/10.1117/12.2082164

Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study. / Swingle, Emily K.; Lang, Andrew; Carass, Aaron; Al-Louzi, Omar; Saidha, Shiv; Prince, Jerry Ladd; Calabresi, Peter.

Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging. Vol. 9417 SPIE, 2015. 94170P.

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

Swingle, EK, Lang, A, Carass, A, Al-Louzi, O, Saidha, S, Prince, JL & Calabresi, P 2015, Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study. in Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging. vol. 9417, 94170P, SPIE, Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging, Orlando, United States, 2/24/15. https://doi.org/10.1117/12.2082164
Swingle EK, Lang A, Carass A, Al-Louzi O, Saidha S, Prince JL et al. Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study. In Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging. Vol. 9417. SPIE. 2015. 94170P https://doi.org/10.1117/12.2082164
Swingle, Emily K. ; Lang, Andrew ; Carass, Aaron ; Al-Louzi, Omar ; Saidha, Shiv ; Prince, Jerry Ladd ; Calabresi, Peter. / Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study. Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging. Vol. 9417 SPIE, 2015.
@inproceedings{db8ddd18cead428484a5196f726d05a3,
title = "Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study",
abstract = "Microcystic macular edema (MME) is a term used to describe pseudocystic spaces in the inner nuclear layer (INL) of the human retina. It has been noted in multiple sclerosis (MS) as well as a variety of other diseases. The processes that lead to MME formation and their change over time have yet to be explained sufficiently. The low rate at which MME occurs within such diverse patient groups makes the identification and consistent quantification of this pathology important for developing patient-specific prognoses. MME is observed in optical coherence tomography (OCT) scans of the retina as changes in light reflectivity in a pattern suggestive of fluid accumulations called pseudocysts. Pseudocysts can be readily identified in higher signal-to-noise ratio (SNR) images, however pseudocysts can be indistinguishable from noise in lower SNR scans. In this work, we expand upon our earlier MME identification methods on Spectralis OCT scans to handle lower quality Cirrus OCT scans. Our approach uses a random forest classifier, trained on manual segmentation of ten subjects, to automatically detect MME. The algorithm has a true positive rate for MME identification of 0.95 and a Dice score of 0.79. We include a preliminary longitudinal study of three patients over four to five years to explore the longitudinal changes of MME. The patients with relapsing-remitting MS and neuromyelitis optica appear to have dynamic pseudocyst volumes, while the MME volume appears stable in the one patient with primary progressive MS.",
keywords = "Microcystic macular edema, OCT, Retina, Segmentation",
author = "Swingle, {Emily K.} and Andrew Lang and Aaron Carass and Omar Al-Louzi and Shiv Saidha and Prince, {Jerry Ladd} and Peter Calabresi",
year = "2015",
doi = "10.1117/12.2082164",
language = "English (US)",
isbn = "9781628415070",
volume = "9417",
booktitle = "Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging",
publisher = "SPIE",

}

TY - GEN

T1 - Segmentation of microcystic macular edema in Cirrus OCT scans with an exploratory longitudinal study

AU - Swingle, Emily K.

AU - Lang, Andrew

AU - Carass, Aaron

AU - Al-Louzi, Omar

AU - Saidha, Shiv

AU - Prince, Jerry Ladd

AU - Calabresi, Peter

PY - 2015

Y1 - 2015

N2 - Microcystic macular edema (MME) is a term used to describe pseudocystic spaces in the inner nuclear layer (INL) of the human retina. It has been noted in multiple sclerosis (MS) as well as a variety of other diseases. The processes that lead to MME formation and their change over time have yet to be explained sufficiently. The low rate at which MME occurs within such diverse patient groups makes the identification and consistent quantification of this pathology important for developing patient-specific prognoses. MME is observed in optical coherence tomography (OCT) scans of the retina as changes in light reflectivity in a pattern suggestive of fluid accumulations called pseudocysts. Pseudocysts can be readily identified in higher signal-to-noise ratio (SNR) images, however pseudocysts can be indistinguishable from noise in lower SNR scans. In this work, we expand upon our earlier MME identification methods on Spectralis OCT scans to handle lower quality Cirrus OCT scans. Our approach uses a random forest classifier, trained on manual segmentation of ten subjects, to automatically detect MME. The algorithm has a true positive rate for MME identification of 0.95 and a Dice score of 0.79. We include a preliminary longitudinal study of three patients over four to five years to explore the longitudinal changes of MME. The patients with relapsing-remitting MS and neuromyelitis optica appear to have dynamic pseudocyst volumes, while the MME volume appears stable in the one patient with primary progressive MS.

AB - Microcystic macular edema (MME) is a term used to describe pseudocystic spaces in the inner nuclear layer (INL) of the human retina. It has been noted in multiple sclerosis (MS) as well as a variety of other diseases. The processes that lead to MME formation and their change over time have yet to be explained sufficiently. The low rate at which MME occurs within such diverse patient groups makes the identification and consistent quantification of this pathology important for developing patient-specific prognoses. MME is observed in optical coherence tomography (OCT) scans of the retina as changes in light reflectivity in a pattern suggestive of fluid accumulations called pseudocysts. Pseudocysts can be readily identified in higher signal-to-noise ratio (SNR) images, however pseudocysts can be indistinguishable from noise in lower SNR scans. In this work, we expand upon our earlier MME identification methods on Spectralis OCT scans to handle lower quality Cirrus OCT scans. Our approach uses a random forest classifier, trained on manual segmentation of ten subjects, to automatically detect MME. The algorithm has a true positive rate for MME identification of 0.95 and a Dice score of 0.79. We include a preliminary longitudinal study of three patients over four to five years to explore the longitudinal changes of MME. The patients with relapsing-remitting MS and neuromyelitis optica appear to have dynamic pseudocyst volumes, while the MME volume appears stable in the one patient with primary progressive MS.

KW - Microcystic macular edema

KW - OCT

KW - Retina

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84943405106&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943405106&partnerID=8YFLogxK

U2 - 10.1117/12.2082164

DO - 10.1117/12.2082164

M3 - Conference contribution

C2 - 26023249

AN - SCOPUS:84943405106

SN - 9781628415070

VL - 9417

BT - Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging

PB - SPIE

ER -