A semi-automated machine-learning based workflow for ellipsoid zone analysis in eyes with macular edema: SCORE2 pilot study

Tyler Etheridge; Ellen T.A. Dobson; Marcel Wiedenmann; Chandana Papudesu; Ingrid U. Scott; Michael S. Ip; Kevin W. Eliceiri; Barbara A. Blodi; Amitha Domalpally

doi:10.1371/journal.pone.0232494

A semi-automated machine-learning based workflow for ellipsoid zone analysis in eyes with macular edema: SCORE2 pilot study

Tyler Etheridge, Ellen T.A. Dobson, Marcel Wiedenmann, Chandana Papudesu, Ingrid U. Scott, Michael S. Ip, Kevin W. Eliceiri, Barbara A. Blodi, Amitha Domalpally

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

Background and objective To develop a semi-automated, machine-learning based workflow to evaluate the ellipsoid zone (EZ) assessed by spectral domain optical coherence tomography (SD-OCT) in eyes with macular edema secondary to central retinal or hemi-retinal vein occlusion in SCORE2 treated with anti-vascular endothelial growth factor agents. Methods SD-OCT macular volume scans of a randomly selected subset of 75 SCORE2 study eyes were converted to the Digital Imaging and Communications in Medicine (DICOM) format, and the EZ layer was segmented using nonproprietary software. Segmented layer coordinates were exported and used to generate en face EZ thickness maps. Within the central subfield, the area of EZ defect was measured using manual and semi-automated approaches via a customized workflow in the open-source data analytics platform, Konstanz Information Miner (KNIME). Results A total of 184 volume scans from 74 study eyes were analyzed. The mean±SD area of EZ defect was similar between manual (0.19±0.22 mm²) and semi-automated measurements (0.19±0.21 mm², p = 0.93; intra-class correlation coefficient = 0.90; average bias = 0.01, 95% confidence interval of limits of agreement -0.18–0.20). Conclusions A customized workflow generated via an open-source data analytics platform that applied machine-learning methods demonstrated reliable measurements of EZ area defect from en face thickness maps. The result of our semi-automated approach were comparable to manual measurements.

Original language	English (US)
Article number	e0232494
Journal	PloS one
Volume	15
Issue number	4
DOIs	https://doi.org/10.1371/journal.pone.0232494
State	Published - Apr 2020

All Science Journal Classification (ASJC) codes

Biochemistry, Genetics and Molecular Biology(all)
Agricultural and Biological Sciences(all)
General

Access to Document

10.1371/journal.pone.0232494

Cite this

@article{45250f1aed8946018e5fba78354e3b0c,

title = "A semi-automated machine-learning based workflow for ellipsoid zone analysis in eyes with macular edema: SCORE2 pilot study",

abstract = "Background and objective To develop a semi-automated, machine-learning based workflow to evaluate the ellipsoid zone (EZ) assessed by spectral domain optical coherence tomography (SD-OCT) in eyes with macular edema secondary to central retinal or hemi-retinal vein occlusion in SCORE2 treated with anti-vascular endothelial growth factor agents. Methods SD-OCT macular volume scans of a randomly selected subset of 75 SCORE2 study eyes were converted to the Digital Imaging and Communications in Medicine (DICOM) format, and the EZ layer was segmented using nonproprietary software. Segmented layer coordinates were exported and used to generate en face EZ thickness maps. Within the central subfield, the area of EZ defect was measured using manual and semi-automated approaches via a customized workflow in the open-source data analytics platform, Konstanz Information Miner (KNIME). Results A total of 184 volume scans from 74 study eyes were analyzed. The mean±SD area of EZ defect was similar between manual (0.19±0.22 mm2) and semi-automated measurements (0.19±0.21 mm2, p = 0.93; intra-class correlation coefficient = 0.90; average bias = 0.01, 95% confidence interval of limits of agreement -0.18–0.20). Conclusions A customized workflow generated via an open-source data analytics platform that applied machine-learning methods demonstrated reliable measurements of EZ area defect from en face thickness maps. The result of our semi-automated approach were comparable to manual measurements.",

author = "Tyler Etheridge and Dobson, {Ellen T.A.} and Marcel Wiedenmann and Chandana Papudesu and Scott, {Ingrid U.} and Ip, {Michael S.} and Eliceiri, {Kevin W.} and Blodi, {Barbara A.} and Amitha Domalpally",

note = "Funding Information: {"}The Standard Care vs Corticosteroid for Retinal Vein Occlusion (SCORE) 2 Study was supported by National Eye Institute (National Institutes of Health, Department of Health and Human Services) grants U10EY023529, U10EY023533, and U10EY023521; and Allergan, Inc. The funder (Allergan, Inc.) had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. KNIME GmbH provided support for this study in the form of salary for MW. The specific roles of all authors are articulated in the{\textquoteright}author contributions{\textquoteright} section. KNIME GmbH had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Publisher Copyright: {\textcopyright} 2020 Etheridge et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.",

year = "2020",

month = apr,

doi = "10.1371/journal.pone.0232494",

language = "English (US)",

volume = "15",

journal = "PloS one",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "4",

}

TY - JOUR

T1 - A semi-automated machine-learning based workflow for ellipsoid zone analysis in eyes with macular edema

T2 - SCORE2 pilot study

AU - Etheridge, Tyler

AU - Dobson, Ellen T.A.

AU - Wiedenmann, Marcel

AU - Papudesu, Chandana

AU - Scott, Ingrid U.

AU - Ip, Michael S.

AU - Eliceiri, Kevin W.

AU - Blodi, Barbara A.

AU - Domalpally, Amitha

N1 - Funding Information: "The Standard Care vs Corticosteroid for Retinal Vein Occlusion (SCORE) 2 Study was supported by National Eye Institute (National Institutes of Health, Department of Health and Human Services) grants U10EY023529, U10EY023533, and U10EY023521; and Allergan, Inc. The funder (Allergan, Inc.) had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. KNIME GmbH provided support for this study in the form of salary for MW. The specific roles of all authors are articulated in the’author contributions’ section. KNIME GmbH had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Publisher Copyright: © 2020 Etheridge et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

PY - 2020/4

Y1 - 2020/4

N2 - Background and objective To develop a semi-automated, machine-learning based workflow to evaluate the ellipsoid zone (EZ) assessed by spectral domain optical coherence tomography (SD-OCT) in eyes with macular edema secondary to central retinal or hemi-retinal vein occlusion in SCORE2 treated with anti-vascular endothelial growth factor agents. Methods SD-OCT macular volume scans of a randomly selected subset of 75 SCORE2 study eyes were converted to the Digital Imaging and Communications in Medicine (DICOM) format, and the EZ layer was segmented using nonproprietary software. Segmented layer coordinates were exported and used to generate en face EZ thickness maps. Within the central subfield, the area of EZ defect was measured using manual and semi-automated approaches via a customized workflow in the open-source data analytics platform, Konstanz Information Miner (KNIME). Results A total of 184 volume scans from 74 study eyes were analyzed. The mean±SD area of EZ defect was similar between manual (0.19±0.22 mm2) and semi-automated measurements (0.19±0.21 mm2, p = 0.93; intra-class correlation coefficient = 0.90; average bias = 0.01, 95% confidence interval of limits of agreement -0.18–0.20). Conclusions A customized workflow generated via an open-source data analytics platform that applied machine-learning methods demonstrated reliable measurements of EZ area defect from en face thickness maps. The result of our semi-automated approach were comparable to manual measurements.

AB - Background and objective To develop a semi-automated, machine-learning based workflow to evaluate the ellipsoid zone (EZ) assessed by spectral domain optical coherence tomography (SD-OCT) in eyes with macular edema secondary to central retinal or hemi-retinal vein occlusion in SCORE2 treated with anti-vascular endothelial growth factor agents. Methods SD-OCT macular volume scans of a randomly selected subset of 75 SCORE2 study eyes were converted to the Digital Imaging and Communications in Medicine (DICOM) format, and the EZ layer was segmented using nonproprietary software. Segmented layer coordinates were exported and used to generate en face EZ thickness maps. Within the central subfield, the area of EZ defect was measured using manual and semi-automated approaches via a customized workflow in the open-source data analytics platform, Konstanz Information Miner (KNIME). Results A total of 184 volume scans from 74 study eyes were analyzed. The mean±SD area of EZ defect was similar between manual (0.19±0.22 mm2) and semi-automated measurements (0.19±0.21 mm2, p = 0.93; intra-class correlation coefficient = 0.90; average bias = 0.01, 95% confidence interval of limits of agreement -0.18–0.20). Conclusions A customized workflow generated via an open-source data analytics platform that applied machine-learning methods demonstrated reliable measurements of EZ area defect from en face thickness maps. The result of our semi-automated approach were comparable to manual measurements.

UR - http://www.scopus.com/inward/record.url?scp=85084277091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084277091&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0232494

DO - 10.1371/journal.pone.0232494

M3 - Article

C2 - 32353052

AN - SCOPUS:85084277091

SN - 1932-6203

VL - 15

JO - PloS one

JF - PloS one

IS - 4

M1 - e0232494

ER -

A semi-automated machine-learning based workflow for ellipsoid zone analysis in eyes with macular edema: SCORE2 pilot study

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this