Discriminating Between Papilledema and Optic Disc Drusen Using 3D Structural Analysis of the Optic Nerve Head.

Humans Optic Disk / diagnostic imaging Papilledema / diagnostic imaging Optic Disk Drusen / diagnosis Artificial Intelligence Retrospective Studies Cross-Sectional Studies Tomography, Optical Coherence / methods

Journal

Neurology
ISSN: 1526-632X
Titre abrégé: Neurology
Pays: United States
ID NLM: 0401060

Informations de publication

Date de publication:
10 01 2023
Historique:
received: 04 02 2022
accepted: 19 08 2022
pubmed: 30 9 2022
medline: 12 1 2023
entrez: 29 9 2022
Statut: ppublish

Résumé

The distinction of papilledema from other optic nerve head (ONH) lesions mimicking papilledema, such as optic disc drusen (ODD), can be difficult in clinical practice. We aimed the following: (1) to develop a deep learning algorithm to automatically identify major structures of the ONH in 3-dimensional (3D) optical coherence tomography (OCT) scans and (2) to exploit such information to robustly differentiate among ODD, papilledema, and healthy ONHs. This was a cross-sectional comparative study of patients from 3 sites (Singapore, Denmark, and Australia) with confirmed ODD, those with papilledema due to raised intracranial pressure, and healthy controls. Raster scans of the ONH were acquired using OCT imaging and then processed to improve deep-tissue visibility. First, a deep learning algorithm was developed to identify major ONH tissues and ODD regions. The performance of our algorithm was assessed using the Dice coefficient. Second, a classification algorithm (random forest) was designed to perform 3-class classifications (1: ODD, 2: papilledema, and 3: healthy ONHs) strictly from their drusen and prelamina swelling scores (calculated from the segmentations). To assess performance, we reported the area under the receiver operating characteristic curve for each class. A total of 241 patients (256 imaged ONHs, including 105 ODD, 51 papilledema, and 100 healthy ONHs) were retrospectively included in this study. Using OCT images of the ONH, our segmentation algorithm was able to isolate neural and connective tissues and ODD regions/conglomerates whenever present. This was confirmed by an averaged Dice coefficient of 0.93 ± 0.03 on the test set, corresponding to good segmentation performance. Classification was achieved with high AUCs, that is, 0.99 ± 0.001 for the detection of ODD, 0.99 ± 0.005 for the detection of papilledema, and 0.98 ± 0.01 for the detection of healthy ONHs. Our artificial intelligence approach can discriminate ODD from papilledema, strictly using a single OCT scan of the ONH. Our classification performance was very good in the studied population, with the caveat that validation in a much larger population is warranted. Our approach may have the potential to establish OCT imaging as one of the mainstays of diagnostic imaging for ONH disorders in neuro-ophthalmology, in addition to fundus photography.

Sections du résumé

BACKGROUND AND OBJECTIVES
The distinction of papilledema from other optic nerve head (ONH) lesions mimicking papilledema, such as optic disc drusen (ODD), can be difficult in clinical practice. We aimed the following: (1) to develop a deep learning algorithm to automatically identify major structures of the ONH in 3-dimensional (3D) optical coherence tomography (OCT) scans and (2) to exploit such information to robustly differentiate among ODD, papilledema, and healthy ONHs.
METHODS
This was a cross-sectional comparative study of patients from 3 sites (Singapore, Denmark, and Australia) with confirmed ODD, those with papilledema due to raised intracranial pressure, and healthy controls. Raster scans of the ONH were acquired using OCT imaging and then processed to improve deep-tissue visibility. First, a deep learning algorithm was developed to identify major ONH tissues and ODD regions. The performance of our algorithm was assessed using the Dice coefficient. Second, a classification algorithm (random forest) was designed to perform 3-class classifications (1: ODD, 2: papilledema, and 3: healthy ONHs) strictly from their drusen and prelamina swelling scores (calculated from the segmentations). To assess performance, we reported the area under the receiver operating characteristic curve for each class.
RESULTS
A total of 241 patients (256 imaged ONHs, including 105 ODD, 51 papilledema, and 100 healthy ONHs) were retrospectively included in this study. Using OCT images of the ONH, our segmentation algorithm was able to isolate neural and connective tissues and ODD regions/conglomerates whenever present. This was confirmed by an averaged Dice coefficient of 0.93 ± 0.03 on the test set, corresponding to good segmentation performance. Classification was achieved with high AUCs, that is, 0.99 ± 0.001 for the detection of ODD, 0.99 ± 0.005 for the detection of papilledema, and 0.98 ± 0.01 for the detection of healthy ONHs.
DISCUSSION
Our artificial intelligence approach can discriminate ODD from papilledema, strictly using a single OCT scan of the ONH. Our classification performance was very good in the studied population, with the caveat that validation in a much larger population is warranted. Our approach may have the potential to establish OCT imaging as one of the mainstays of diagnostic imaging for ONH disorders in neuro-ophthalmology, in addition to fundus photography.

Identifiants

DOI: 10.1212/WNL.0000000000201350 PMID: 36175153
pubmed: 36175153
pii: WNL.0000000000201350
doi: 10.1212/WNL.0000000000201350
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

e192-e202

Informations de copyright

© 2022 American Academy of Neurology.

Auteurs

Michaël J A Girard (MJA)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia. mgirard@ophthalmic.engineering.
ORCID: 0000-0003-4408-5918

Satish Panda (S)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.
ORCID: 0000-0002-3869-3928

Tin Aung Tun (TA)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.

Elisabeth A Wibroe (EA)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.

Raymond P Najjar (RP)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.
ORCID: 0000-0002-3770-2300

Tin Aung (T)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.

Alexandre H Thiéry (AH)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.

Steffen Hamann (S)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.

Clare Fraser (C)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.

Dan Milea (D)

From the Ophthalmic Engineering & Innovation Laboratory (M.J.A.G., S.P.), Singapore Eye Research Institute (T.A.T., R.P.N., T.A., D.M.), Singapore National Eye Centre; Duke-NUS Graduate Medical School (M.J.A.G., T.A.T., R.P.N., T.A., D.M.), Singapore; Institute for Molecular and Clinical Ophthalmology (M.J.A.G.), Basel, Switzerland; Department of Ophthalmology (E.A.W., S.H.), Rigshospitalet, University of Copenhagen, Denmark; Yong Loo Lin School of Medicine (R.P.N., T.A.), and Department of Statistics and Applied Probability (A.H.T.), National University of Singapore; and Save Sight Institute (C.F.), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia.
ORCID: 0000-0002-6388-8639

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female

Evaluation of Low-Value Services Across Major Medicare Advantage Insurers and Traditional Medicare.

Ciara Duggan, Adam L Beckman, Ishani Ganguli et al.
1.00
Humans United States Aged Cross-Sectional Studies Medicare Part C

Effectiveness of Virtual Yoga for Chronic Low Back Pain: A Randomized Clinical Trial.

Hallie Tankha, Devyn Gaskins, Amanda Shallcross et al.
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH

questionsmedicales.fr › Eucaryotes › Animaux › Chordés › Vertébrés › Mammifères › Eutheria › Primates › Haplorhini › Catarrhini › Hominidae › Humains › Discriminating Between Papilledema and Optic...
questionsmedicales.fr › Organes des sens › Oeil › Rétine › Papille optique › Discriminating Between Papilledema and Optic...
questionsmedicales.fr › Maladies de l'oeil › Atteintes du nerf optique › Oedème papillaire › Discriminating Between Papilledema and Optic...
questionsmedicales.fr › Maladies de l'oeil › Atteintes du nerf optique › Druses de la papille optique › Discriminating Between Papilledema and Optic...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Discriminating Between Papilledema and Optic...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Caractéristiques des études épidémiologiques › Études épidémiologiques › Études de cohortes › Études rétrospectives › Discriminating Between Papilledema and Optic...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Caractéristiques des études épidémiologiques › Études épidémiologiques › Études transversales › Discriminating Between Papilledema and Optic...
questionsmedicales.fr › Techniques d'investigation › Imagerie optique › Tomographie optique › Tomographie par cohérence optique › Discriminating Between Papilledema and Optic...