Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

John Kruper; Adam Richie-Halford; Noah C. Benson; Sendy Caffarra; Julia Owen; Yue Wu; Catherine Egan; Aaron Y. Lee; Cecilia S. Lee; Jason D. Yeatman; Ariel Rokem; UK Biobank Eye and Vision Consortium

doi:10.1038/s43856-024-00496-w

Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

John Kruper
, Adam Richie-Halford
, Noah C. Benson
, Sendy Caffarra
, Julia Owen
, Yue Wu
, Catherine Egan
, Aaron Y. Lee
, Cecilia S. Lee
, Jason D. Yeatman
, Ariel Rokem
, UK Biobank Eye and Vision Consortium

University of Washington
Stanford University
University of Modena and Reggio Emilia
University of Washington School of Medicine
NIHR Moorfields Biomedical Research Centre
City St George's, University of London

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

13 Citations (Scopus)

14 Downloads (Pure)

Abstract

Background: Sensory changes due to aging or disease can impact brain tissue. This study aims to investigate the link between glaucoma, a leading cause of blindness, and alterations in brain connections. Methods: We analyzed diffusion MRI measurements of white matter tissue in a large group, consisting of 905 glaucoma patients (aged 49-80) and 5292 healthy individuals (aged 45-80) from the UK Biobank. Confounds due to group differences were mitigated by matching a sub-sample of controls to glaucoma subjects. We compared classification of glaucoma using convolutional neural networks (CNNs) focusing on the optic radiations, which are the primary visual connection to the cortex, against those analyzing non-visual brain connections. As a control, we evaluated the performance of regularized linear regression models. Results: We showed that CNNs using information from the optic radiations exhibited higher accuracy in classifying subjects with glaucoma when contrasted with CNNs relying on information from non-visual brain connections. Regularized linear regression models were also tested, and showed significantly weaker classification performance. Additionally, the CNN was unable to generalize to the classification of age-group or of age-related macular degeneration. Conclusions: Our findings indicate a distinct and potentially non-linear signature of glaucoma in the tissue properties of optic radiations. This study enhances our understanding of how glaucoma affects brain tissue and opens avenues for further research into how diseases that affect sensory input may also affect brain aging.

Original language	English
Article number	72
Number of pages	10
Journal	Communications Medicine
Volume	4
Issue number	1
Early online date	11 Apr 2024
DOIs	https://doi.org/10.1038/s43856-024-00496-w
Publication status	Published - 24 Apr 2024
Externally published	Yes

Bibliographical note

This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated
otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

ASJC Scopus subject areas

Public Health, Environmental and Occupational Health
Internal Medicine
Epidemiology
Medicine (miscellaneous)
Assessment and Diagnosis

Access to Document

10.1038/s43856-024-00496-wLicence: CC BY

s43856-024-00496-wFinal published version, 1.76 MBLicence: CC BY

Cite this

Kruper, J., Richie-Halford, A., Benson, N. C., Caffarra, S., Owen, J., Wu, Y., Egan, C., Lee, A. Y., Lee, C. S., Yeatman, J. D., Rokem, A., & UK Biobank Eye and Vision Consortium (2024). Convolutional neural network-based classification of glaucoma using optic radiation tissue properties. Communications Medicine, 4(1), Article 72. https://doi.org/10.1038/s43856-024-00496-w

@article{5be9d6b4616d43a78addb3283e1c6cec,

title = "Convolutional neural network-based classification of glaucoma using optic radiation tissue properties",

abstract = "Background: Sensory changes due to aging or disease can impact brain tissue. This study aims to investigate the link between glaucoma, a leading cause of blindness, and alterations in brain connections. Methods: We analyzed diffusion MRI measurements of white matter tissue in a large group, consisting of 905 glaucoma patients (aged 49-80) and 5292 healthy individuals (aged 45-80) from the UK Biobank. Confounds due to group differences were mitigated by matching a sub-sample of controls to glaucoma subjects. We compared classification of glaucoma using convolutional neural networks (CNNs) focusing on the optic radiations, which are the primary visual connection to the cortex, against those analyzing non-visual brain connections. As a control, we evaluated the performance of regularized linear regression models. Results: We showed that CNNs using information from the optic radiations exhibited higher accuracy in classifying subjects with glaucoma when contrasted with CNNs relying on information from non-visual brain connections. Regularized linear regression models were also tested, and showed significantly weaker classification performance. Additionally, the CNN was unable to generalize to the classification of age-group or of age-related macular degeneration. Conclusions: Our findings indicate a distinct and potentially non-linear signature of glaucoma in the tissue properties of optic radiations. This study enhances our understanding of how glaucoma affects brain tissue and opens avenues for further research into how diseases that affect sensory input may also affect brain aging.",

author = "John Kruper and Adam Richie-Halford and Benson, \{Noah C.\} and Sendy Caffarra and Julia Owen and Yue Wu and Catherine Egan and Lee, \{Aaron Y.\} and Lee, \{Cecilia S.\} and Yeatman, \{Jason D.\} and Ariel Rokem and \{UK Biobank Eye and Vision Consortium\} and Robyn Tapp",

note = "This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article{\textquoteright}s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article{\textquoteright}s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.",

year = "2024",

month = apr,

day = "24",

doi = "10.1038/s43856-024-00496-w",

language = "English",

volume = "4",

journal = "Communications Medicine",

issn = "2730-664X",

publisher = "Springer Nature",

number = "1",

}

TY - JOUR

T1 - Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

AU - Kruper, John

AU - Richie-Halford, Adam

AU - Benson, Noah C.

AU - Caffarra, Sendy

AU - Owen, Julia

AU - Wu, Yue

AU - Egan, Catherine

AU - Lee, Aaron Y.

AU - Lee, Cecilia S.

AU - Yeatman, Jason D.

AU - Rokem, Ariel

AU - UK Biobank Eye and Vision Consortium

AU - Tapp, Robyn

N1 - This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

PY - 2024/4/24

Y1 - 2024/4/24

N2 - Background: Sensory changes due to aging or disease can impact brain tissue. This study aims to investigate the link between glaucoma, a leading cause of blindness, and alterations in brain connections. Methods: We analyzed diffusion MRI measurements of white matter tissue in a large group, consisting of 905 glaucoma patients (aged 49-80) and 5292 healthy individuals (aged 45-80) from the UK Biobank. Confounds due to group differences were mitigated by matching a sub-sample of controls to glaucoma subjects. We compared classification of glaucoma using convolutional neural networks (CNNs) focusing on the optic radiations, which are the primary visual connection to the cortex, against those analyzing non-visual brain connections. As a control, we evaluated the performance of regularized linear regression models. Results: We showed that CNNs using information from the optic radiations exhibited higher accuracy in classifying subjects with glaucoma when contrasted with CNNs relying on information from non-visual brain connections. Regularized linear regression models were also tested, and showed significantly weaker classification performance. Additionally, the CNN was unable to generalize to the classification of age-group or of age-related macular degeneration. Conclusions: Our findings indicate a distinct and potentially non-linear signature of glaucoma in the tissue properties of optic radiations. This study enhances our understanding of how glaucoma affects brain tissue and opens avenues for further research into how diseases that affect sensory input may also affect brain aging.

AB - Background: Sensory changes due to aging or disease can impact brain tissue. This study aims to investigate the link between glaucoma, a leading cause of blindness, and alterations in brain connections. Methods: We analyzed diffusion MRI measurements of white matter tissue in a large group, consisting of 905 glaucoma patients (aged 49-80) and 5292 healthy individuals (aged 45-80) from the UK Biobank. Confounds due to group differences were mitigated by matching a sub-sample of controls to glaucoma subjects. We compared classification of glaucoma using convolutional neural networks (CNNs) focusing on the optic radiations, which are the primary visual connection to the cortex, against those analyzing non-visual brain connections. As a control, we evaluated the performance of regularized linear regression models. Results: We showed that CNNs using information from the optic radiations exhibited higher accuracy in classifying subjects with glaucoma when contrasted with CNNs relying on information from non-visual brain connections. Regularized linear regression models were also tested, and showed significantly weaker classification performance. Additionally, the CNN was unable to generalize to the classification of age-group or of age-related macular degeneration. Conclusions: Our findings indicate a distinct and potentially non-linear signature of glaucoma in the tissue properties of optic radiations. This study enhances our understanding of how glaucoma affects brain tissue and opens avenues for further research into how diseases that affect sensory input may also affect brain aging.

UR - https://www.scopus.com/pages/publications/85198529109

U2 - 10.1038/s43856-024-00496-w

DO - 10.1038/s43856-024-00496-w

M3 - Article

AN - SCOPUS:85198529109

SN - 2730-664X

VL - 4

JO - Communications Medicine

JF - Communications Medicine

IS - 1

M1 - 72

ER -

Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

Abstract

Bibliographical note

UN SDGs

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this