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; Yalin Zheng; Max Yates; Jayne Woodside; Cathy Williams; Katie Williams; Mike Weedon; Veronique Vitart; Ananth Viswanathan; Adnan Tufail; Emanuele Trucco; Mervyn Thomas; Dhanes Thomas; Robyn Tapp; Zihan Sun; Cathie Sudlow; Nicholas Strouthidis; Irene Stratton; David Steel; Sobha Sivaprasad; Panagiotis Sergouniotis; Jay Self; Naveed Sattar; Alicja Rudnicka; Jugnoo Rahi; Nikolas Pontikos; Axel Petzold; Tunde Peto; Euan Paterson; Praveen Patel; Chris Owen; Richard Oram; Eoin O’Sullivan; James Morgan; Tony Moore; Martin McKibbin; Gareth McKay; Bernadette McGuinness; Ruth Hogg; Usha Chakravarthy; 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^*, Yalin Zheng, Max Yates, Jayne Woodside, Cathy Williams, Katie Williams, Mike Weedon, Veronique Vitart, Ananth Viswanathan, Adnan TufailEmanuele Trucco, Mervyn Thomas, Dhanes Thomas, Robyn Tapp, Zihan Sun, Cathie Sudlow, Nicholas Strouthidis, Irene Stratton, David Steel, Sobha Sivaprasad, Panagiotis Sergouniotis, Jay Self, Naveed Sattar, Alicja Rudnicka, Jugnoo Rahi, Nikolas Pontikos, Axel Petzold, Tunde Peto, Euan Paterson, Praveen Patel, Chris Owen, Richard Oram, Eoin O’Sullivan, James Morgan, Tony Moore, Martin McKibbin, Gareth McKay, Bernadette McGuinness, Ruth Hogg, Usha Chakravarthy, UK Biobank Eye and Vision Consortium

^*Corresponding author for this work

School of Medicine, Dentistry and Biomedical Sciences

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

3 Citations (Scopus)

3 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
Journal	Communications Medicine
Volume	4
DOIs	https://doi.org/10.1038/s43856-024-00496-w
Publication status	Published - 11 Apr 2024

Keywords

glaucoma
Convolutional neural network-based classification
optic radiation tissue
brain tissue

ASJC Scopus subject areas

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

UN SDGs

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

Access to Document

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

Convolutional neural network-based classification of glaucoma using optic radiation tissue properties
Copyright 2024 the authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final 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., Zheng, Y., Yates, M., Woodside, J., Williams, C., Williams, K., Weedon, M., Vitart, V., Viswanathan, A., ... UK Biobank Eye and Vision Consortium (2024). Convolutional neural network-based classification of glaucoma using optic radiation tissue properties. Communications Medicine, 4, Article 72. https://doi.org/10.1038/s43856-024-00496-w

@article{751894422012416b92ee10ee08ffa41a,

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.",

keywords = "glaucoma, Convolutional neural network-based classification, optic radiation tissue, brain tissue",

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 Yalin Zheng and Max Yates and Jayne Woodside and Cathy Williams and Katie Williams and Mike Weedon and Veronique Vitart and Ananth Viswanathan and Adnan Tufail and Emanuele Trucco and Mervyn Thomas and Dhanes Thomas and Robyn Tapp and Zihan Sun and Cathie Sudlow and Nicholas Strouthidis and Irene Stratton and David Steel and Sobha Sivaprasad and Panagiotis Sergouniotis and Jay Self and Naveed Sattar and Alicja Rudnicka and Jugnoo Rahi and Nikolas Pontikos and Axel Petzold and Tunde Peto and Euan Paterson and Praveen Patel and Chris Owen and Richard Oram and Eoin O{\textquoteright}Sullivan and James Morgan and Tony Moore and Martin McKibbin and Gareth McKay and Bernadette McGuinness and Ruth Hogg and Usha Chakravarthy and {UK Biobank Eye and Vision Consortium}",

year = "2024",

month = apr,

day = "11",

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

language = "English",

volume = "4",

journal = "Communications Medicine",

issn = "2730-664X",

publisher = "Springer Nature",

}

Kruper, J, Richie-Halford, A, Benson, NC, Caffarra, S, Owen, J, Wu, Y, Egan, C, Lee, AY, Lee, CS, Yeatman, JD, Rokem, A, Zheng, Y, Yates, M, Woodside, J, Williams, C, Williams, K, Weedon, M, Vitart, V, Viswanathan, A, Tufail, A, Trucco, E, Thomas, M, Thomas, D, Tapp, R, Sun, Z, Sudlow, C, Strouthidis, N, Stratton, I, Steel, D, Sivaprasad, S, Sergouniotis, P, Self, J, Sattar, N, Rudnicka, A, Rahi, J, Pontikos, N, Petzold, A, Peto, T, Paterson, E, Patel, P, Owen, C, Oram, R, O’Sullivan, E, Morgan, J, Moore, T, McKibbin, M, McKay, G , McGuinness, B , Hogg, R, Chakravarthy, U & UK Biobank Eye and Vision Consortium 2024, 'Convolutional neural network-based classification of glaucoma using optic radiation tissue properties', Communications Medicine, vol. 4, 72. https://doi.org/10.1038/s43856-024-00496-w

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 - Zheng, Yalin

AU - Yates, Max

AU - Woodside, Jayne

AU - Williams, Cathy

AU - Williams, Katie

AU - Weedon, Mike

AU - Vitart, Veronique

AU - Viswanathan, Ananth

AU - Tufail, Adnan

AU - Trucco, Emanuele

AU - Thomas, Mervyn

AU - Thomas, Dhanes

AU - Tapp, Robyn

AU - Sun, Zihan

AU - Sudlow, Cathie

AU - Strouthidis, Nicholas

AU - Stratton, Irene

AU - Steel, David

AU - Sivaprasad, Sobha

AU - Sergouniotis, Panagiotis

AU - Self, Jay

AU - Sattar, Naveed

AU - Rudnicka, Alicja

AU - Rahi, Jugnoo

AU - Pontikos, Nikolas

AU - Petzold, Axel

AU - Peto, Tunde

AU - Paterson, Euan

AU - Patel, Praveen

AU - Owen, Chris

AU - Oram, Richard

AU - O’Sullivan, Eoin

AU - Morgan, James

AU - Moore, Tony

AU - McKibbin, Martin

AU - McKay, Gareth

AU - McGuinness, Bernadette

AU - Hogg, Ruth

AU - Chakravarthy, Usha

AU - UK Biobank Eye and Vision Consortium

PY - 2024/4/11

Y1 - 2024/4/11

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.

KW - glaucoma

KW - Convolutional neural network-based classification

KW - optic radiation tissue

KW - brain tissue

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

M1 - 72

ER -

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

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this