Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study

James T. Grist; Stephanie Withey; Lesley Macpherson; Adam Oates; Stephen Powell; Jan Novak; Laurence Abernethy; Barry Pizer; Richard Grundy; Simon Bailey; Dipayan Mitra; Theodoros N. Arvanitis; Dorothee P. Auer; Shivaram Avula; Andrew C Peet

doi:10.1016/j.nicl.2020.102172

Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study

James T. Grist, Stephanie Withey, Lesley Macpherson, Adam Oates, Stephen Powell, Jan Novak, Laurence Abernethy, Barry Pizer, Richard Grundy, Simon Bailey, Dipayan Mitra, Theodoros N. Arvanitis, Dorothee P. Auer, Shivaram Avula, Andrew C Peet

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

Abstract

The imaging and subsequent accurate diagnosis of paediatric brain tumours presents a radiological challenge, with magnetic resonance imaging playing a key role in providing tumour specific imaging information. Diffusion weighted and perfusion imaging are commonly used to aid the non-invasive diagnosis of children's brain tumours, but are usually evaluated by expert qualitative review. Quantitative studies are mainly single centre and single modality. The aim of this work was to combine multi-centre diffusion and perfusion imaging, with machine learning, to develop machine learning based classifiers to discriminate between three common paediatric tumour types. The results show that diffusion and perfusion weighted imaging of both the tumour and whole brain provide significant features which differ between tumour types, and that combining these features gives the optimal machine learning classifier with >80% predictive precision. This work represents a step forward to aid in the non-invasive diagnosis of paediatric brain tumours, using advanced clinical imaging.

Original language	English
Article number	102172
Journal	NeuroImage: Clinical
Volume	25
Early online date	23 Jan 2020
DOIs	https://doi.org/10.1016/j.nicl.2020.102172
Publication status	Published - 15 Feb 2020

Bibliographical note

© 2020 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/BY/4.0/).

Funding: We would like to acknowledge funding from the Cancer Research UK and EPSRC Cancer Imaging Programme at the Children's Cancer and Leukaemia Group (CCLG) in association with the MRC and Department of Health (England) (C7809/A10342), the Cancer Research UK and NIHR Experimental Cancer Medicine Centre Paediatric Network (C8232/A25261), the Medical Research Council – Health Data Research UK Substantive Site and Help Harry Help Others charity. Professor Peet is funded through an NIHR Research Professorship, NIHR-RP-R2-12-019. Stephen Powell gratefully acknowledges financial support from EPSRC through a studentship from the Physical Sciences for Health Centre for Doctoral Training (EP/L016346/1). Professor Theodoros N Arvanitis is partially supported by Health Data Research UK, which is funded by the UK Medical Research Council, Engineering and Physical Sciences Research Council, Economic and Social Research Council, Department of Health and Social Care (England), Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research and Development Division (Welsh Government), Public Health Agency (Northern Ireland), British Heart Foundation and Wellcome Trust. We would also like to acknowledge the MR radiographers at Birmingham Children's Hospital, Alder Hey Children's Hospital, the Royal Victoria Infirmary in Newcastle and Nottingham Children's Hospital for scanning the patients in this study. We would also like to thank Selene Rowe at Nottingham University Hospitals NHS Trust for help with gaining MRI protocol information. Dr James Grist is funded by the Little Princess Trust (CCLGA 2017 15).

Keywords

Diffusion
Machine learning
Perfusion

Access to Document

10.1016/j.nicl.2020.102172Licence: CC BY 3.0

Distinguishing between paediatric brain tumour types
Creative Commons Attribution 4.0 International (CC BY 4.0)
Accepted author manuscript, 946 KBLicence: CC BY 3.0
1-s2.0-S2213158220300115-main
© 2020 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/BY/4.0/).
Final published version, 599 KBLicence: CC BY 3.0

Cite this

Grist, J. T., Withey, S., Macpherson, L., Oates, A., Powell, S., Novak, J., Abernethy, L., Pizer, B., Grundy, R., Bailey, S., Mitra, D., Arvanitis, T. N., Auer, D. P., Avula, S., & Peet, A. C. (2020). Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study. NeuroImage: Clinical, 25, Article 102172. https://doi.org/10.1016/j.nicl.2020.102172

@article{d0b431f3417f4af1a62b0e16b43a6263,

title = "Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study",

abstract = "The imaging and subsequent accurate diagnosis of paediatric brain tumours presents a radiological challenge, with magnetic resonance imaging playing a key role in providing tumour specific imaging information. Diffusion weighted and perfusion imaging are commonly used to aid the non-invasive diagnosis of children's brain tumours, but are usually evaluated by expert qualitative review. Quantitative studies are mainly single centre and single modality. The aim of this work was to combine multi-centre diffusion and perfusion imaging, with machine learning, to develop machine learning based classifiers to discriminate between three common paediatric tumour types. The results show that diffusion and perfusion weighted imaging of both the tumour and whole brain provide significant features which differ between tumour types, and that combining these features gives the optimal machine learning classifier with >80% predictive precision. This work represents a step forward to aid in the non-invasive diagnosis of paediatric brain tumours, using advanced clinical imaging.",

keywords = "Diffusion, Machine learning, Perfusion",

author = "Grist, {James T.} and Stephanie Withey and Lesley Macpherson and Adam Oates and Stephen Powell and Jan Novak and Laurence Abernethy and Barry Pizer and Richard Grundy and Simon Bailey and Dipayan Mitra and Arvanitis, {Theodoros N.} and Auer, {Dorothee P.} and Shivaram Avula and Peet, {Andrew C}",

note = "{\textcopyright} 2020 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/BY/4.0/). Funding: We would like to acknowledge funding from the Cancer Research UK and EPSRC Cancer Imaging Programme at the Children's Cancer and Leukaemia Group (CCLG) in association with the MRC and Department of Health (England) (C7809/A10342), the Cancer Research UK and NIHR Experimental Cancer Medicine Centre Paediatric Network (C8232/A25261), the Medical Research Council – Health Data Research UK Substantive Site and Help Harry Help Others charity. Professor Peet is funded through an NIHR Research Professorship, NIHR-RP-R2-12-019. Stephen Powell gratefully acknowledges financial support from EPSRC through a studentship from the Physical Sciences for Health Centre for Doctoral Training (EP/L016346/1). Professor Theodoros N Arvanitis is partially supported by Health Data Research UK, which is funded by the UK Medical Research Council, Engineering and Physical Sciences Research Council, Economic and Social Research Council, Department of Health and Social Care (England), Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research and Development Division (Welsh Government), Public Health Agency (Northern Ireland), British Heart Foundation and Wellcome Trust. We would also like to acknowledge the MR radiographers at Birmingham Children's Hospital, Alder Hey Children's Hospital, the Royal Victoria Infirmary in Newcastle and Nottingham Children's Hospital for scanning the patients in this study. We would also like to thank Selene Rowe at Nottingham University Hospitals NHS Trust for help with gaining MRI protocol information. Dr James Grist is funded by the Little Princess Trust (CCLGA 2017 15).",

year = "2020",

month = feb,

day = "15",

doi = "10.1016/j.nicl.2020.102172",

language = "English",

volume = "25",

journal = "NeuroImage: Clinical",

issn = "2213-1582",

publisher = "Elsevier",

}

Grist, JT, Withey, S, Macpherson, L, Oates, A, Powell, S, Novak, J, Abernethy, L, Pizer, B, Grundy, R, Bailey, S, Mitra, D, Arvanitis, TN, Auer, DP, Avula, S & Peet, AC 2020, 'Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study', NeuroImage: Clinical, vol. 25, 102172. https://doi.org/10.1016/j.nicl.2020.102172

TY - JOUR

T1 - Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study

AU - Grist, James T.

AU - Withey, Stephanie

AU - Macpherson, Lesley

AU - Oates, Adam

AU - Powell, Stephen

AU - Novak, Jan

AU - Abernethy, Laurence

AU - Pizer, Barry

AU - Grundy, Richard

AU - Bailey, Simon

AU - Mitra, Dipayan

AU - Arvanitis, Theodoros N.

AU - Auer, Dorothee P.

AU - Avula, Shivaram

AU - Peet, Andrew C

N1 - © 2020 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/BY/4.0/). Funding: We would like to acknowledge funding from the Cancer Research UK and EPSRC Cancer Imaging Programme at the Children's Cancer and Leukaemia Group (CCLG) in association with the MRC and Department of Health (England) (C7809/A10342), the Cancer Research UK and NIHR Experimental Cancer Medicine Centre Paediatric Network (C8232/A25261), the Medical Research Council – Health Data Research UK Substantive Site and Help Harry Help Others charity. Professor Peet is funded through an NIHR Research Professorship, NIHR-RP-R2-12-019. Stephen Powell gratefully acknowledges financial support from EPSRC through a studentship from the Physical Sciences for Health Centre for Doctoral Training (EP/L016346/1). Professor Theodoros N Arvanitis is partially supported by Health Data Research UK, which is funded by the UK Medical Research Council, Engineering and Physical Sciences Research Council, Economic and Social Research Council, Department of Health and Social Care (England), Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research and Development Division (Welsh Government), Public Health Agency (Northern Ireland), British Heart Foundation and Wellcome Trust. We would also like to acknowledge the MR radiographers at Birmingham Children's Hospital, Alder Hey Children's Hospital, the Royal Victoria Infirmary in Newcastle and Nottingham Children's Hospital for scanning the patients in this study. We would also like to thank Selene Rowe at Nottingham University Hospitals NHS Trust for help with gaining MRI protocol information. Dr James Grist is funded by the Little Princess Trust (CCLGA 2017 15).

PY - 2020/2/15

Y1 - 2020/2/15

N2 - The imaging and subsequent accurate diagnosis of paediatric brain tumours presents a radiological challenge, with magnetic resonance imaging playing a key role in providing tumour specific imaging information. Diffusion weighted and perfusion imaging are commonly used to aid the non-invasive diagnosis of children's brain tumours, but are usually evaluated by expert qualitative review. Quantitative studies are mainly single centre and single modality. The aim of this work was to combine multi-centre diffusion and perfusion imaging, with machine learning, to develop machine learning based classifiers to discriminate between three common paediatric tumour types. The results show that diffusion and perfusion weighted imaging of both the tumour and whole brain provide significant features which differ between tumour types, and that combining these features gives the optimal machine learning classifier with >80% predictive precision. This work represents a step forward to aid in the non-invasive diagnosis of paediatric brain tumours, using advanced clinical imaging.

AB - The imaging and subsequent accurate diagnosis of paediatric brain tumours presents a radiological challenge, with magnetic resonance imaging playing a key role in providing tumour specific imaging information. Diffusion weighted and perfusion imaging are commonly used to aid the non-invasive diagnosis of children's brain tumours, but are usually evaluated by expert qualitative review. Quantitative studies are mainly single centre and single modality. The aim of this work was to combine multi-centre diffusion and perfusion imaging, with machine learning, to develop machine learning based classifiers to discriminate between three common paediatric tumour types. The results show that diffusion and perfusion weighted imaging of both the tumour and whole brain provide significant features which differ between tumour types, and that combining these features gives the optimal machine learning classifier with >80% predictive precision. This work represents a step forward to aid in the non-invasive diagnosis of paediatric brain tumours, using advanced clinical imaging.

KW - Diffusion

KW - Machine learning

KW - Perfusion

UR - https://linkinghub.elsevier.com/retrieve/pii/S2213158220300115

UR - http://www.scopus.com/inward/record.url?scp=85078834345&partnerID=8YFLogxK

U2 - 10.1016/j.nicl.2020.102172

DO - 10.1016/j.nicl.2020.102172

M3 - Article

C2 - 32032817

SN - 2213-1582

VL - 25

JO - NeuroImage: Clinical

JF - NeuroImage: Clinical

M1 - 102172

ER -

Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this