Metabolite selection for machine learning in childhood brain tumour classification

Dadi Zhao, James T. Grist, Heather E.L. Rose, Nigel P. Davies, Martin Wilson, Lesley MacPherson, Laurence J. Abernethy, Shivaram Avula, Barry Pizer, Daniel R. Gutierrez, Tim Jaspan, Paul S. Morgan, Dipayan Mitra, Simon Bailey, Vijay Sawlani, Theodoros N. Arvanitis, Yu Sun, Andrew C. Peet

Research output: Contribution to journalArticlepeer-review

3 Downloads (Pure)

Abstract

MRS can provide high accuracy in the diagnosis of childhood brain tumours when combined with machine learning. A feature selection method such as principal component analysis is commonly used to reduce the dimensionality of metabolite profiles prior to classification. However, an alternative approach of identifying the optimal set of metabolites has not been fully evaluated, possibly due to the challenges of defining this for a multi-class problem. This study aims to investigate metabolite selection from in vivo MRS for childhood brain tumour classification. Multi-site 1.5 T and 3 T cohorts of patients with a brain tumour and histological diagnosis of ependymoma, medulloblastoma and pilocytic astrocytoma were retrospectively evaluated. Dimensionality reduction was undertaken by selecting metabolite concentrations through multi-class receiver operating characteristics and compared with principal component analysis. Classification accuracy was determined through leave-one-out and k-fold cross-validation. Metabolites identified as crucial in tumour classification include myo-inositol (P < 0.05, (Formula presented.)), total lipids and macromolecules at 0.9 ppm (P < 0.05, (Formula presented.)) and total creatine (P < 0.05, (Formula presented.)) for the 1.5 T cohort, and glycine (P < 0.05, (Formula presented.)), total N-acetylaspartate (P < 0.05, (Formula presented.)) and total choline (P < 0.05, (Formula presented.)) for the 3 T cohort. Compared with the principal components, the selected metabolites were able to provide significantly improved discrimination between the tumours through most classifiers (P < 0.05). The highest balanced classification accuracy determined through leave-one-out cross-validation was 85% for 1.5 T 1H-MRS through support vector machine and 75% for 3 T 1H-MRS through linear discriminant analysis after oversampling the minority. The study suggests that a group of crucial metabolites helps to achieve better discrimination between childhood brain tumours.

Original languageEnglish
Article numbere4673
Number of pages16
JournalNMR in biomedicine
Early online date27 Jan 2022
DOIs
Publication statusE-pub ahead of print - 27 Jan 2022

Bibliographical note

Funding Information:
D.Z. was partly funded by a doctoral scholarship from the Help Harry Help Others Cancer Charity. A.C.P. is funded through an NIHR Research Professorship, NIHR‐RP‐R2‐12‐019. We would also 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 Children's Research Fund, Birmingham Women's and Children's Hospital Charities, The Children's Cancer and Leukaemia Group—Little Princess Trust (2017/15 and 2019/01), Children with Cancer (15/118), Action Medical Research (GN2181), The Brain Tumour Charity (GN2181) and Health Data Research UK (HDR UK). HDR UK 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.

Publisher Copyright:
© 2022 The Authors. NMR in Biomedicine published by John Wiley & Sons Ltd.

Keywords

  • childhood brain tumour
  • machine learning
  • metabolite concentration
  • MRS
  • multi-class classification
  • receiver operating characteristics

ASJC Scopus subject areas

  • Molecular Medicine
  • Radiology Nuclear Medicine and imaging
  • Spectroscopy

Fingerprint

Dive into the research topics of 'Metabolite selection for machine learning in childhood brain tumour classification'. Together they form a unique fingerprint.

Cite this