Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Proton magnetic resonance spectroscopy (1 H-MRS) is increasingly used for clinical brain tumour diagnosis, but suffers from limited spectral quality. This retrospective and comparative study aims at improving paediatric brain tumour classification by performing noise suppression on clinical 1 H-MRS. Eighty-three/forty-two children with either an ependymoma (ages 4.6 ± $$ \pm $$ 5.3/9.3 ± $$ \pm $$ 5.4), a medulloblastoma (ages 6.9 ± $$ \pm $$ 3.5/6.5 ± $$ \pm $$ 4.4), or a pilocytic astrocytoma (8.0 ± $$ \pm $$ 3.6/6.3 ± $$ \pm $$ 5.0), recruited from four centres across England, were scanned with 1.5T/3T short-echo-time point-resolved spectroscopy. The acquired raw 1 H-MRS was quantified by using Totally Automatic Robust Quantitation in NMR (TARQUIN), assessed by experienced spectroscopists, and processed with adaptive wavelet noise suppression (AWNS). Metabolite concentrations were extracted as features, selected based on multiclass receiver operating characteristics, and finally used for identifying brain tumour types with supervised machine learning. The minority class was oversampled through the synthetic minority oversampling technique for comparison purposes. Post-noise-suppression 1 H-MRS showed significantly elevated signal-to-noise ratios (P < .05, Wilcoxon signed-rank test), stable full width at half-maximum (P > .05, Wilcoxon signed-rank test), and significantly higher classification accuracy (P < .05, Wilcoxon signed-rank test). Specifically, the cross-validated overall and balanced classification accuracies can be improved from 81% to 88% overall and 76% to 86% balanced for the 1.5T cohort, whilst for the 3T cohort they can be improved from 62% to 76% overall and 46% to 56%, by applying Naïve Bayes on the oversampled 1 H-MRS. The study shows that fitting-based signal-to-noise ratios of clinical 1 H-MRS can be significantly improved by using AWNS with insignificantly altered line width, and the post-noise-suppression 1 H-MRS may have better diagnostic performance for paediatric brain tumours.

Original publication

DOI

10.1002/nbm.5129

Type

Journal article

Journal

NMR Biomed

Publication Date

17/03/2024

Keywords

machine learning, metabolite concentration, noise suppression, paediatric brain tumour, proton magnetic resonance spectroscopy, wavelet