Noise suppression of proton magnetic resonance spectroscopy improves paediatric brain tumour classification.

Proton magnetic resonance spectroscopy (1H-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 1H-MRS. Eighty-three/forty-two children with either an ependymoma (ages 4.6 ± 5.3/9.3 ± 5.4), a medulloblastoma (ages 6.9 ± 3.5/6.5 ± 4.4), or a pilocytic astrocytoma (8.0 ± 3.6/6.3 ± 5.0), recruited from four centres across England, were scanned with 1.5T/3T short-echo-time point-resolved spectroscopy. The acquired raw 1H-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 1H-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 1H-MRS. The study shows that fitting-based signal-to-noise ratios of clinical 1H-MRS can be significantly improved by using AWNS with insignificantly altered line width, and the post-noise-suppression 1H-MRS may have better diagnostic performance for paediatric brain tumours.

Characterisation of paediatric brain tumours by their MRS metabolite profiles.

1H-magnetic resonance spectroscopy (MRS) has the potential to improve the noninvasive diagnostic accuracy for paediatric brain tumours. However, studies analysing large, comprehensive, multicentre datasets are lacking, hindering translation to widespread clinical practice. Single-voxel MRS (point-resolved single-voxel spectroscopy sequence, 1.5 T: echo time [TE] 23-37 ms/135-144 ms, repetition time [TR] 1500 ms; 3 T: TE 37-41 ms/135-144 ms, TR 2000 ms) was performed from 2003 to 2012 during routine magnetic resonance imaging for a suspected brain tumour on 340 children from five hospitals with 464 spectra being available for analysis and 281 meeting quality control. Mean spectra were generated for 13 tumour types. Mann-Whitney U-tests and Kruskal-Wallis tests were used to compare mean metabolite concentrations. Receiver operator characteristic curves were used to determine the potential for individual metabolites to discriminate between specific tumour types. Principal component analysis followed by linear discriminant analysis was used to construct a classifier to discriminate the three main central nervous system tumour types in paediatrics. Mean concentrations of metabolites were shown to differ significantly between tumour types. Large variability existed across each tumour type, but individual metabolites were able to aid discrimination between some tumour types of importance. Complete metabolite profiles were found to be strongly characteristic of tumour type and, when combined with the machine learning methods, demonstrated a diagnostic accuracy of 93% for distinguishing between the three main tumour groups (medulloblastoma, pilocytic astrocytoma and ependymoma). The accuracy of this approach was similar even when data of marginal quality were included, greatly reducing the proportion of MRS excluded for poor quality. Children's brain tumours are strongly characterised by MRS metabolite profiles readily acquired during routine clinical practice, and this information can be used to support noninvasive diagnosis. This study provides both key evidence and an important resource for the future use of MRS in the diagnosis of children's brain tumours.

Metabolite profiles of medulloblastoma for rapid and non-invasive detection of molecular disease groups.

BACKGROUND: The malignant childhood brain tumour, medulloblastoma, is classified clinically into molecular groups which guide therapy. DNA-methylation profiling is the current classification 'gold-standard', typically delivered 3-4 weeks post-surgery. Pre-surgery non-invasive diagnostics thus offer significant potential to improve early diagnosis and clinical management. Here, we determine tumour metabolite profiles of the four medulloblastoma groups, assess their diagnostic utility using tumour tissue and potential for non-invasive diagnosis using in vivo magnetic resonance spectroscopy (MRS). METHODS: Metabolite profiles were acquired by high-resolution magic-angle spinning NMR spectroscopy (MAS) from 86 medulloblastomas (from 59 male and 27 female patients), previously classified by DNA-methylation array (WNT (n = 9), SHH (n = 22), Group3 (n = 21), Group4 (n = 34)); RNA-seq data was available for sixty. Unsupervised class-discovery was performed and a support vector machine (SVM) constructed to assess diagnostic performance. The SVM classifier was adapted to use only metabolites (n = 10) routinely quantified from in vivo MRS data, and re-tested. Glutamate was assessed as a predictor of overall survival. FINDINGS: Group-specific metabolite profiles were identified; tumours clustered with good concordance to their reference molecular group (93%). GABA was only detected in WNT, taurine was low in SHH and lipids were high in Group3. The tissue-based metabolite SVM classifier had a cross-validated accuracy of 89% (100% for WNT) and, adapted to use metabolites routinely quantified in vivo, gave a combined classification accuracy of 90% for SHH, Group3 and Group4. Glutamate predicted survival after incorporating known risk-factors (HR = 3.39, 95% CI 1.4-8.1, p = 0.025). INTERPRETATION: Tissue metabolite profiles characterise medulloblastoma molecular groups. Their combination with machine learning can aid rapid diagnosis from tissue and potentially in vivo. Specific metabolites provide important information; GABA identifying WNT and glutamate conferring poor prognosis. FUNDING: Children with Cancer UK, Cancer Research UK, Children's Cancer North and a Newcastle University PhD studentship.