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 selection for machine learning in childhood brain tumour classification.

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, AUC=0.81±0.01 ), total lipids and macromolecules at 0.9 ppm (P < 0.05, AUC=0.78±0.01 ) and total creatine (P < 0.05, AUC=0.77±0.01 ) for the 1.5 T cohort, and glycine (P < 0.05, AUC=0.79±0.01 ), total N-acetylaspartate (P < 0.05, AUC=0.79±0.01 ) and total choline (P < 0.05, AUC=0.75±0.01 ) 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 1 H-MRS through support vector machine and 75% for 3 T 1 H-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.

Added value of magnetic resonance spectroscopy for diagnosing childhood cerebellar tumours.

1 H-magnetic resonance spectroscopy (MRS) provides noninvasive metabolite profiles with the potential to aid the diagnosis of brain tumours. Prospective studies of diagnostic accuracy and comparisons with conventional MRI are lacking. The aim of the current study was to evaluate, prospectively, the diagnostic accuracy of a previously established classifier for diagnosing the three major childhood cerebellar tumours, and to determine added value compared with standard reporting of conventional imaging. Single-voxel MRS (1.5 T, PRESS, TE 30 ms, TR 1500 ms, spectral resolution 1 Hz/point) was acquired prospectively on 39 consecutive cerebellar tumours with histopathological diagnoses of pilocytic astrocytoma, ependymoma or medulloblastoma. Spectra were analysed with LCModel and predefined quality control criteria were applied, leaving 33 cases in the analysis. The MRS diagnostic classifier was applied to this dataset. A retrospective analysis was subsequently undertaken by three radiologists, blind to histopathological diagnosis, to determine the change in diagnostic certainty when sequentially viewing conventional imaging, MRS and a decision support tool, based on the classifier. The overall classifier accuracy, evaluated prospectively, was 91%. Incorrectly classified cases, two anaplastic ependymomas, and a rare histological variant of medulloblastoma, were not well represented in the original training set. On retrospective review of conventional MRI, MRS and the classifier result, all radiologists showed a significant increase (Wilcoxon signed rank test, p < 0.001) in their certainty of the correct diagnosis, between viewing the conventional imaging and MRS with the decision support system. It was concluded that MRS can aid the noninvasive diagnosis of posterior fossa tumours in children, and that a decision support classifier helps in MRS interpretation.

Combining multi-site magnetic resonance imaging with machine learning predicts survival in pediatric brain tumors.

Brain tumors represent the highest cause of mortality in the pediatric oncological population. Diagnosis is commonly performed with magnetic resonance imaging. Survival biomarkers are challenging to identify due to the relatively low numbers of individual tumor types. 69 children with biopsy-confirmed brain tumors were recruited into this study. All participants had perfusion and diffusion weighted imaging performed at diagnosis. Imaging data were processed using conventional methods, and a Bayesian survival analysis performed. Unsupervised and supervised machine learning were performed with the survival features, to determine novel sub-groups related to survival. Sub-group analysis was undertaken to understand differences in imaging features. Survival analysis showed that a combination of diffusion and perfusion imaging were able to determine two novel sub-groups of brain tumors with different survival characteristics (p < 0.01), which were subsequently classified with high accuracy (98%) by a neural network. Analysis of high-grade tumors showed a marked difference in survival (p = 0.029) between the two clusters with high risk and low risk imaging features. This study has developed a novel model of survival for pediatric brain tumors. Tumor perfusion plays a key role in determining survival and should be considered as a high priority for future imaging protocols.

Diffusion-weighted MRI and intravoxel incoherent motion model for diagnosis of pediatric solid abdominal tumors.

BACKGROUND: Pediatric retroperitoneal tumors in the renal bed are often large and heterogeneous, and their diagnosis based on conventional imaging alone is not possible. More advanced imaging methods, such as diffusion-weighted (DW) MRI and the use of intravoxel incoherent motion (IVIM), have the potential to provide additional biomarkers that could facilitate their noninvasive diagnosis. PURPOSE: To assess the use of an IVIM model for diagnosis of childhood malignant abdominal tumors and discrimination of benign from malignant lesions. STUDY TYPE: Retrospective. POPULATION: Forty-two pediatric patients with abdominal lesions (n = 32 malignant, n = 10 benign), verified by histopathology. FIELD STRENGTH/SEQUENCE: 1.5T MRI system and a DW-MRI sequence with six b-values (0, 50, 100, 150, 600, 1000 s/mm2 ). ASSESSMENT: Parameter maps of apparent diffusion coefficient (ADC), and IVIM maps of slow diffusion coefficient (D), fast diffusion coefficient (D*), and perfusion fraction (f) were computed using a segmented fitting model. Histograms were constructed for whole-tumor regions of each parameter. STATISTICAL TESTS: Comparison of histogram parameters of and their diagnostic performance was determined using Kruskal-Wallis, Mann-Whitney U, and receiver-operating characteristic (ROC) analysis. RESULTS: IVIM parameters D* and f were significantly higher in neuroblastoma compared to Wilms' tumors (P < 0.05). The ROC analysis showed that the best diagnostic performance was achieved with D* 90th percentile (area under the curve [AUC] = 0.935; P = 0.002; cutoff value = 32,376 × 10-6 mm2 /s) and f mean values (AUC = 1.00; P < 0.001; cutoff value = 14.7) in discriminating between neuroblastoma (n = 11) and Wilms' tumors (n = 8). Discrimination between tumor types was not possible with IVIM D or ADC parameters. Malignant tumors revealed significantly lower ADC, D, and higher D* values than in benign lesions (all P < 0.05). DATA CONCLUSION: IVIM perfusion parameters could distinguish between malignant childhood tumor types, providing potential imaging biomarkers for their diagnosis. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1475-1486.

Application of pattern recognition techniques for classification of pediatric brain tumors by in vivo 3T 1 H-MR spectroscopy-A multi-center study.

PURPOSE: 3T magnetic resonance scanners have boosted clinical application of 1 H-MR spectroscopy (MRS) by offering an improved signal-to-noise ratio and increased spectral resolution, thereby identifying more metabolites and extending the range of metabolic information. Spectroscopic data from clinical 1.5T MR scanners has been shown to discriminate between pediatric brain tumors by applying machine learning techniques to further aid diagnosis. The purpose of this multi-center study was to investigate the discriminative potential of metabolite profiles obtained from 3T scanners in classifying pediatric brain tumors. METHODS: A total of 41 pediatric patients with brain tumors (17 medulloblastomas, 20 pilocytic astrocytomas, and 4 ependymomas) were scanned across four different hospitals. Raw spectroscopy data were processed using TARQUIN. Borderline synthetic minority oversampling technique was used to correct for the data skewness. Different classifiers were trained using linear discriminative analysis, support vector machine, and random forest techniques. RESULTS: Support vector machine had the highest balanced accuracy for discriminating the three tumor types. The balanced accuracy achieved was higher than the balanced accuracy previously reported for similar multi-center dataset from 1.5T magnets with echo time 20 to 32 ms alone. CONCLUSION: This study showed that 3T MRS can detect key differences in metabolite profiles for the main types of childhood tumors. Magn Reson Med 79:2359-2366, 2018. © 2017 International Society for Magnetic Resonance in Medicine.