Diagnostic accuracy and added value of qualitative radiological review of 1H-magnetic resonance spectroscopy in evaluation of childhood brain tumors

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.

European Society for Paediatric Oncology (SIOPE) MRI guidelines for imaging patients with central nervous system tumours

INTRODUCTION

Standardisation of imaging acquisition is essential in facilitating multicentre studies related to childhood CNS tumours. It is important to ensure that the imaging protocol can be adopted by centres with varying imaging capabilities without compromising image quality.

MATERIALS AND METHOD

An imaging protocol has been developed by the Brain Tumour Imaging Working Group of the European Society for Paediatric Oncology (SIOPE) based on consensus among its members, which consists of neuroradiologists, imaging scientists and paediatric neuro-oncologists. This protocol has been developed to facilitate SIOPE led studies and regularly reviewed by the imaging working group.

RESULTS

The protocol consists of essential MRI sequences with imaging parameters for 1.5 and 3 Tesla MRI scanners and a set of optional sequences that can be used in appropriate clinical settings. The protocol also provides guidelines for early post-operative imaging and surveillance imaging. The complementary use of multimodal advanced MRI including diffusion tensor imaging (DTI), MR spectroscopy and perfusion imaging is encouraged, and optional guidance is provided in this publication.

CONCLUSION

The SIOPE brain tumour imaging protocol will enable consistent imaging across multiple centres involved in paediatric CNS tumour studies.

Measuring transverse relaxation rates of the major brain metabolites from single-voxel PRESS acquisitions at a single TE

PURPOSE

To compare transverse relaxation rates of brain metabolites estimated from single-TE PRESS acquisitions with more conventionally derived rates estimated from multiple-TE PRESS acquisitions.

METHODS

Single-voxel (8 mL) PRESS data within white matter from 6 subjects were acquired at five different TEs. Transverse relaxation rates R₂ of N-acetylaspartate, creatine, and choline were estimated from a single TE using full versus right-side-only sampling of the echo. These R₂ values were compared with R_2Hahn values obtained from the multiple-TE PRESS acquisitions.

RESULTS

Following baseline subtraction and RMS weighting, interindividual mean R₂ values from TE = 288 ms magnitude spectra for choline, creatine, and N-acetylaspartate were highly correlated with respective R_2Hahn values (r² = 0.99). Paired individual measurements at this TE showed less correlation (r² = 0.48), primarily due to the N-acetylaspartate resonance. Using TE = 360 ms data for N-acetylaspartate and 288 ms for choline and creatine resulted in an improved correlation coefficient (r² = 0.80). The average absolute intra-individual differences in the estimated R₂ s between single-TE and Hahn method was 9.6 ± 7.7%.

CONCLUSION

For the major brain metabolite singlets, R_2Hahn values showed correlations with more fragile measurements of R₂ from a single TE that are worthy of interest. Because the left side of long-TE spin echoes is available "for free" from an acquisition perspective, and although the single-TE method for estimating R₂ values is associated with lower precision, the reduction in scan time may be clinically helpful.

Automatic Machine Learning to Differentiate Pediatric Posterior Fossa Tumors on Routine MR Imaging

BACKGROUND AND PURPOSE

Differentiating the types of pediatric posterior fossa tumors on routine imaging may help in preoperative evaluation and guide surgical resection planning. However, qualitative radiologic MR imaging review has limited performance. This study aimed to compare different machine learning approaches to classify pediatric posterior fossa tumors on routine MR imaging.

MATERIALS AND METHODS

This retrospective study included preoperative MR imaging of 288 patients with pediatric posterior fossa tumors, including medulloblastoma (n = 111), ependymoma (n = 70), and pilocytic astrocytoma (n = 107). Radiomics features were extracted from T2-weighted images, contrast-enhanced T1-weighted images, and ADC maps. Models generated by standard manual optimization by a machine learning expert were compared with automatic machine learning via the Tree-Based Pipeline Optimization Tool for performance evaluation.

RESULTS

For 3-way classification, the radiomics model by automatic machine learning with the Tree-Based Pipeline Optimization Tool achieved a test micro-averaged area under the curve of 0.91 with an accuracy of 0.83, while the most optimized model based on the feature-selection method χ2 score and the Generalized Linear Model classifier achieved a test micro-averaged area under the curve of 0.92 with an accuracy of 0.74. Tree-Based Pipeline Optimization Tool models achieved significantly higher accuracy than average qualitative expert MR imaging review (0.83 versus 0.54, P < .001). For binary classification, Tree-Based Pipeline Optimization Tool models achieved an area under the curve of 0.94 with an accuracy of 0.85 for medulloblastoma versus nonmedulloblastoma, an area under the curve of 0.84 with an accuracy of 0.80 for ependymoma versus nonependymoma, and an area under the curve of 0.94 with an accuracy of 0.88 for pilocytic astrocytoma versus non-pilocytic astrocytoma.

CONCLUSIONS

Automatic machine learning based on routine MR imaging classified pediatric posterior fossa tumors with high accuracy compared with manual expert pipeline optimization and qualitative expert MR imaging review.