The aim of this study was to assess the efficacy of three-dimensional texture analysis (3D TA) of conventional MR images for the classification of childhood brain tumours in a quantitative manner. The dataset comprised pre-contrast T1 - and T2-weighted MRI series obtained from 48 children diagnosed with brain tumours (medulloblastoma, pilocytic astrocytoma and ependymoma). 3D and 2D TA were carried out on the images using first-, second- and higher order statistical methods. Six supervised classification algorithms were trained with the most influential 3D and 2D textural features, and their performances in the classification of tumour types, using the two feature sets, were compared. Model validation was carried out using the leave-one-out cross-validation (LOOCV) approach, as well as stratified 10-fold cross-validation, in order to provide additional reassurance. McNemar's test was used to test the statistical significance of any improvements demonstrated by 3D-trained classifiers. Supervised learning models trained with 3D textural features showed improved classification performances to those trained with conventional 2D features. For instance, a neural network classifier showed 12% improvement in area under the receiver operator characteristics curve (AUC) and 19% in overall classification accuracy. These improvements were statistically significant for four of the tested classifiers, as per McNemar's tests. This study shows that 3D textural features extracted from conventional T1 - and T2-weighted images can improve the diagnostic classification of childhood brain tumours. Long-term benefits of accurate, yet non-invasive, diagnostic aids include a reduction in surgical procedures, improvement in surgical and therapy planning, and support of discussions with patients' families. It remains necessary, however, to extend the analysis to a multicentre cohort in order to assess the scalability of the techniques used.

PurposeTo investigate the robustness of constrained and simultaneous intravoxel incoherent motion (IVIM) fitting methods and the estimated IVIM parameters (D, D* and f) for applications in brain and low‐perfused tissues.Materials and MethodsModel data simulations relevant to brain and low‐perfused tumor tissues were computed to assess the accuracy, relative bias, and reproducibility (CV%) of the fitting methods in estimating the IVIM parameters. The simulations were performed at a series of signal‐to‐noise ratio (SNR) levels to assess the influence of noise on the fitting.ResultsThe estimated IVIM parameters from model simulations were found significantly different (P < 0.05) using simultaneous and constrained fitting methods at low SNR. Higher accuracy and reproducibility were achieved with the constrained fitting method. Using this method, the mean error (%) for the estimated IVIM parameters at a clinically relevant SNR = 40 were D 0.35, D* 41.0 and f 4.55 for the tumor model and D 1.87, D* 2.48, and f 7.49 for the gray matter model. The most robust parameters were the IVIM‐D and IVIM‐f. The IVIM‐D* was increasingly overestimated at low perfusion.ConclusionA constrained IVIM fitting method provides more accurate and reproducible IVIM parameters in low‐perfused tissue compared with simultaneous fitting. Level of Evidence: 3J. MAGN. RESON. IMAGING 2017;45:1325–1334

To determine if apparent diffusion coefficients (ADC) can discriminate between posterior fossa brain tumours on a multicentre basis. A total of 124 paediatric patients with posterior fossa tumours (including 55 Medulloblastomas, 36 Pilocytic Astrocytomas and 26 Ependymomas) were scanned using diffusion weighted imaging across 12 different hospitals using a total of 18 different scanners. Apparent diffusion coefficient maps were produced and histogram data was extracted from tumour regions of interest. Total histograms and histogram metrics (mean, variance, skew, kurtosis and 10th, 20th and 50th quantiles) were used as data input for classifiers with accuracy determined by tenfold cross validation. Mean ADC values from the tumour regions of interest differed between tumour types, (ANOVA P < 0.001). A cut off value for mean ADC between Ependymomas and Medulloblastomas was found to be of 0.984 × 10−3 mm2 s−1 with sensitivity 80.8% and specificity 80.0%. Overall classification for the ADC histogram metrics were 85% using Naïve Bayes and 84% for Random Forest classifiers. The most commonly occurring posterior fossa paediatric brain tumours can be classified using Apparent Diffusion Coefficient histogram values to a high accuracy on a multicentre basis.