Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study

TL;DR

This study combines multi-site diffusion and perfusion MRI data with machine learning to accurately classify three common paediatric brain tumour types, achieving over 80% predictive precision.

Contribution

It introduces a multi-centre, multi-parametric MRI approach integrated with machine learning for non-invasive tumour classification, advancing prior single-centre, single-modality studies.

Findings

Diffusion and perfusion imaging features differ significantly between tumour types.

Combining multiple imaging features improves classification accuracy.

Achieved over 80% predictive precision in tumour discrimination.

Abstract

The imaging and subsequent accurate diagnosis of paediatric brain tumours presents a radiological challenge, with magnetic resonance imaging playing a key role in providing tumour specific imaging information. Diffusion weighted and perfusion imaging are commonly used to aid the non invasive diagnosis of paediatric brain tumours, but are usually evaluated by expert qualitative review. Quantitative studies are mainly single centre and single modality. The aim of this work was to combine multi centre diffusion and perfusion imaging, with machine learning, to develop machine learning based classifiers to discriminate between three common paediatric tumour types. The results show that diffusion and perfusion weighted imaging of both the tumour and whole brain provide significant features which differ between tumour types, and that combining these features gives the optimal machine learning classifier with greater than 80 percent predictive precision. This work represents a step forward to aid in the non invasive diagnosis of paediatric brain tumours, using advanced clinical imaging.