# Radiological Predictors of Cognitive Impairment in Paediatric Brain Tumours Using Multiparametric Magnetic Resonance Imaging: A Review of Current Practice, Challenges and Future Directions

## TL;DR

This paper reviews how brain imaging can help predict cognitive problems in children with brain tumors, highlighting challenges and future directions.

## Contribution

The paper introduces the use of multiparametric MRI combined with AI to better understand and predict cognitive impairment in pediatric brain tumor patients.

## Key findings

- Multiparametric MRI can identify risk factors like tumor location and brain damage linked to cognitive impairment.
- Advanced MRI sequences provide physiological insights but face clinical limitations due to long scanning times and analysis difficulties.
- Machine learning offers new ways to analyze complex data for predicting cognitive outcomes in pediatric brain tumor patients.

## Abstract

While many children with brain tumours survive to adulthood, brain damage from tumours and their treatment impact future quality of life. Cognitive impairment, which involves thinking processes, learning and academic performance, is a key issue. Many factors contribute to cognitive impairment with tumours occurring at any age, in different locations with various tumour types requiring different treatments. Patients have varying combinations of risk factors, making it difficult for traditional statistical techniques to determine the causes of cognitive impairment. This review focuses on how brain imaging can be used to predict cognitive impairment. We discuss the challenges and possible solutions for this research including the need for large patient numbers requiring multi-site collaboration and variations in imaging performed. We discuss how imaging data can be combined with health and treatment data using artificial intelligence techniques to identify the key drivers of cognitive impairment and those children likely to be at high-risk.

Paediatric brain tumours and their treatments are associated with long-term cognitive impairment. While the aetiology of cognitive impairment is complex and multifactorial, multiparametric Magnetic Resonance Imaging (MRI) can identify many risk factors including tumour location, damage to eloquent structures and tumour phenotype. Hydrocephalus and raised intracranial pressure can be observed, along with risk factors for post-operative paediatric cerebellar mutism syndrome or epilepsy. MRI can also identify complications of surgery or radiotherapy and monitor treatment response. Advanced imaging sequences provide valuable information about tumour and brain physiology, but clinical use is limited by extended scanning times and difficulties in processing and analysis. Brain eloquence classifications exist, but focus on adults with neurological deficits and are outdated. For the analysis of childhood tumours, limited numbers within tumour subgroups and the investigation of long-term outcomes necessitate using historical scans and/or multi-site collaboration. Variable imaging quality and differing acquisition parameters limit the use of segmentation algorithms and radiomic analysis. Harmonisation can standardise imaging in collaborative research, but can be challenging, while data-sharing produces further logistical challenges. Consequently, most research consists of small single-centre studies limited to regional analyses of tumour location. Technological advances reducing scanning times increase the feasibility of clinical acquisition of high-resolution standardised imaging including advanced physiological sequences. The RAPNO and SIOPE paediatric brain tumour imaging guidelines have improved image standardisation, which will benefit future collaborative imaging research. Modern machine learning techniques provide more nuanced approaches for integration and analysis of the complex and multifactorial data involved in cognitive outcome prediction.