Predictive Modelling of Brain Disorders with Magnetic Resonance Imaging: A Systematic Review of Modelling Practices, Transparency, and Interpretability in the use of Convolutional Neural Networks

Brain disorders comprise several psychiatric and neurological disorders which can be characterised by impaired cognition, mood alteration, psychosis, depressive episodes, and neurodegeneration. Clinical diagnoses primarily rely on a combination of life history information and questionnaires, with a distinct lack of discriminative biomarkers in use for psychiatric disorders. Given that symptoms across brain conditions are associated with functional alterations of cognitive and emotional processes, which can correlate with anatomical variation, structural magnetic resonance imaging (MRI) data of the brain are an important focus of research studies, particularly for predictive modelling. With the advent of large MRI data consortia (such as the Alzheimer’s Disease Neuroimaging Initiative) facilitating a greater number of MRI-based classification studies, convolutional neural networks (CNNs) – deep learning models suited to image processing – have become increasingly popular for research into brain conditions. This has resulted in a myriad of studies reporting impressive predictive performances, demonstrating the potential clinical value of deep learning systems. However, modelling practices, transparency, and interpretability vary widely across studies, making them difficult to compare and/or reproduce, thus potentially limiting clinical applications. Here, we conduct a qualitative systematic literature review of 60 studies carrying out CNN-based predictive modelling of brain disorders using MRI data and evaluate them based on three principles – modelling practices, transparency, and interpretability. We furthermore propose several recommendations aimed at maximising the potential for the integration of CNNs into clinical frameworks.