Tractometry-based Anomaly Detection for Single-subject White Matter Analysis
This work addresses the need for individual-level analysis in neuroimaging to handle rare cases and clinical heterogeneity, representing an incremental advance in applying deep autoencoders to white matter pathway data.
The authors tackled the problem of shifting from group-wise comparisons to individual diagnosis in diffusion MRI by developing a tractometry-based anomaly detection framework that learns normative white matter features and discriminates individuals at genetic risk from controls in a pediatric population, achieving discrimination between these groups.
There is an urgent need for a paradigm shift from group-wise comparisons to individual diagnosis in diffusion MRI (dMRI) to enable the analysis of rare cases and clinically-heterogeneous groups. Deep autoencoders have shown great potential to detect anomalies in neuroimaging data. We present a framework that operates on the manifold of white matter (WM) pathways to learn normative microstructural features, and discriminate those at genetic risk from controls in a paediatric population.