NEURO HAND: A weakly supervised Hierarchical Attention Network for interpretable neuroimaging abnormality Detection
This work addresses the need for automated triaging systems in radiology departments by offering an interpretable model for abnormality detection in neuroimaging, though it is incremental as it builds on existing hierarchical and attention-based methods.
The authors tackled the problem of detecting abnormalities in clinical neuroimaging data by developing a hierarchical attention network for MRI scans, which improved classification performance and provided interpretability for localization and importance scoring.
Clinical neuroimaging data is naturally hierarchical. Different magnetic resonance imaging (MRI) sequences within a series, different slices covering the head, and different regions within each slice all confer different information. In this work we present a hierarchical attention network for abnormality detection using MRI scans obtained in a clinical hospital setting. The proposed network is suitable for non-volumetric data (i.e. stacks of high-resolution MRI slices), and can be trained from binary examination-level labels. We show that this hierarchical approach leads to improved classification, while providing interpretability through either coarse inter- and intra-slice abnormality localisation, or giving importance scores for different slices and sequences, making our model suitable for use as an automated triaging system in radiology departments.