AGA3DNet: Anatomy-Guided Gaussian Priors with Multi-view xLSTM for 3D Brain MRI Subtype Classification
For clinicians and researchers in medical imaging, this work provides an interpretable, annotation-efficient method for 3D brain MRI classification, though it is incremental and limited by single-cohort evaluation.
AGA3DNet introduces anatomy-guided Gaussian priors from radiology reports and multi-view xLSTM aggregation for 3D brain MRI subtype classification, achieving improved balanced performance over baselines on a retrospective institutional cohort.
Accurate 3D brain MRI subtype classification benefits from both localized anatomical cues and long-range contextual reasoning. We present AGA3DNet, a report-grounded framework that incorporates brief anatomical phrases extracted from radiology reports as a soft anatomical prior channel and fuses it with a lightweight 3D CNN and multi-view xLSTM aggregation. Specifically, extracted anatomical phrases are mapped to atlas-defined regions and converted into smooth spatial priors using a signed-distance transform followed by Gaussian weighting, providing interpretable, anatomy-grounded guidance without requiring dense voxel annotations. We evaluate AGA3DNet on a retrospective institutional brain MRI cohort for abnormal subtype discrimination and compare against reproducible 3D classification baselines. AGA3DNet achieves improved overall balance across performance metrics and supports clinically interpretable localization through the prior channel. We discuss limitations related to single-cohort evaluation and the lack of large-scale public brain MRI datasets paired with radiology reports under broadly usable terms.