Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI
Study of label leakage and anatomical grounding in multimodal MRI models for Alzheimer's staging shows cognitive-score fusion accuracy of 87.3% is leakage-driven.
The authors train a ResNet18 slice-based encoder with a one-layer Transformer on 1,075 ADNI-1 T1 MRI scans, using FastSurfer segmentations and YOLOv8 localization (mAP_50 above 0.96) as anatomical reference. Grad-CAM shows the image-only classifier often attends to skull and background rather than disease-relevant structures. A CLIP-style image-tabular contrastive framework organized along a label-leakage spectrum yields 87.3% three-way accuracy with cognitive scores versus 73.0% with regional volumes, and cropping to the medial temporal lobe raises image-only accuracy from 58.7% to 65.1%. Results come from single runs on a small balanced test set with reported confidence intervals.
- Cognitive-score fusion accuracy of 87.3% treated as label-leakage upper bound, not imaging signal
- Contrastive target choice shifts image-only MCI-vs-CN accuracy between 52.4% and 73.8%
- Grad-CAM reveals classifiers attending to skull, orbits, and background regions
- Medial temporal lobe cropping improves image-only three-way accuracy from 58.7% to 65.1%
From the original article
1 min read at arxiv.orgDeep networks trained on structural MRI for Alzheimer's disease (AD) staging often reach reasonable accuracy while attending to anatomically irrelevant regions, and multimodal models that add clinical tables frequently rely on variables that were used to assign the diagnostic label in the first place.
By Paul-Gabriel Nicolae · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.