analiza aiqbench
This arXiv preprint proposes SYMBA, a self-supervised pretraining method for structural brain MRI that uses anatomically constrained masking and an MS-SSIM reconstruction loss. Its most useful feature is the evaluation design: frozen linear probing on two unseen datasets tests out-of-distribution generalization more strictly than most neuroimaging papers. The reported gains over neuroimaging foundation models (e.g., 0.930 AUROC for AD classification) are unreviewed, so readers should wait for independent replication before treating them as settled.
Systematic Morphometric Brain Autoencoding for Representation Learning in Neurodegenerative Diseases
arXiv:2610.37074v1 Announce Type: cross Abstract: Early identification of neurodegenerative disorders using structural T1-weighted MRI is essential for timely clinical intervention, yet supervised deep learning models often struggle to generalize due to limited annotations and scanner-induced distribution shift. Self-supervised learning offers a promising alternative; however, existing approaches are largely adapted from natural image paradigms, relying on contrastive objectives or generic masked reconstruction with voxel-wise losses, which may not fully capture the distributed morphometric patterns associated with neurodegeneration. We introduce SYMBA (SYstematic Morphometric Brain Autoencoding), a self-supervised pretraining framework specifically designed for structural brain MRI. SYMBA integrates anatomically constrained masking, a multi-scale structural similarity (MS-SSIM) reconstruction objective, and a progressive curriculum that transitions from local anatomical detail to global brain morphology. These components explicitly incorporate neuroanatomical structure into the self-supervised objective rather than relying on generic image priors. Pretrained on 6,953 T1-weighted MRI scans from nine heterogeneous cohorts, SYMBA is evaluated using frozen linear probing on two independent unseen datasets, enabling a strict assessment of out-of-distribution generalization. Across multiple clinical tasks, SYMBA consistently outperforms recent neuroimaging foundation models, achieving 0.930 AUROC for Alzheimer's disease classification, 0.772 for mild cognitive impairment conversion prediction, and strong performance in amyloid status prediction. In low-label regimes, SYMBA demonstrates high sample efficiency, reaching approximately 0.90 AUROC for AD/CN classification using only six labeled subjects.
Abstract:Early identification of neurodegenerative disorders using structural T1-weighted MRI is essential for timely clinical intervention, yet supervised deep learning models often struggle to generalize due to limited annotations and scanner-induced distribution shift. Self-supervised learning offers a promising alternative; however, existing approaches are largely adapted from natural image paradigms, relying on contrastive objectives or generic masked reconstruction with voxel-wise losses, which may not fully capture the distributed morphometric patterns associated with neurodegeneration. We introduce SYMBA (SYstematic Morphometric Brain Autoencoding), a self-supervised pretraining framework specifically designed for structural brain MRI. SYMBA integrates anatomically constrained masking, a multi-scale structural similarity (MS-SSIM) reconstruction objective, and a progressive curriculum that transitions from local anatomical detail to global brain morphology. These components explicitly incorporate neuroanatomical structure into the self-supervised objective rather than relying on generic image priors. Pretrained on 6,953 T1-weighted MRI scans from nine heterogeneous cohorts, SYMBA is evaluated using frozen linear probing on two independent unseen datasets, enabling a strict assessment of out-of-distribution generalization. Across multiple clinical tasks, SYMBA consistently outperforms recent neuroimaging foundation models, achieving 0.930 AUROC for Alzheimer's disease classification, 0.772 for mild cognitive impairment conversion prediction, and strong performance in amyloid status prediction. In low-label regimes, SYMBA demonstrates high sample efficiency, reaching approximately 0.90 AUROC for AD/CN classification using only six labeled subjects.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2610.37074 [cs.CV]
(or arXiv:2610.37074v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.37074 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 312 cuvinte
Subiecte conexe
Multi-Modal Graph Neural Network with Transformer-Guided Adaptive Diffusion for Preclinical Alzheimer Classification
arXiv · 3 iun. 2026
Explaining Unsupervised Disease Staging in Huntington's Disease: Insights into Model Representations and Clusters
arXiv · 10 iun. 2026
Explaining Unsupervised Disease Staging in Huntington's Disease: Insights into Model Representations and Clusters
arXiv · 8 iun. 2026
Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative Screening
arXiv · 16 iun. 2026