mlsanityData to 7 Oct 2026

A Cautionary Tale of Self-Supervised Learning for Imaging Biomarkers: Alzheimer's Disease Case Study

arXiv 2601.16467 ↗First posted 23 Jan 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Discovery of sensitive and biologically grounded biomarkers is essential for early detection and monitoring of Alzheimer's disease (AD). Structural MRI is widely available but typically relies on hand-crafted features such as cortical thickness or volume. We ask whether self-supervised learning (SSL) can uncover more powerful biomarkers from the same data. Existing SSL methods underperform FreeSurfer-derived features in disease classification, conversion prediction, and amyloid status prediction. We introduce Residual Noise Contrastive Estimation (R-NCE), a new SSL framework that integrates auxiliary FreeSurfer features while maximizing additional augmentation-invariant information. R-NCE outperforms traditional features and existing SSL methods across multiple benchmarks, including AD conversion prediction. To assess biological relevance, we derive Brain Age Gap (BAG) measures and perform genome-wide association studies. R-NCE-BAG shows high heritability and associations with MAPT and IRAG1, with enrichment in astrocytes and oligodendrocytes, indicating sensitivity to neurodegenerative and cerebrovascular processes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 78 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

20 of 78 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  6. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  7. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  8. 2022MONAI: An open-source framework for deep learning in healthcarecited by 438
  9. 2020TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningcited by 176
  10. 2022On the duality between contrastive and non-contrastive self-supervised learningcited by 107
  11. 2016Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarkercited by 72
  12. 2020Longitudinal Self-Supervised Learningcited by 30
8 more
  1. 2021SAME: Deformable Image Registration based on Self-supervised Anatomical Embeddingscited by 21
  2. 2021Intermediate Layers Matter in Momentum Contrastive Self Supervised Learningcited by 19
  3. 2021A Study of the Generalizability of Self-Supervised Representationscited by 18
  4. 2023Learning to Compare Longitudinal Imagescited by 12
  5. 2020Context Matters: Graph-based Self-supervised Representation Learning for Medical Imagescited by 8
  6. 2022Robust Alzheimer's Progression Modeling using Cross-Domain Self-Supervised Deep Learningcited by 1
  7. 2023DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Imagescited by 1
  8. 2023Regional Deep Atrophy: a Self-Supervised Learning Method to Automatically Identify Regions Associated With Alzheimer's Disease Progression From Longitudinal MRIcited by 1

Built on by

Not cited yet.