🛰️ Daily AI Frontier
‹ back to 2026-08-04

Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability

Research Medical/Healthcare AI

Ranking

Overall 70
Content 85
Popularity 36

Observed public metrics from 1 member.

Representative image for Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability

Merged summary

TL;DR - LeDXA is a JEPA-based self-supervised vision model trained from scratch on 11,540 unlabeled whole-body DXA scans that turns routine bone-density images into representations predicting multi-system disease risk, biological age, and heritable traits. It matters because it extracts prognostic signal that conventional tabular DXA readouts discard, using far less data and compute than general-purpose foundation models.

  • Trained on 11,540 Human Phenotype Project scans and validated on 47,400 external UK Biobank scans, it beat both scanner-derived DXA measures and DINOv3 on cross-cohort prevalent disease/biomarker prediction — with ~150,000× fewer training images and ~40× fewer parameters.
  • Over a median 4.3-year UKBB follow-up it improved incident disease prediction, largest gains for hip/knee arthrosis and type 2 diabetes; 66% of incident hip arthrosis cases fell in its highest-risk quartile vs 41% for tabular measures.
  • Embeddings predicted chronological age externally (r = 0.88, MAE 2.90 years); the biological-age gap tracked disease burden, carried a 45% higher mortality hazard in the oldest-appearing quartile, and decreased in women after starting hormone-replacement therapy, suggesting modifiability.
  • GWAS on the embeddings recovered mostly known body-composition and bone-density loci, and LeDXA representations were more heritable than DINOv3's, supporting biological grounding rather than scanner artifacts.

Sources (1)

Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability

arXiv cs.CV Gil Sasson, Zachary Levine, Smadar Shilo, Sarah Kohn, Guy Lutsker, Anastasia Godneva, Adam Gabet, David Krongauz, Adina Weinberger, Yann LeCun, Randall Balestriero, Eran Segal 2026-08-03 arXiv:2608.02208
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-03 14:33:49.000377 UTC

TL;DR - LeDXA is a JEPA-based self-supervised vision model trained from scratch on 11,540 unlabeled whole-body DXA scans that turns routine bone-density images into representations predicting multi-system disease risk, biological age, and heritable traits. It matters because it extracts prognostic signal that conventional tabular DXA readouts discard, using far less data and compute than general-purpose foundation models.

  • Trained on 11,540 Human Phenotype Project scans and validated on 47,400 external UK Biobank scans, it beat both scanner-derived DXA measures and DINOv3 on cross-cohort prevalent disease/biomarker prediction — with ~150,000× fewer training images and ~40× fewer parameters.
  • Over a median 4.3-year UKBB follow-up it improved incident disease prediction, largest gains for hip/knee arthrosis and type 2 diabetes; 66% of incident hip arthrosis cases fell in its highest-risk quartile vs 41% for tabular measures.
  • Embeddings predicted chronological age externally (r = 0.88, MAE 2.90 years); the biological-age gap tracked disease burden, carried a 45% higher mortality hazard in the oldest-appearing quartile, and decreased in women after starting hormone-replacement therapy, suggesting modifiability.
  • GWAS on the embeddings recovered mostly known body-composition and bone-density loci, and LeDXA representations were more heritable than DINOv3's, supporting biological grounding rather than scanner artifacts.
item →