Skip to main content
Search

# E(3)-invariance

1 related articles

Subscribe to updates
  1. arXiv

    ADPKD genotype calls move to kidney point clouds: E3PN trains 163 times faster on one GPU, yet F1 reaches only 0.226

    Inferring autosomal dominant polycystic kidney disease (ADPKD) genotype from 3D abdominal MRI had no public benchmark, and full-abdomen voxel volumes were hard to train on a single GPU. E3PN represents each kidney as a point cloud sampled from a Gaussian-mixture density and removes orientation with principal-component coordinate canonicalization, reaching F1 0.226 on 441 patients under 10-fold cross-validation, above 3D ResNet at 0.165 and e3nn at 0.163. All three methods stay near the 0.20 chance level, so the authors position E3PN as an efficient, reproducible baseline rather than a clinically deployable classifier.

You’re all caught up