AI Paper Atlas

Research map / 3D vision / Face and shape

NePhi: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registration

Lin Tian, Thomas H Greer, Raul San Jose Estepar, Roni Sengupta, Marc Niethammer

ECCV 2024 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
represent deformation with a conditioned MLP (NePhi) instead of a voxel field, single-resolutionGradICON-style registration · DirLab (single-resolution)Peak train memory (MB): 6394 -> 2466Improved
add instance optimization (200 iterations) to NePhi versus GradICON with 50 (ablation)NePhi single-resolution · DirLabmTRE (mm): 5.44 -> 1.73Improved
use multi-resolution NePhi instead of single-resolution (ablation)NePhi · DirLabmTRE (mm): 5.44 -> 2.78Improved
NePhi multi-resolution compared with multi-resolution GradICONNePhi · DirLab (multi-resolution)mTRE (mm): 1.93 -> 2.78Hurt
use NePhi instead of LapIRN in multi-resolution settingmulti-resolution registration · DirLabmTRE (mm): 4.24 -> 2.78Improved
NePhi on brain MRI instead of GradICONmulti-resolution registration · HCP brain MRIDICE: 78.7 -> 76.2 DICE, memory 6716 -> 1760 MBMixed
increase training image resolution from 21 to 175 (ablation)NePhi · DirLabmTRE (mm): 16.85 -> 5.44Improved
increase training image resolution from 175 to 256 (ablation)NePhi · DirLabmTRE (mm): 5.44 -> 5.30No clear effect
increase IO iterations from 100 to 1600 (ablation)NePhi(S) · DirLabmTRE (mm): 1.94 -> 1.51Improved
reduce regularizer sampling ratio over a wide range (ablation)NePhi · Triangles and CirclesDice and regularityNo clear effect
use gradient inverse consistency regularizer instead of diffusion regularizer in NDF instance optimization (ablation)NePhi · Triangles and Circles hollowDice at convergenceImproved
apply gradient inverse consistency to voxel-based transformation in optimization (ablation)voxel deformation field · instance optimizationregularityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy