Research map / Probabilistic and scientific modeling / Dynamical systems
Learning Distributions of Shape Trajectories From Longitudinal Datasets: A Hierarchical Model on a Manifold of Diffeomorphisms
Alexandre Bône, Olivier Colliot, Stanley Durrleman
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use longitudinal deformation-model shape features instead of a hippocampal volume-versus-age slope | ADNI MCIc vs CN classification · ADNI test subjects with varying numbers of observations | classification score: 71% ±4.5 vs 50% ±5.0; 77% ±4.3 vs 58% ±4.9; 79% ±4.1 vs 67% ±4.7; 77% ±4.2 vs 77% ±4.2; 83% ±3.7 vs 80% ±4.0 | Improved |
| Combine shape-model features with the naive volume-slope feature (ablation) | ADNI MCIc vs CN classification · ADNI test subjects with varying numbers of observations | classification score: 58% ±5.0; 68% ±4.7; 80% ±4.0; 82% ±3.8; 86% ±3.4 | Mixed |
| Provide more longitudinal observations per test subject (ablation) | Longitudinal deformation-model classification · ADNI MCIc vs CN classification | classification score: 71% ±4.5; 77% ±4.3; 79% ±4.1; 77% ±4.2; 83% ±3.7 | Mixed |
| Model subject-specific acceleration factors | Hippocampal atrophy trajectories in MCIc subjects · ADNI MCIc, female versus male subjects | acceleration factor αi: p = 0.045 | Improved |
| Model subject-specific time shifts | Hippocampal atrophy trajectories in MCIc subjects · ADNI MCIc, APOE4 allele groups | time-shift τi: p = 0.017 and 0.015 | Improved |
Closest papers by meaning
- A Bayesian Mixed-Effects Model to Learn Trajectories of Changes from Repeated Manifold-Valued Observations (JMLR 2017 · similarity 0.90)
- BrainODE: Neural Shape Dynamics for Age- and Disease-aware Brain Trajectories (NeurIPS 2025 · similarity 0.90)
- Learning Riemannian metric for disease progression modeling (NeurIPS 2021 · similarity 0.89)
- Unscrambling disease progression at scale: fast inference of event permutations with optimal transport (NeurIPS 2024 · similarity 0.86)
- Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories (ICLR 2025 · similarity 0.86)
- Denoising Functional Maps: Diffusion Models for Shape Correspondence (CVPR 2025 · similarity 0.85)
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.
