Saved in:
Bibliographic Details
Main Authors: Aftabi, Hamidreza, Yu, Faye, Switzer, Brooke, Fishman, Zachary, Prisman, Eitan, Hodgson, Antony, Whyne, Cari, Fels, Sidney, Hardisty, Michael
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22421
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909027714203648
author Aftabi, Hamidreza
Yu, Faye
Switzer, Brooke
Fishman, Zachary
Prisman, Eitan
Hodgson, Antony
Whyne, Cari
Fels, Sidney
Hardisty, Michael
author_facet Aftabi, Hamidreza
Yu, Faye
Switzer, Brooke
Fishman, Zachary
Prisman, Eitan
Hodgson, Antony
Whyne, Cari
Fels, Sidney
Hardisty, Michael
contents Predicting long-term bone remodeling after mandibular reconstruction would be of great clinical benefit, yet standard generative models struggle to maintain trajectory-level consistency and anatomical fidelity over long horizons. We introduce OsteoFlow, a flow-based framework predicting Year-1 post-operative CT scans from Day-5 scans. Our core contribution is Lyapunov-guided trajectory distillation: Unlike one-step distillation, our method distills a continuous trajectory over transport time from a registration-derived stationary velocity field teacher. Combined with a resection-aware image loss, this enforces geometric correspondence without sacrificing generative capacity. Evaluated on 344 paired regions of interest, OsteoFlow significantly outperforms state of-the-art baselines, reducing mean absolute error in the surgical resection zone by ~20%. This highlights the promise of trajectory distillation for long-term prediction. Code is available on GitHub: OsteoFlow.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22421
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OsteoFlow: Lyapunov-Guided Flow Distillation for Predicting Bone Remodeling after Mandibular Reconstruction
Aftabi, Hamidreza
Yu, Faye
Switzer, Brooke
Fishman, Zachary
Prisman, Eitan
Hodgson, Antony
Whyne, Cari
Fels, Sidney
Hardisty, Michael
Computer Vision and Pattern Recognition
Predicting long-term bone remodeling after mandibular reconstruction would be of great clinical benefit, yet standard generative models struggle to maintain trajectory-level consistency and anatomical fidelity over long horizons. We introduce OsteoFlow, a flow-based framework predicting Year-1 post-operative CT scans from Day-5 scans. Our core contribution is Lyapunov-guided trajectory distillation: Unlike one-step distillation, our method distills a continuous trajectory over transport time from a registration-derived stationary velocity field teacher. Combined with a resection-aware image loss, this enforces geometric correspondence without sacrificing generative capacity. Evaluated on 344 paired regions of interest, OsteoFlow significantly outperforms state of-the-art baselines, reducing mean absolute error in the surgical resection zone by ~20%. This highlights the promise of trajectory distillation for long-term prediction. Code is available on GitHub: OsteoFlow.
title OsteoFlow: Lyapunov-Guided Flow Distillation for Predicting Bone Remodeling after Mandibular Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.22421