Abstract
Non-rigid medical image registration (NRR) is critical for aligning multi-modal anatomical structures but is challenged by complex physiological deformations (e.g., respiration, contrast variations). Traditional NRR incurs high computational costs and requires extensive parameter tuning, while deep learning (DL) approaches rely on restrictive task-specific retraining. Addressing these limitations, we introduce a novel AI-driven 3D NRR framework that generalizes across diverse imaging modalities and anatomies. By eliminating anatomy- and modality-specific customization, our approach provides an efficient, universal solution for streamlined integration into heterogeneous clinical workflows.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MLMI_018.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=dJbwhDlXH0
BibTex
@InProceedings{CSne_Efficient_MICCAISAT2026,
author = { C, Sneha Sree AND Shanbhag, Dattesh D. AND Chatterjee, Sudhanya},
title = { { Efficient Test-Time Optimization via Knowledge Distillation for Modality-Agnostic Medical Image Registration } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17272},
month = {pending},
page = {pending}
}
