Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping

Bulut B, Dannecker M, Sanchez T, Neves Silva S, Zalevskyi V, Jia S, Ledoux JB, Auzias G, Rousseau F, Hutter J, Rueckert D, Cuadra MB (2026)


Publication Type: Conference contribution

Publication year: 2026

Journal

Publisher: Springer Science and Business Media Deutschland GmbH

Book Volume: 16118 LNCS

Pages Range: 61-72

Conference Proceedings Title: Lecture Notes in Computer Science

Event location: Daejeon, KOR

ISBN: 9783032059963

DOI: 10.1007/978-3-032-05997-0_6

Abstract

T2 mapping in fetal brain MRI has the potential to improve characterization of the developing brain, especially at mid-field (0.55T), where T2 decay is slower. However, this is challenging as fetal MRI acquisition relies on multiple motion-corrupted stacks of thick slices, requiring slice-to-volume reconstruction (SVR) to estimate a high-resolution (HR) 3D volume. Currently, T2 mapping involves repeated acquisitions of these stacks at each echo time (TE), leading to long scan times and high sensitivity to motion. We tackle this challenge with a method that jointly reconstructs data across TEs, addressing severe motion. Our approach combines implicit neural representations with a physics-informed regularization that models T2 decay, enabling information sharing across TEs while preserving anatomical and quantitative T2 fidelity. We demonstrate state-of-the-art performance on simulated fetal brain and in vivo adult datasets with fetal-like motion. We also present the first in vivo fetal T2 mapping results at 0.55T. Our study shows potential for reducing the number of stacks per TE in T2 mapping by leveraging anatomical redundancy.

Involved external institutions

How to cite

APA:

Bulut, B., Dannecker, M., Sanchez, T., Neves Silva, S., Zalevskyi, V., Jia, S.,... Cuadra, M.B. (2026). Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping. In Daphna Link-Sourani, Esra Abaci Turk, Wietske Bastiaansen, Jana Hutter, Andrew Melbourne, Roxane Licandro (Eds.), Lecture Notes in Computer Science (pp. 61-72). Daejeon, KOR: Springer Science and Business Media Deutschland GmbH.

MLA:

Bulut, Busra, et al. "Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping." Proceedings of the 10th International Workshop on Perinatal, Preterm and Paediatric Image Analysis, PIPPI 2025, Held in Conjunction with 28th International Conference on Medical Imaging and Computer Assisted Intervention, MICCAI 2025, Daejeon, KOR Ed. Daphna Link-Sourani, Esra Abaci Turk, Wietske Bastiaansen, Jana Hutter, Andrew Melbourne, Roxane Licandro, Springer Science and Business Media Deutschland GmbH, 2026. 61-72.

BibTeX: Download