Joint Motion Estimation with Geometric Deformation Correction for Fetal Echo Planar Images Via Deep Learning

Jian Wang, Razieh Faghihpirayesh, Deniz Erdogmus, Ali Gholipour
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1640-1651, 2024.

Abstract

In this paper, we introduce a novel end-to-end predictive model for efficient fetal motion correction using deep neural networks. Diverging from conventional methods that estimate fetal brain motions and geometric distortions separately, our approach introduces a newly developed joint learning framework that not only reliably estimates various degrees of rigid movements, but also effectively corrects local geometric distortions of fetal brain images. Specifically, we first develop a method to learn rigid motion through a closed-form update integrated into network training. Subsequently, we incorporate a diffeomorphic deformation estimation model to guide the motion correction network, particularly in regions where local distortions and deformations occur. To the best of our knowledge, our study is the first to simultaneously track fetal motion and address geometric deformations in fetal echo-planar images. We validated our model using real fetal functional magnetic resonance imaging data with simulated and real motions. Our method demonstrates significant practical value to measure, track, and correct fetal motion in fetal MRI.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-wang24a, title = {Joint Motion Estimation with Geometric Deformation Correction for Fetal Echo Planar Images Via Deep Learning}, author = {Wang, Jian and Faghihpirayesh, Razieh and Erdogmus, Deniz and Gholipour, Ali}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1640--1651}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/wang24a/wang24a.pdf}, url = {https://proceedings.mlr.press/v250/wang24a.html}, abstract = {In this paper, we introduce a novel end-to-end predictive model for efficient fetal motion correction using deep neural networks. Diverging from conventional methods that estimate fetal brain motions and geometric distortions separately, our approach introduces a newly developed joint learning framework that not only reliably estimates various degrees of rigid movements, but also effectively corrects local geometric distortions of fetal brain images. Specifically, we first develop a method to learn rigid motion through a closed-form update integrated into network training. Subsequently, we incorporate a diffeomorphic deformation estimation model to guide the motion correction network, particularly in regions where local distortions and deformations occur. To the best of our knowledge, our study is the first to simultaneously track fetal motion and address geometric deformations in fetal echo-planar images. We validated our model using real fetal functional magnetic resonance imaging data with simulated and real motions. Our method demonstrates significant practical value to measure, track, and correct fetal motion in fetal MRI.} }
Endnote
%0 Conference Paper %T Joint Motion Estimation with Geometric Deformation Correction for Fetal Echo Planar Images Via Deep Learning %A Jian Wang %A Razieh Faghihpirayesh %A Deniz Erdogmus %A Ali Gholipour %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-wang24a %I PMLR %P 1640--1651 %U https://proceedings.mlr.press/v250/wang24a.html %V 250 %X In this paper, we introduce a novel end-to-end predictive model for efficient fetal motion correction using deep neural networks. Diverging from conventional methods that estimate fetal brain motions and geometric distortions separately, our approach introduces a newly developed joint learning framework that not only reliably estimates various degrees of rigid movements, but also effectively corrects local geometric distortions of fetal brain images. Specifically, we first develop a method to learn rigid motion through a closed-form update integrated into network training. Subsequently, we incorporate a diffeomorphic deformation estimation model to guide the motion correction network, particularly in regions where local distortions and deformations occur. To the best of our knowledge, our study is the first to simultaneously track fetal motion and address geometric deformations in fetal echo-planar images. We validated our model using real fetal functional magnetic resonance imaging data with simulated and real motions. Our method demonstrates significant practical value to measure, track, and correct fetal motion in fetal MRI.
APA
Wang, J., Faghihpirayesh, R., Erdogmus, D. & Gholipour, A.. (2024). Joint Motion Estimation with Geometric Deformation Correction for Fetal Echo Planar Images Via Deep Learning. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1640-1651 Available from https://proceedings.mlr.press/v250/wang24a.html.

Related Material