DRIMET: Deep Registration-based 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue

Zhangxing Bian, Fangxu Xing, Jinglun Yu, Muhan Shao, Yihao Liu, Aaron Carass, Jonghye Woo, Jerry L Prince
Medical Imaging with Deep Learning, PMLR 227:134-150, 2024.

Abstract

Tagged magnetic resonance imaging (MRI) has been used for decades to observe and quantify the detailed motion of deforming tissue. However, this technique faces several challenges such as tag fading, large motion, long computation times, and difficulties in obtaining diffeomorphic incompressible flow fields. To address these issues, this paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI. We introduce two key innovations. First, we apply a sinusoidal transformation to the harmonic phase input, which enables end-to-end training and avoids the need for phase interpolation. Second, we propose a Jacobian determinant-based learning objective to encourage incompressible flow fields for deforming biological tissues. Our method efficiently estimates 3D motion fields that are accurate, dense, and approximately diffeomorphic and incompressible. The efficacy of the method is assessed using human tongue motion during speech, and includes both healthy controls and patients that have undergone glossectomy. We show that the method outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion. The code is available.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-bian24a, title = {DRIMET: Deep Registration-based 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue}, author = {Bian, Zhangxing and Xing, Fangxu and Yu, Jinglun and Shao, Muhan and Liu, Yihao and Carass, Aaron and Woo, Jonghye and Prince, Jerry L}, booktitle = {Medical Imaging with Deep Learning}, pages = {134--150}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/bian24a/bian24a.pdf}, url = {https://proceedings.mlr.press/v227/bian24a.html}, abstract = {Tagged magnetic resonance imaging (MRI) has been used for decades to observe and quantify the detailed motion of deforming tissue. However, this technique faces several challenges such as tag fading, large motion, long computation times, and difficulties in obtaining diffeomorphic incompressible flow fields. To address these issues, this paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI. We introduce two key innovations. First, we apply a sinusoidal transformation to the harmonic phase input, which enables end-to-end training and avoids the need for phase interpolation. Second, we propose a Jacobian determinant-based learning objective to encourage incompressible flow fields for deforming biological tissues. Our method efficiently estimates 3D motion fields that are accurate, dense, and approximately diffeomorphic and incompressible. The efficacy of the method is assessed using human tongue motion during speech, and includes both healthy controls and patients that have undergone glossectomy. We show that the method outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion. The code is available.} }
Endnote
%0 Conference Paper %T DRIMET: Deep Registration-based 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue %A Zhangxing Bian %A Fangxu Xing %A Jinglun Yu %A Muhan Shao %A Yihao Liu %A Aaron Carass %A Jonghye Woo %A Jerry L Prince %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-bian24a %I PMLR %P 134--150 %U https://proceedings.mlr.press/v227/bian24a.html %V 227 %X Tagged magnetic resonance imaging (MRI) has been used for decades to observe and quantify the detailed motion of deforming tissue. However, this technique faces several challenges such as tag fading, large motion, long computation times, and difficulties in obtaining diffeomorphic incompressible flow fields. To address these issues, this paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI. We introduce two key innovations. First, we apply a sinusoidal transformation to the harmonic phase input, which enables end-to-end training and avoids the need for phase interpolation. Second, we propose a Jacobian determinant-based learning objective to encourage incompressible flow fields for deforming biological tissues. Our method efficiently estimates 3D motion fields that are accurate, dense, and approximately diffeomorphic and incompressible. The efficacy of the method is assessed using human tongue motion during speech, and includes both healthy controls and patients that have undergone glossectomy. We show that the method outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion. The code is available.
APA
Bian, Z., Xing, F., Yu, J., Shao, M., Liu, Y., Carass, A., Woo, J. & Prince, J.L.. (2024). DRIMET: Deep Registration-based 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:134-150 Available from https://proceedings.mlr.press/v227/bian24a.html.

Related Material