Breathing Freely: Self-supervised Liver T1rho Mapping from A Single T1rho-weighted Image

Chaoxing Huang, Yurui Qian, Jian Hou, Baiyan Jiang, Queenie Chan, Vincent Wong, Winne Chu, Weitian Chen
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:565-575, 2022.

Abstract

Quantitative T1rho imaging is a promising technique for assessment of chronic liver disease. The standard approach requires acquisition of multiple T1rho-weighted images of the liver to quantify T1rho relaxation time. The quantification accuracy can be affected by respiratory motion if the subjects cannot hold the breath during the scan. To tackle this problem, we propose a self-supervised mapping method by taking only one T1rho-weighted image to do the mapping. Our method takes into account of signal scale variations in MR scan when performing T1rho quantification. Preliminary experimental results show that our method can achieve better mapping performance than the traditional fitting method, particularly in free-breathing scenarios.

Cite this Paper


BibTeX
@InProceedings{pmlr-v172-huang22a, title = {Breathing Freely: Self-supervised Liver T1rho Mapping from A Single T1rho-weighted Image}, author = {Huang, Chaoxing and Qian, Yurui and Hou, Jian and Jiang, Baiyan and Chan, Queenie and Wong, Vincent and Chu, Winne and Chen, Weitian}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {565--575}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/huang22a/huang22a.pdf}, url = {https://proceedings.mlr.press/v172/huang22a.html}, abstract = {Quantitative T1rho imaging is a promising technique for assessment of chronic liver disease. The standard approach requires acquisition of multiple T1rho-weighted images of the liver to quantify T1rho relaxation time. The quantification accuracy can be affected by respiratory motion if the subjects cannot hold the breath during the scan. To tackle this problem, we propose a self-supervised mapping method by taking only one T1rho-weighted image to do the mapping. Our method takes into account of signal scale variations in MR scan when performing T1rho quantification. Preliminary experimental results show that our method can achieve better mapping performance than the traditional fitting method, particularly in free-breathing scenarios.} }
Endnote
%0 Conference Paper %T Breathing Freely: Self-supervised Liver T1rho Mapping from A Single T1rho-weighted Image %A Chaoxing Huang %A Yurui Qian %A Jian Hou %A Baiyan Jiang %A Queenie Chan %A Vincent Wong %A Winne Chu %A Weitian Chen %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-huang22a %I PMLR %P 565--575 %U https://proceedings.mlr.press/v172/huang22a.html %V 172 %X Quantitative T1rho imaging is a promising technique for assessment of chronic liver disease. The standard approach requires acquisition of multiple T1rho-weighted images of the liver to quantify T1rho relaxation time. The quantification accuracy can be affected by respiratory motion if the subjects cannot hold the breath during the scan. To tackle this problem, we propose a self-supervised mapping method by taking only one T1rho-weighted image to do the mapping. Our method takes into account of signal scale variations in MR scan when performing T1rho quantification. Preliminary experimental results show that our method can achieve better mapping performance than the traditional fitting method, particularly in free-breathing scenarios.
APA
Huang, C., Qian, Y., Hou, J., Jiang, B., Chan, Q., Wong, V., Chu, W. & Chen, W.. (2022). Breathing Freely: Self-supervised Liver T1rho Mapping from A Single T1rho-weighted Image. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:565-575 Available from https://proceedings.mlr.press/v172/huang22a.html.

Related Material