Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Sep;50(9):5331-5342.
doi: 10.1002/mp.16643. Epub 2023 Aug 1.

Accelerated respiratory-resolved 4D-MRI with separable spatio-temporal neural networks

Maarten L Terpstra  1   2 , Matteo Maspero  1   2 , Joost J C Verhoeff  1 , Cornelis A T van den Berg  1   2
Affiliations

Accelerated respiratory-resolved 4D-MRI with separable spatio-temporal neural networks

Maarten L Terpstra et al. Med Phys. 2023 Sep.

Abstract

Background: Respiratory-resolved four-dimensional magnetic resonance imaging (4D-MRI) provides essential motion information for accurate radiation treatments of mobile tumors. However, obtaining high-quality 4D-MRI suffers from long acquisition and reconstruction times.

Purpose: To develop a deep learning architecture to quickly acquire and reconstruct high-quality 4D-MRI, enabling accurate motion quantification for MRI-guided radiotherapy (MRIgRT).

Methods: A small convolutional neural network called MODEST is proposed to reconstruct 4D-MRI by performing a spatial and temporal decomposition, omitting the need for 4D convolutions to use all the spatio-temporal information present in 4D-MRI. This network is trained on undersampled 4D-MRI after respiratory binning to reconstruct high-quality 4D-MRI obtained by compressed sensing reconstruction. The network is trained, validated, and tested on 4D-MRI of 28 lung cancer patients acquired with a T1-weighted golden-angle radial stack-of-stars (GA-SOS) sequence. The 4D-MRI of 18, 5, and 5 patients were used for training, validation, and testing. Network performances are evaluated on image quality measured by the structural similarity index (SSIM) and motion consistency by comparing the position of the lung-liver interface on undersampled 4D-MRI before and after respiratory binning. The network is compared to conventional architectures such as a U-Net, which has 30 times more trainable parameters.

Results: MODEST can reconstruct high-quality 4D-MRI with higher image quality than a U-Net, despite a thirty-fold reduction in trainable parameters. High-quality 4D-MRI can be obtained using MODEST in approximately 2.5 min, including acquisition, processing, and reconstruction.

Conclusion: High-quality accelerated 4D-MRI can be obtained using MODEST, which is particularly interesting for MRIgRT.

Keywords: 4D-MRI; MR Linac; machine learning; radiotherapy; respiratory motion.

PubMed Disclaimer

References

REFERENCES

    1. Park JC, Park SH, Kim JH, et al. Liver motion during cone beam computed tomography guided stereotactic body radiation therapy. Med Phys. 2012;39:6431-6442.
    1. Ekberg L, Holmberg O, Wittgren L, Bjelkengren G, Landberg T. What margins should be added to the clinical target volume in radiotherapy treatment planning for lung cancer? Radiother Oncol. 1998;48:71-77.
    1. Song R, Tipirneni A, Johnson P, Loeffler RB, Hillenbrand CM. Evaluation of respiratory liver and kidney movements for MRI navigator gating. J Magn Reson Imaging. 2011;33:143-148.
    1. Feng M, Balter JM, Normolle D, et al. Characterization of pancreatic tumor motion using cine MRI: surrogates for tumor position should be used with caution. Int J Radiat Oncol Biol Phys. 2009;74:884-891.
    1. Wood ML, Henkelman RM. MR image artifacts from periodic motion. Med Phys. 1985;12(2):143-151.

MeSH terms

LinkOut - more resources