Deep Learning Improves Robustness of Voxelwise Kinetic Modeling for Hyperpolarized Carbon‐13 MRI
Magnetic Resonance in Medicine · 2026
DOI: 10.1002/mrm.70549 ↗At a glance
Journal article in Magnetic Resonance in Medicine, 2026. Written by Kofi Deh and 5 co-authors. Institution: Department of Physics and Astronomy, Howard University, Washington, DC, USA. Major MEDLINE topics: Deep Learning, Carbon Isotopes, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. 21 references. The full text is freely available (open access, CC BY 4.0). Funded by: American Cancer Society, NIH HHS, National Institutes of Health.
Abstract (original language)
Purpose
To evaluate whether deep learning improves the robustness of voxelwise kinetic parameter estimation from hyperpolarized (HP) 13 C MRI compared with nonlinear least‐squares (NLLS) fitting.
Methods
A hybrid neural network (NN) was trained on synthetic pyruvate/lactate time courses generated from an open‐system two‐compartment HP 13 C signal model to estimate the pyruvate‐to‐lactate conversion rate (), vascular‐extravascular exchange rate (), and vascular volume fraction (). NN performance was compared with NLLS across flip‐angle schemes, SNR levels, perturbations in acquisition parameters, and in vivo. Matched‐ratio simulations tested whether model‐estimated () retained information beyond the Lac/Pyr area‐under‐the‐curve ratio, .
Results
In simulations, NLLS and NN performance were comparable for estimation at high SNR, whereas the NN outperformed NLLS at low SNR and for the weakly identifiable parameters and . In vivo, NN maps were more spatially coherent than NLLS maps: corresponded with , while and corresponded with pyruvate AUC. In matched‐ratio simulations, NLLS‐derived discriminated the metabolic classes better than NN‐derived , although both model‐based estimates retained discriminatory information.
Conclusion
NLLS is effective for estimation under ideal model‐matched conditions, whereas the NN provides more stable voxelwise maps, especially for weakly identifiable parameters and under low‐SNR or in vivo conditions. Prospective biological or repeatability validation is needed to establish quantitative accuracy.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Department of Physics and Astronomy, Howard University, Washington, DC, USA.
- Department of Mathematics, Howard University, Washington, DC, USA.
- College of Medicine, Howard University, Washington, DC, USA.
- Department of Radiation Oncology, Johns Hopkins Medicine, Washington, DC, USA.
Funding
- American Cancer Society
- NIH HHS
- National Institutes of Health
Cite
APA
Deh, K., Kang, Y., Tu, T. W., Jones, R., Deville, C., & Khan, R. (2026). Deep Learning Improves Robustness of Voxelwise Kinetic Modeling for Hyperpolarized Carbon‐13 MRI. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70549
Vancouver
Deh K, Kang Y, Tu TW, Jones R, Deville C, Khan R. Deep Learning Improves Robustness of Voxelwise Kinetic Modeling for Hyperpolarized Carbon‐13 MRI. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70549
BibTeX
@article{Deh2026,
author = {Deh, Kofi and Kang, Yeona and Tu, Tsang-Wei and Jones, Rania and Deville, Curtiland and Khan, Rao},
title = {Deep Learning Improves Robustness of Voxelwise Kinetic Modeling for Hyperpolarized Carbon‐13 MRI},
journal = {Magnetic Resonance in Medicine},
year = {2026},
doi = {10.1002/mrm.70549}
}
EUVIMED