Radiation Physics and Engineering
A peer-reviewed journal published by K. N. Toosi University of Technology

PKest-LSnet: A robust LSTM-Based deep learning framework for accurate pharmacokinetic parameter estimation in DCE-MRI with clinical validation

Articles in Press

Document Type : Research Article

Authors

Azimeh NV Dehkordi 1
Hossein Malekmohammadi 2
Sedigheh Sina 2, 3

1 Department of Physics, Na. C, Islamic Azad University, Najafabad, Iran

2 Mechanical Engineering Department, Shiraz University, Shiraz, Iran

3 Radiation Research Center, Shiraz University, Shiraz, Iran

https://doi.org/10.22034/rpe.2026.579118.1347
Abstract
Dynamic contrast-enhanced MRI (DCE-MRI) plays a pivotal role in quantifying tissue hemodynamics, yet accurate pharmacokinetic (PK) parameter estimation remains challenging. We present PKest-LSnet, a novel Long Short-Term Memory (LSTM)-based deep learning framework for robust PK analysis. The network was trained on comprehensive simulated data generated using physiologically plausible ranges of PK parameters (parameetrs of Tofts equation: vp, Ktrans, kep) and a population-based arterial input function (AIF), enabling precise ground-truth validation. Rigorous testing on clinical data from 19 glioblastoma patients demonstrated strong agreement with reference method maximum likelihood estimation (MPE <12% for all parameters), with 99.42% accuracy in classifying tumor signals. The model maintained stability across variable acquisition protocols (time intervals: 2-6 sec; SNR: 5–100), proving its adaptability to real-world clinical variability. While excelling in tumor characterization (DSC=77.27%), leaky vasculature classification challenges (DSC=36.76%) revealed opportunities for architectural refinements. PKest-LSnet eliminates dependency on initial parameter estimates, reduces computational time by orders of magnitude compared to conventional methods, and offers a robustness method to the tested variations in temporal sampling intervals and SNRs-critical for multicenter studies. This work bridges the gap between simulated training and clinical deployment, providing a validated tool for precision DCE-MRI analysis with direct applications in oncology and therapeutic monitoring. Future directions include hybrid architectures for improved intermediate-tissue classification and patient-specific AIF integration.

Highlights

  • The model maintained stability across variable acquisition protocols.
  • Excelling in tumor characterization (DSC=77%) leaky vasculature classification challenges (DSC=36%).
  • This work bridges the gap between simulated training and clinical deployment.

Keywords

DCE-MRI
Pharmacokinetic modeling
LSTM networks
Glioblastoma
Deep learning
Subjects

Copyright
RPE is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).

Conflict of Interest
The authors declare no potential conflict of interest regarding the publication of this work‎.

Funding
‎The authors declare that no funds‎, ‎grants‎, ‎or other financial support were received during the preparation of this manuscript‎.

Acharjee, M. K., Kumar, U., Bachar, S. C., et al. (2014). Estimation of pharmacokinetic parameters using nonlinear fixed effects one compartment open model. Journal of Applied Pharmaceutical Science, 4(12):056–059.
Bagher-Ebadian, H., Dehkordi, A., and Ewing, J. (2016). SU-F-I-26: Maximum likelihood and nested model selection techniques for pharmacokinetic analysis of dynamic contrast enhanced MRI in patients with glioblastoma tumors. Medical Physics, 43(6Part7):3392–3392.
Bagher-Ebadian, H., Jafari-Khouzani, K., Mitsias, P. D., et al. (2011). Predicting final extent of ischemic infarction using artificial neural network analysis of multi-parametric MRI in patients with stroke. PloS one, 6(8):e22626.
Brocks, D. R. and Hamdy, D. A. (2020). Bayesian estimation of pharmacokinetic parameters: an important component to include in the teaching of clinical pharmacokinetics and therapeutic drug monitoring. Research in Pharmaceutical Sciences, 15(6):503.
Choi, Y., Kim, D., Lee, S.-K., et al. (2015). The added prognostic value of preoperative dynamic contrast-enhanced MRI histogram analysis in patients with glioblastoma: analysis of overall and progression-free survival. American Journal of Neuroradiology, 36(12):2235–2241.
Clark, K., Vendt, B., Smith, K., et al. (2013). The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. Journal of Digital Imaging, 26(6):1045–1057.
Dansirikul, C., Choi, M., and Duffull, S. B. (2005). Estimation of pharmacokinetic parameters from non-compartmental variables using Microsoft Excel R?. Computers in Biology and Medicine, 35(5):389–403.
De Naeyer, D., De Deene, Y., Ceelen, W. P., et al. (2011). Precision analysis of kinetic modelling estimates in dynamic contrast enhanced MRI. Magnetic Resonance Materials in Physics, Biology and Medicine, 24(2):51–66.
Dehkordi, A. N., Kamali-Asl, A., Ewing, J. R., et al. (2017). An adaptive model for rapid and direct estimation of extravascular extracellular space in dynamic contrast enhanced MRI studies. NMR in Biomedicine, 30(5):e3682.
Dehkordi, A. N., Sina, S., and Khodadadi, F. (2021). A comparison of deep learning and pharmacokinetic model selection methods in segmentation of high-grade glioma. Frontiers in Biomedical Technologies.
Donahue, J., Anne Hendricks, L., Guadarrama, S., et al. (2015). Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2625–2634.
Gill, A. B., Anandappa, G., Patterson, A. J., et al. (2015). The use of error-category mapping in pharmacokinetic model analysis of dynamic contrast-enhanced MRI data. Magnetic Resonance Imaging, 33(2):246–251.
Gravina, M., Marrone, S., Piantadosi, G., et al. (2019). 3TP-CNN: radiomics and deep learning for lesions classification in DCE-MRI. In International Conference on Image Analysis and Processing, pages 661–671. Springer.
Hsu, Y.-H. H., Ferl, G. Z., and Ng, C. M. (2013). GPU-accelerated nonparametric kinetic analysis of DCE-MRI data from glioblastoma patients treated with bevacizumab. Magnetic Resonance Imaging, 31(4):618–623.
H`yvlová, D., Jiˇ r´ ık, R., and Vitouˇ s, J. (2024). Deep-learning estimation of second-generation pharmacokinetic-model parameters in DCE-MRI. In 2024 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), pages 1–8. IEEE.
Jung, W., Bollmann, S., and Lee, J. (2022). Overview of quantitative susceptibility mapping using deep learning: current status, challenges and opportunities. NMR in Biomedicine, 35(4):e4292.
Kayastha, M. B., Liu, T., Titze, D., et al. (2023). Reconstructing 42 Years (1979–2020) of Great Lakes surface temperature through a deep learning approach. Remote Sensing, 15(17):4253.
Klepaczko, A., Strzelecki, M., Kocio lek, M., et al. (2020). A multi-layer perceptron network for perfusion parameter estimation in DCE-MRI studies of the healthy kidney. Applied Sciences, 10(16):5525.
Li, X., Zhu, Y., Kang, H., et al. (2015). Glioma grading by microvascular permeability parameters derived from dynamic contrast-enhanced mri and intratumoral susceptibility signal on susceptibility weighted imaging. Cancer Imaging, 15(1):4.
Lonser, R. R., Sarntinoranont, M., and Bankiewicz, K. (2019). Nervous system drug delivery: principles and practice. Academic Press.
Metzler, C. M. (1986). Estimation of pharmacokinetic parameters: statistical considerations. International Encyclopedia of Pharmacological Therapy, pages 407–420.
NV, D. A. and Koohestani, S. (2019). The influence of signal to noise ratio on the pharmacokinetic analysis in dce-mristudies.
Oh, G., Moon, Y., Moon, W.-J., et al. (2024). Unpaired deep learning for pharmacokinetic parameter estimation from dynamic contrast-enhanced MRI without AIF measurements. Neuroimage, 291:120571.
Ottens, T., Barbieri, S., Orton, M. R., et al. (2022). Deep learning DCE-MRI parameter estimation: Application in pancreatic cancer. Medical Image Analysis, 80:102512.
Reavey-Cantwell, J. F., Haroun, R. I., Zahurak, M., et al. (2001). The prognostic value of tumor markers in patients with glioblastoma multiforme: analysis of 32 patients and review of the literature. Journal of Neuro-Oncology, 55(3):195–204.
Rygh, C. B., Wang, J., Thuen, M., et al. (2014). Dynamic contrast enhanced MRI detects early response to adoptive NK cellular immunotherapy targeting the NG2 proteoglycan in a rat model of glioblastoma. PLoS One, 9(9):e108414.
Schabel, M. C. and Parker, D. L. (2008). Uncertainty and bias in contrast concentration measurements using spoiled gradient echo pulse sequences. Physics in Medicine & Biology, 53(9):2345–2373.
Simeth, J. and Cao, Y. (2020). Gan and dual-input two-compartment model-based training of a neural network for robust quantification of contrast uptake rate in gadoxetic acid- enhanced MRI. Medical Physics, 47(4):1702–1712.
Tofts, P. S., Brix, G., Buckley, D. L., et al. (1999). Estimating kinetic parameters from dynamic contrast-enhanced T1-weighted MRI of a diffusable tracer: standardized quantities and symbols. Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine, 10(3):223–232.
Tofts, P. S. and Kermode, A. G. (1991). Measurement of the blood-brain barrier permeability and leakage space using dynamic MR imaging. 1. Fundamental concepts. Magnetic Resonance in Medicine, 17(2):357–367.
Ulas, C., Das, D., Thrippleton, M. J., et al. (2019). Convolutional neural networks for direct inference of pharmacokinetic parameters: application to stroke dynamic contrast-enhanced
MRI. Frontiers in Neurology, 9:1147. Ulas, C., Tetteh, G., Thrippleton, M. J., et al. (2018). Direct estimation of pharmacokinetic parameters from DCE-MRI using deep CNN with forward physical model loss. In International conference on medical image computing and computer-assisted intervention, pages 39–47. Springer.
Urien, S. and Lokiec, F. (2004). Population pharmacokinetics of total and unbound plasma cisplatin in adult patients. British Journal of Clinical Pharmacology, 57(6):756–763.
Wang, S., Liu, P., Turkbey, B., et al. (2012). Gaussian process inference for estimating pharmacokinetic parameters of dynamic contrast-enhanced MR images. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 582–589. Springer.
Xue, X., Feng, J., Gao, Y., et al. (2019). Convolutional recurrent neural networks with a self-attention mechanism for personnel performance prediction. Entropy, 21(12):1227.
Yan, F.-R., Zhang, P., Liu, J.-L., et al. (2014). Parameter estimation of population pharmacokinetic models with stochastic differential equations: Implementation of an estimation algorithm. Journal of Probability and Statistics, 2014(1):836518.
Yu, R.-h. and Cao, Y.-x. (2017). A method to determine pharmacokinetic parameters based on andante constant-rate intravenous infusion. Scientific Reports, 7(1):13279.
Zhao, J., Huang, F., Lv, J., et al. (2020). Do RNN and LSTM have long memory? In International Conference on Machine Learning, pages 11365–11375. PMLR.
Ziayee, F., Müller-Lutz, A., Gross, J., et al. (2018). Influence of arterial input function (AIF) on quantitative prostate dynamic contrast-enhanced (DCE) MRI and zonal prostate anatomy. Magnetic Resonance Imaging, 53:28–33.
Zou, J., Balter, J. M., and Cao, Y. (2020). Estimation of pharmacokinetic parameters from DCE-MRI by extracting long and short time-dependent features using an LSTM network. Medical Physics, 47(8):3447–3457.
Radiation Physics and Engineering

Articles in Press, Accepted Manuscript
Available Online from 09 September 2026

  • Receive Date 19 April 2026
  • Revise Date 29 August 2026
  • Accept Date 06 September 2026

Home

Submit Manuscript

Reviewers

Contact Us