VTDCE‐Net: A time invariant deep neural network for direct estimation of pharmacokinetic parameters from undersampled DCE MRI data

Abstract

To propose a robust time and space invariant deep learning (DL) method to directly estimate the pharmacokinetic/tracer kinetic (PK/TK) parameters from undersampled dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) data. Methods: DCE-MRI consists of 4D (3D-spatial + temporal) data and has been utilized to estimate 3D (spatial) tracer kinetic maps. Existing DL architecture for this task needs retraining for variation in temporal and/or spatial dimensions. This work proposes a DL algorithm that is invariant to training and testing in both temporal and spatial dimensions. The proposed network was based on a 2.5-dimensional Unet architecture, where the encoder consists of a 3D convolutional layer and the decoder consists of a 2D convolutional layer. The proposed VTDCE-Net was evaluated for solving the ill-posed inverse problem of directly estimating TK parameters from undersampled k − t space data of breast cancer patients, and the results were systematically compared with a total variation (TV) regularization based direct parameter estimation scheme. In the breast dataset, the training was performed on patients with 32 time samples, and testing was carried out on patients with 26 and 32 time samples. Translation of the proposed VTDCE-Net for brain dataset to show the generalizability was also carried out. Undersampling rates (R) of 8×, 12×, and 20× were utilized with PSNR and SSIM as the figures of merit in this evaluation. TK parameter maps estimated from fully sampled data were utilized as ground truth. Results: Experiments carried out in this work demonstrate that the proposed VTDCE-Net outperforms the TV scheme on both breast and brain datasets across all undersampling rates. For K trans and V p maps, the improvement over TV is as high as 2 and 5 dB, respectively, using the proposed VTDCE-Net. Conclusion: Temporal points invariant DL network that was proposed in this work to estimate the TK-parameters using DCE-MRI data has provided stateof -the-art performance compared to standard image reconstruction methods and is shown to work across all undersampling rates.

Retrospective quantification of clinical abdominal DCE-MRI using pharmacokinetics-informed deep learning: a proof-of-concept study

“…In the last few years, deep learning (DL) techniques have been actively explored for applications in medical imaging (8), such as image registration, spatial super-resolution, denoising, and disease prediction. Several studies investigated the potential of applying DL to DCE-MRI, including tumor segmentation (9), therapy response prediction for cancer (10), lesion malignancy classification (11), and pharmacokinetic parameter estimation from time-resolved DCE-MRI (12)(13)(14)(15)(16)(17). These studies demonstrated the capability of DL to extract information and simplify postprocessing, as well as the growing interest in pharmacokinetic modeling.…”

Dynamic contrast enhanced (DCE) MRI estimation of vascular parameters using knowledge-based adaptive models

“…Kettelkamp et al 29 also estimated the PK parameters from fully sampled DCE-MRI data with explicit knowledge of AIF. Rastogi et al 30 have recently proposed an adaptive model with different architecture to address the issues of the information retention (spatiotemporal dimension) requirement as well as the need for the AIF information for PK parameter estimation. They proposed a 2.5D Unet-based architecture for direct estimation of the PK parameters from under-sampled k-t space.…”