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

Rastogi, A and Dutta, A and Yalavarthy, PK (2022) VTDCE-Net: A time invariant deep neural network for direct estimation of pharmacokinetic parameters from undersampled DCE MRI data. In: Medical Physics .

PDF med_phy_2022.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Purpose: 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 (Formula presented.) 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 (Formula presented.) and (Formula presented.) 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 state-of-the-art performance compared to standard image reconstruction methods and is shown to work across all undersampling rates.

Item Type:	Journal Article
Publication:	Medical Physics
Publisher:	John Wiley and Sons Ltd
Additional Information:	The copyright for this article belongs to John Wiley and Sons Ltd.
Keywords:	Convolution; Deep neural networks; Image reconstruction; Inverse problems; Medical imaging; Network architecture; Parameter estimation; Pharmacokinetics; Statistical tests, Dynamic contrast-enhanced magnetic resonance imaging; Medical image reconstruction; Permeability imaging and magnetic resonance imaging; Pharmacokinetic modeling; Resonance imaging data; Spatial dimension; Time samples; Tracer kinetics; Under sampled; Under-sampling, Magnetic resonance imaging
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	09 Jan 2023 07:16
Last Modified:	09 Jan 2023 07:16
URI:	https://eprints.iisc.ac.in/id/eprint/78915

Actions (login required)

View Item