Perfusion deconvolution in DSC-MRI with dispersion-compliant bases

A deep learning approach for quantifying CT perfusion parameters in stroke

Objective. Computed tomography perfusion (CTP) imaging is widely used for assessing acute ischemic stroke. However, conventional methods for quantifying CTP images, such as singular value decomposition (SVD), often lead to oscillations in the estimated residue function and underestimation of tissue perfusion. In addition, the use of global arterial input function (AIF) potentially leads to erroneous parameter estimates. We aim to develop a method for accurately estimating physiological parameters from CTP images.Approach. We introduced a Transformer-based network to learn voxel-wise temporal features of CTP images. With global AIF and concentration time curve (CTC) of brain tissue as inputs, the network estimated local AIF and flow-scaled residue function. The derived parameters, including cerebral blood flow (CBF) and bolus arrival delay (BAD), were validated on both simulated and patient data (ISLES18 dataset), and were compared with multiple SVD-based methods, including standard SVD (sSVD), block-circulant SVD (cSVD) and oscillation-index SVD (oSVD).Main results.On data simulating multiple scenarios, local AIF estimated by the proposed method correlated with true AIF with a coefficient of 0.97 ± 0.04 (P < 0.001), estimated CBF with a mean error of 4.95 ml/100 g min-1, and estimated BAD with a mean error of 0.51 s; the latter two errors were significantly lower than those of the SVD-based methods (P < 0.001). The CBF estimated by the SVD-based methods were underestimated by 10% ∼ 15%. For patient data, the CBF estimates of the proposed method were significantly higher than those of the sSVD method in both normally perfused and ischemic tissues, by 13.83 ml/100 g min-1or 39.33% and 8.55 ml/100 g min-1or 57.73% (P < 0.001), respectively, which was in agreement with the simulation results.Significance. The proposed method is capable of estimating local AIF and perfusion parameters from CTP images with high accuracy, potentially improving CTP's performance and efficiency in diagnosing and treating ischemic stroke.

A physics-informed deep learning framework for dynamic susceptibility contrast perfusion MRI

BACKGROUND

Perfusion magnetic resonance imaging (MRI)s plays a central role in the diagnosis and monitoring of neurovascular or neurooncological disease. However, conventional processing techniques are limited in their ability to capture relevant characteristics of the perfusion dynamics and suffer from a lack of standardization.

PURPOSE

We propose a physics-informed deep learning framework which is capable of analyzing dynamic susceptibility contrast perfusion MRI data and recovering the dynamic tissue response with high accuracy.

METHODS

The framework uses physics-informed neural networks (PINNs) to learn the voxel-wise TRF, which represents the dynamic response of the local vascular network to the contrast agent bolus. The network output is stabilized by total variation and elastic net regularization. Parameter maps of normalized cerebral blood flow (nCBF) and volume (nCBV) are then calculated from the predicted residue functions. The results are validated using extensive comparisons to values derived by conventional Tikhonov-regularized singular value decomposition (TiSVD), in silico simulations and an in vivo dataset of perfusion MRI exams of patients with high-grade gliomas.

RESULTS

The simulation results demonstrate that PINN-derived residue functions show a high concordance with the true functions and that the calculated values of nCBF and nCBV converge towards the true values for higher contrast-to-noise ratios. In the in vivo dataset, we find high correlations between conventionally derived and PINN-predicted perfusion parameters (Pearson's rho for nCBF:0.84 ± 0.03 $0.84 \pm 0.03$ and nCBV:0.92 ± 0.03 $0.92 \pm 0.03$ ) and very high indices of image similarity (structural similarity index for nCBF:0.91 ± 0.03 $0.91 \pm 0.03$ and for nCBV:0.98 ± 0.00 $0.98 \pm 0.00$ ).

CONCLUSIONS

PINNs can be used to analyze perfusion MRI data and stably recover the response functions of the local vasculature with high accuracy.

SPINNED: Simulation-based physics-informed neural network for deconvolution of dynamic susceptibility contrast MRI perfusion data

PURPOSE

To propose the simulation-based physics-informed neural network for deconvolution of dynamic susceptibility contrast (DSC) MRI (SPINNED) as an alternative for more robust and accurate deconvolution compared to existing methods.

METHODS

The SPINNED method was developed by generating synthetic tissue residue functions and arterial input functions through mathematical simulations and by using them to create synthetic DSC MRI time series. The SPINNED model was trained using these simulated data to learn the underlying physical relation (deconvolution) between the DSC-MRI time series and the arterial input functions. The accuracy and robustness of the proposed SPINNED method were assessed by comparing it with two common deconvolution methods in DSC MRI data analysis, circulant singular value decomposition, and Volterra singular value decomposition, using both simulation data and real patient data.

RESULTS

The proposed SPINNED method was more accurate than the conventional methods across all SNR levels and showed better robustness against noise in both simulation and real patient data. The SPINNED method also showed much faster processing speed than the conventional methods.

CONCLUSION

These results support that the proposed SPINNED method can be a good alternative to the existing methods for resolving the deconvolution problem in DSC MRI. The proposed method does not require any separate ground-truth measurement for training and offers additional benefits of quick processing time and coverage of diverse clinical scenarios. Consequently, it will contribute to more reliable, accurate, and rapid diagnoses in clinical applications compared with the previous methods including those based on supervised learning.

Non-parametric deconvolution using Bézier curves for quantification of cerebral perfusion in dynamic susceptibility contrast MRI

Objective

Deconvolution is an ill-posed inverse problem that tends to yield non-physiological residue functions R(t) in dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI). In this study, the use of Bézier curves is proposed for obtaining physiologically reasonable residue functions in perfusion MRI.

Materials and methods

Cubic Bézier curves were employed, ensuring R(0) = 1, bounded-input, bounded-output stability and a non-negative monotonically decreasing solution, resulting in 5 parameters to be optimized. Bézier deconvolution (BzD), implemented in a Bayesian framework, was tested by simulation under realistic conditions, including effects of arterial delay and dispersion. BzD was also applied to DSC-MRI data from a healthy volunteer.

Results

Bézier deconvolution showed robustness to different underlying residue function shapes. Accurate perfusion estimates were observed, except for boxcar residue functions at low signal-to-noise ratio. BzD involving corrections for delay, dispersion, and delay with dispersion generally returned accurate results, except for some degree of cerebral blood flow (CBF) overestimation at low levels of each effect. Maps of mean transit time and delay were markedly different between BzD and block-circulant singular value decomposition (oSVD) deconvolution.

Discussion

A novel DSC-MRI deconvolution method based on Bézier curves was implemented and evaluated. BzD produced physiologically plausible impulse response, without spurious oscillations, with generally less CBF underestimation than oSVD.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10334-021-00995-0.

Differentiating Nonenhancing Grade II Gliomas from Grade III Gliomas Using Diffusion Tensor Imaging and Dynamic Susceptibility Contrast MRI

BACKGROUND

Contrast enhancement in a brain tumor on magnetic resonance imaging is typically indicative of a high-grade glioma. However, a significant proportion of nonenhancing gliomas can be either grade II or III. While gross total resection remains the primary goal, imaging biomarkers may guide management when surgery is not possible, especially for nonenhancing gliomas. The utility of diffusion tensor imaging and dynamic susceptibility contrast magnetic resonance imaging was evaluated in differentiating nonenhancing gliomas.

METHODS

Retrospective analysis was performed on imaging data from 72 nonenhancing gliomas, including grade II (n = 49) and III (n = 23) gliomas. Diffusion tensor imaging and dynamic susceptibility contrast data were used to generate fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity as well as cerebral blood volume, cerebral blood flow, and mean transit time maps. Univariate and multivariate logistic regression and area under the curve analyses were used to measure sensitivity and specificity of imaging parameters. A subanalysis was performed to evaluate the utility of imaging parameters in differentiating between different histologic groups.

RESULTS

Logistic regression analysis indicated that tumor volume and relative mean transit time could differentiate between grade II and III nonenhancing gliomas. At a cutoff value of 0.33, this combination provided an area under the curve of 0.71, 70.6% sensitivity, and 64.3% specificity. Logistic regression analyses demonstrated much higher sensitivity and specificity in the differentiation of astrocytomas from oligodendrogliomas or identification of grades within these histologic subtypes.

CONCLUSIONS

Diffusion tensor imaging and dynamic susceptibility contrast imaging can aid in differentiation of nonenhancing grade II and III gliomas and between histologic subtypes.

Reconstruction of Undersampled Big Dynamic MRI Data Using Non-Convex Low-Rank and Sparsity Constraints

Dynamic magnetic resonance imaging (MRI) has been extensively utilized for enhancing medical living environment visualization, however, in clinical practice it often suffers from long data acquisition times. Dynamic imaging essentially reconstructs the visual image from raw (k,t)-space measurements, commonly referred to as big data. The purpose of this work is to accelerate big medical data acquisition in dynamic MRI by developing a non-convex minimization framework. In particular, to overcome the inherent speed limitation, both non-convex low-rank and sparsity constraints were combined to accelerate the dynamic imaging. However, the non-convex constraints make the dynamic reconstruction problem difficult to directly solve through the commonly-used numerical methods. To guarantee solution efficiency and stability, a numerical algorithm based on Alternating Direction Method of Multipliers (ADMM) is proposed to solve the resulting non-convex optimization problem. ADMM decomposes the original complex optimization problem into several simple sub-problems. Each sub-problem has a closed-form solution or could be efficiently solved using existing numerical methods. It has been proven that the quality of images reconstructed from fewer measurements can be significantly improved using non-convex minimization. Numerous experiments have been conducted on two in vivo cardiac datasets to compare the proposed method with several state-of-the-art imaging methods. Experimental results illustrated that the proposed method could guarantee the superior imaging performance in terms of quantitative and visual image quality assessments.