Purpose
This prospective clinical study assesses the feasibility of training a deep neural network (DNN) for intravoxel incoherent motion (IVIM) model fitting to diffusion‐weighted MRI (DW‐MRI) data ...and evaluates its performance.
Methods
In May 2011, 10 male volunteers (age range, 29–53 years; mean, 37) underwent DW‐MRI of the upper abdomen on 1.5T and 3.0T MR scanners. Regions of interest in the left and right liver lobe, pancreas, spleen, renal cortex, and renal medulla were delineated independently by 2 readers. DNNs were trained for IVIM model fitting using these data; results were compared to least‐squares and Bayesian approaches to IVIM fitting. Intraclass correlation coefficients (ICCs) were used to assess consistency of measurements between readers. Intersubject variability was evaluated using coefficients of variation (CVs). The fitting error was calculated based on simulated data, and the average fitting time of each method was recorded.
Results
DNNs were trained successfully for IVIM parameter estimation. This approach was associated with high consistency between the 2 readers (ICCs between 50% and 97%), low intersubject variability of estimated parameter values (CVs between 9.2 and 28.4), and the lowest error when compared with least‐squares and Bayesian approaches. Fitting by DNNs was several orders of magnitude quicker than the other methods, but the networks may need to be retrained for different acquisition protocols or imaged anatomical regions.
Conclusion
DNNs are recommended for accurate and robust IVIM model fitting to DW‐MRI data. Suitable software is available for download.
Purpose
Earlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art intravoxel‐incoherent motion (IVIM) ...fitting approaches to diffusion‐weighted imaging (DWI). This study presents a substantially improved version, IVIM‐NEToptim, and characterizes its superior performance in pancreatic cancer patients.
Method
In simulations (signal‐to‐noise ratio SNR = 20), the accuracy, independence, and consistency of IVIM‐NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root‐mean‐square error (NRMSE), Spearman’s ρ, and the coefficient of variation (CVNET), respectively. The best performing network, IVIM‐NEToptim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM‐NEToptim’s performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within‐subject standard deviations (wSD) and treatment‐induced changes were assessed.
Results
In simulations (SNR = 20), IVIM‐NEToptim outperformed IVIM‐NETorig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CVNET(D) = 0.013 vs 0.104; CVNET(f) = 0.020 vs 0.054; CVNET(D*) = 0.036 vs 0.110). IVIM‐NEToptim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM‐NEToptim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM‐NEToptim detected the most individual patients with significant parameter changes compared to day‐to‐day variations.
Conclusion
IVIM‐NEToptim is recommended for accurate, informative, and consistent IVIM fitting to DWI data.
Purpose
Online adaptive radiotherapy would greatly benefit from the development of reliable auto‐segmentation algorithms for organs‐at‐risk and radiation targets. Current practice of manual ...segmentation is subjective and time‐consuming. While deep learning‐based algorithms offer ample opportunities to solve this problem, they typically require large datasets. However, medical imaging data are generally sparse, in particular annotated MR images for radiotherapy. In this study, we developed a method to exploit the wealth of publicly available, annotated CT images to generate synthetic MR images, which could then be used to train a convolutional neural network (CNN) to segment the parotid glands on MR images of head and neck cancer patients.
Methods
Imaging data comprised 202 annotated CT and 27 annotated MR images. The unpaired CT and MR images were fed into a 2D CycleGAN network to generate synthetic MR images from the CT images. Annotations of axial slices of the synthetic images were generated by propagating the CT contours. These were then used to train a 2D CNN. We assessed the segmentation accuracy using the real MR images as test dataset. The accuracy was quantified with the 3D Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD) between manual and auto‐generated contours. We benchmarked the approach by a comparison to the interobserver variation determined for the real MR images, as well as to the accuracy when training the 2D CNN to segment the CT images.
Results
The determined accuracy (DSC: 0.77±0.07, HD: 18.04±12.59mm, MSD: 2.51±1.47mm) was close to the interobserver variation (DSC: 0.84±0.06, HD: 10.85±5.74mm, MSD: 1.50±0.77mm), as well as to the accuracy when training the 2D CNN to segment the CT images (DSC: 0.81±0.07, HD: 13.00±7.61mm, MSD: 1.87±0.84mm).
Conclusions
The introduced cross‐modality learning technique can be of great value for segmentation problems with sparse training data. We anticipate using this method with any nonannotated MRI dataset to generate annotated synthetic MR images of the same type via image style transfer from annotated CT images. Furthermore, as this technique allows for fast adaptation of annotated datasets from one imaging modality to another, it could prove useful for translating between large varieties of MRI contrasts due to differences in imaging protocols within and between institutions.
Purpose
The intravoxel incoherent motion (IVIM) model for DWI might provide useful biomarkers for disease management in head and neck cancer. This study compared the repeatability of three IVIM ...fitting methods to the conventional nonlinear least‐squares regression: Bayesian probability estimation, a recently introduced neural network approach, IVIM‐NET, and a version of the neural network modified to increase consistency, IVIM‐NETmod.
Methods
Ten healthy volunteers underwent two imaging sessions of the neck, two weeks apart, with two DWI acquisitions per session. Model parameters (ADC, diffusion coefficient Dt, perfusion fraction fp, and pseudo‐diffusion coefficient Dp) from each fit method were determined in the tonsils and in the pterygoid muscles. Within‐subject coefficients of variation (wCV) were calculated to assess repeatability. Training of the neural network was repeated 100 times with random initialization to investigate consistency, quantified by the coefficient of variance.
Results
The Bayesian and neural network approaches outperformed nonlinear regression in terms of wCV. Intersession wCV of Dt in the tonsils was 23.4% for nonlinear regression, 9.7% for Bayesian estimation, 9.4% for IVIM‐NET, and 11.2% for IVIM‐NETmod. However, results from repeated training of the neural network on the same data set showed differences in parameter estimates: The coefficient of variances over the 100 repetitions for IVIM‐NET were 15% for both Dt and fp, and 94% for Dp; for IVIM‐NETmod, these values improved to 5%, 9%, and 62%, respectively.
Conclusion
Repeatabilities from the Bayesian and neural network approaches are superior to that of nonlinear regression for estimating IVIM parameters in the head and neck.
Purpose
Flow‐compensated (FC) diffusion‐weighted MRI (DWI) for intravoxel‐incoherent motion (IVIM) modeling allows for a more detailed description of tissue microvasculature than conventional IVIM. ...The long acquisition time of current FC‐IVIM protocols, however, has prohibited clinical application. Therefore, we developed an optimized abdominal FC‐IVIM acquisition with a clinically feasible scan time.
Methods
Precision and accuracy of the FC‐IVIM parameters were assessed by fitting the FC‐IVIM model to signal decay curves, simulated for different acquisition schemes. Diffusion‐weighted acquisitions were added subsequently to the protocol, where we chose the combination of b‐value, diffusion time and gradient profile (FC or bipolar) that resulted in the largest improvement to its accuracy and precision. The resulting two optimized FC‐IVIM protocols with 25 and 50 acquisitions (FC‐IVIMopt25 and FC‐IVIMopt50), together with a complementary acquisition consisting of 50 diffusion‐weighting (FC‐IVIMcomp), were acquired in repeated abdominal free‐breathing FC‐IVIM imaging of seven healthy volunteers. Intersession and intrasession within‐subject coefficient of variation of the FC‐IVIM parameters were compared for the liver, spleen, and kidneys.
Results
Simulations showed that the performance of FC‐IVIM improved in tissue with larger perfusion fraction and signal‐to‐noise ratio. The scan time of the FC‐IVIMopt25 and FC‐IVIMopt50 protocols were 8 and 16 min. The best in vivo performance was seen in FC‐IVIMopt50. The intersession within‐subject coefficients of variation of FC‐IVIMopt50 were 11.6%, 16.3%, 65.5%, and 36.0% for FC‐IVIM model parameters diffusivity, perfusion fraction, characteristic time and blood flow velocity, respectively.
Conclusions
We have optimized the FC‐IVIM protocol, allowing for clinically feasible scan times (8‐16 min).
Purpose
Software has a substantial impact on quantitative perfusion MRI values. The lack of generally accepted implementations, code sharing and transparent testing reduces reproducibility, hindering ...the use of perfusion MRI in clinical trials. To address these issues, the ISMRM Open Science Initiative for Perfusion Imaging (OSIPI) aimed to establish a community‐led, centralized repository for sharing open‐source code for processing contrast‐based perfusion imaging, incorporating an open‐source testing framework.
Methods
A repository was established on the OSIPI GitHub website. Python was chosen as the target software language. Calls for code contributions were made to OSIPI members, the ISMRM Perfusion Study Group, and publicly via OSIPI websites. An automated unit‐testing framework was implemented to evaluate the output of code contributions, including visual representation of the results.
Results
The repository hosts 86 implementations of perfusion processing steps contributed by 12 individuals or teams. These cover all core aspects of DCE‐ and DSC‐MRI processing, including multiple implementations of the same functionality. Tests were developed for 52 implementations, covering five analysis steps. For T1 mapping, signal‐to‐concentration conversion and population AIF functions, different implementations resulted in near‐identical output values. For the five pharmacokinetic models tested (Tofts, extended Tofts‐Kety, Patlak, two‐compartment exchange, and two‐compartment uptake), differences in output parameters were observed between contributions.
Conclusions
The OSIPI DCE‐DSC code repository represents a novel community‐led model for code sharing and testing. The repository facilitates the re‐use of existing code and the benchmarking of new code, promoting enhanced reproducibility in quantitative perfusion imaging.
Purpose
For reliable DCE MRI parameter estimation, k‐space undersampling is essential to meet resolution, coverage, and signal‐to‐noise requirements. Pseudo‐spiral (PS) sampling achieves this by ...sampling k‐space on a Cartesian grid following a spiral trajectory. The goal was to optimize PS k‐space sampling patterns for abdomin al DCE MRI.
Methods
The optimal PS k‐space sampling pattern was determined using an anthropomorphic digital phantom. Contrast agent inflow was simulated in the liver, spleen, pancreas, and pancreatic ductal adenocarcinoma (PDAC). A total of 704 variable sampling and reconstruction approaches were created using three algorithms using different parametrizations to control sampling density, halfscan and compressed sensing regularization. The sampling patterns were evaluated based on image quality scores and the accuracy and precision of the DCE pharmacokinetic parameters. The best and worst strategies were assessed in vivo in five healthy volunteers without contrast agent administration. The best strategy was tested in a DCE scan of a PDAC patient.
Results
The best PS reconstruction was found to be PS‐diffuse based, with quadratic distribution of readouts on a spiral, without random shuffling, halfscan factor of 0.8, and total variation regularization of 0.05 in the spatial and temporal domains. The best scoring strategy showed sharper images with less prominent artifacts in healthy volunteers compared to the worst strategy. Our suggested DCE sampling strategy also showed high quality DCE images in the PDAC patient.
Conclusion
Using an anthropomorphic digital phantom, we identified an optimal PS sampling strategy for abdominal DCE MRI, and demonstrated feasibility in a PDAC patient.
Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving ...healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.
Intravoxel incoherent motion (IVIM) imaging and diffusion tensor imaging (DTI) facilitate noninvasive quantification of tissue perfusion and diffusion. Both are promising biomarkers in various ...diseases and a combined acquisition is therefore desirable. This comes with challenges, including noisy parameter maps and long scan times, especially for the perfusion fraction f and pseudo‐diffusion coefficient D*. A model‐based reconstruction has the potential to overcome these challenges. As a first step, our goal was to develop a model‐based reconstruction framework for IVIM and combined IVIM‐DTI parameter estimation. The IVIM and IVIM‐DTI models were implemented in the PyQMRI model‐based reconstruction framework and validated with simulations and in vivo data. Commonly used voxel‐wise nonlinear least‐squares fitting was used as the reference. Simulations with the IVIM and IVIM‐DTI models were performed with 100 noise realizations to assess accuracy and precision. Diffusion‐weighted data were acquired for IVIM reconstruction in the liver (n = 5), as well as for IVIM‐DTI in the kidneys (n = 5) and lower‐leg muscles (n = 6) of healthy volunteers. The median and interquartile range (IQR) values of the IVIM and IVIM‐DTI parameters were compared to assess bias and precision. With model‐based reconstruction, the parameter maps exhibited less noise, which was most pronounced in the f and D* maps, both in the simulations and in vivo. The bias values in the simulations were comparable between model‐based reconstruction and the reference method. The IQR was lower with model‐based reconstruction compared with the reference for all parameters. In conclusion, model‐based reconstruction is feasible for IVIM and IVIM‐DTI and improves the precision of the parameter estimates, particularly for f and D* maps.
We propose a model‐based reconstruction framework for intravoxel incoherent motion (IVIM) and combined IVIM and diffusion tensor imaging (IVIM‐DTI) parameter estimation. The framework was validated with simulations and in vivo data. With model‐based reconstruction, the parameter maps exhibit less noise, which was most pronounced in the f and D* maps, both in the simulations and in vivo. We found that model‐based reconstruction is feasible for IVIM and IVIM‐DTI and improves the precision of the parameter estimates, particularly for f and D* maps.
To obtain better microstructural integrity, interstitial fluid, and microvascular images from multi-b-value diffusion MRI data by using a physics-informed neural network (PINN) fitting approach.
...Test-retest whole-brain inversion recovery diffusion-weighted images with multiple b-values (IVIM: intravoxel incoherent motion) were acquired on separate days for 16 patients with cerebrovascular disease on a 3.0T MRI system. The performance of the PINN three-component IVIM (3C-IVIM) model fitting approach was compared with conventional fitting approaches (i.e., non-negative least squares and two-step least squares) in terms of (1) parameter map quality, (2) test-retest repeatability, and (3) voxel-wise accuracy. Using the in vivo data, the parameter map quality was assessed by the parameter contrast-to-noise ratio (PCNR) between normal-appearing white matter and white matter hyperintensities, and test-retest repeatability was expressed by the coefficient of variation (CV) and intraclass correlation coefficient (ICC). The voxel-wise accuracy of the 3C-IVIM parameters was determined by 10,000 computer simulations mimicking our in vivo data. Differences in PCNR and CV values obtained with the PINN approach versus conventional fitting approaches were assessed using paired Wilcoxon signed-rank tests.
The PINN-derived 3C-IVIM parameter maps were of higher quality and more repeatable than those of conventional fitting approaches, while also achieving higher voxel-wise accuracy.
Physics-informed neural networks enable robust voxel-wise estimation of three diffusion components from the diffusion-weighted signal. The repeatable and high-quality biological parameter maps generated with PINNs allow for visual evaluation of pathophysiological processes in cerebrovascular disease.
PDF
