Accelerated in Vivo Cardiac Diffusion-Tensor MRI Using Residual Deep Learning-based Denoising in Participants with Obesity

In vivo cardiac diffusion tensor imaging on an MR system featuring ultrahigh performance gradients with 200 mT/m maximum gradient strength

PURPOSE

Our aim is to assess the potential of an MR system with ultrahigh performance gradients (200 mT/m maximum gradient strength) to address two interrelated challenges in cardiac DTI: low SNR and sensitivity to bulk motion.

METHODS

Imaging was performed in 20 healthy volunteers, two patients, and one swine post-myocardial infarction. The impact of maximum gradient strength was assessed with spin echo cardiac DTI featuring second-order motion compensation and varying maximum system gradient strengths (40, 80, 200 mT/m). Motion compensation requirements at 200 mT/m were assessed with sequences featuring zeroth-, first-, and second-order motion compensation. SNR, mean diffusivity, fractional anisotropy, helix angle transmurality, and secondary eigenvector angle in the left ventricle were compared.

RESULTS

Increasing maximum system gradient strength from 40 and 80 mT/m to 200 mT/m increased SNR of b = 500 s/mm2 images by 150% and 40% due to reductions in TE. Observed improvements in DTI metrics included reduction in variance in mean diffusivity and helix angle transmurality across healthy volunteers, improved visualization of myocardial borders and delineation of suspected scar. Whereas second-order motion compensation acquisitions were robust to motion-induced signal dropout, zeroth- and first-order motion compensation acquisitions suffered from severe signal loss and localized signal voids, respectively.

CONCLUSION

Ultrahigh performance gradients (200 mT/m) enable high SNR DWIs of the heart and resultant improvements in diffusion tensor metrics. Despite reduced diffusion-encoding duration, second-order motion compensation is required to overcome sensitivity to cardiac motion.

Cardiac diffusion-weighted and tensor imaging: a Society for Cardiovascular Magnetic Resonance (SCMR) special interest group consensus statement

Thanks to recent developments in Cardiovascular magnetic resonance (CMR), cardiac diffusion-weighted magnetic resonance is fast emerging in a range of clinical applications. Cardiac diffusion-weighted imaging (cDWI) and diffusion tensor imaging (cDTI) now enable investigators and clinicians to assess and quantify the 3D microstructure of the heart. Free-contrast DWI is uniquely sensitized to the presence and displacement of water molecules within the myocardial tissue, including the intra-cellular, extra-cellular and intra-vascular spaces. CMR can determine changes in microstructure by quantifying: a) mean diffusivity (MD) -measuring the magnitude of diffusion; b) fractional anisotropy (FA) - specifying the directionality of diffusion; c) helix angle (HA) and transverse angle (TA) -indicating the orientation of the cardiomyocytes; d) E2A and E2A mobility - measuring the alignment and systolic-diastolic mobility of the sheetlets, respectively. This document provides recommendations for both clinical and research cDWI and cDTI, based on published evidence when available and expert consensus when not. It introduces the cardiac microstructure focusing on the cardiomyocytes and their role in cardiac physiology and pathophysiology. It highlights methods, observations and recommendations in terminology, acquisition schemes, post-processing pipelines, data analysis and interpretation of the different biomarkers. Despite the ongoing challenges discussed in the document and the need for ongoing technical improvements, it is clear that cDTI is indeed feasible, can be accurately and reproducibly performed and, most importantly, can provide unique insights into myocardial pathophysiology.

Diffusion Tensor Phenomapping of the Healthy and Pressure-Overloaded Human Heart

Current techniques to image the microstructure of the heart with diffusion tensor MRI (DTI) are highly under-resolved. We present a technique to improve the spatial resolution of cardiac DTI by almost 10-fold and leverage this to measure local gradients in cardiomyocyte alignment or helix angle (HA). We further introduce a phenomapping approach based on voxel-wise hierarchical clustering of these gradients to identify distinct microstructural microenvironments in the heart. Initial development was performed in healthy volunteers (n=8). Thereader, subjects with severe but well-compensated aortic stenosis (AS, n=10) were compared to age-matched controls (CTL, n=10). Radial HA gradient was significantly reduced in AS (8.0±0.8°/mm vs. 10.2±1.8°/mm, p=0.001) but the other HA gradients did not change significantly. Four distinct microstructural clusters could be idenJfied in both the CTL and AS subjects and did not differ significantly in their properties or distribution. Despite marked hypertrophy, our data suggest that the myocardium in well-compensated AS can maintain its microstructural coherence. The described phenomapping approach can be used to characterize microstructural plasticity and perturbation in any organ system and disease.

Deep learning-based diffusion tensor cardiac magnetic resonance reconstruction: a comparison study

In vivo cardiac diffusion tensor imaging (cDTI) is a promising Magnetic Resonance Imaging (MRI) technique for evaluating the microstructure of myocardial tissue in living hearts, providing insights into cardiac function and enabling the development of innovative therapeutic strategies. However, the integration of cDTI into routine clinical practice poses challenging due to the technical obstacles involved in the acquisition, such as low signal-to-noise ratio and prolonged scanning times. In this study, we investigated and implemented three different types of deep learning-based MRI reconstruction models for cDTI reconstruction. We evaluated the performance of these models based on the reconstruction quality assessment, the diffusion tensor parameter assessment as well as the computational cost assessment. Our results indicate that the models discussed in this study can be applied for clinical use at an acceleration factor (AF) of × 2 and × 4 , with the D5C5 model showing superior fidelity for reconstruction and the SwinMR model providing higher perceptual scores. There is no statistical difference from the reference for all diffusion tensor parameters at AF × 2 or most DT parameters at AF × 4 , and the quality of most diffusion tensor parameter maps is visually acceptable. SwinMR is recommended as the optimal approach for reconstruction at AF × 2 and AF × 4 . However, we believe that the models discussed in this study are not yet ready for clinical use at a higher AF. At AF × 8 , the performance of all models discussed remains limited, with only half of the diffusion tensor parameters being recovered to a level with no statistical difference from the reference. Some diffusion tensor parameter maps even provide wrong and misleading information.

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI

Purpose

This study aims to evaluate deep learning (DL) denoising reconstructions for image quality improvement of Doppler ultrasound (DUS)-gated fetal cardiac MRI in congenital heart disease (CHD).

Methods

Twenty-five fetuses with CHD (mean gestational age: 35 ± 1 weeks) underwent fetal cardiac MRI at 3T. Cine imaging was acquired using a balanced steady-state free precession (bSSFP) sequence with Doppler ultrasound gating. Images were reconstructed using both compressed sensing (bSSFP CS) and a pre-trained convolutional neural network trained for DL denoising (bSSFP DL). Images were compared qualitatively based on a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent) and quantitatively by calculating the apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (aCNR). Diagnostic confidence was assessed for the atria, ventricles, foramen ovale, valves, great vessels, aortic arch, and pulmonary veins.

Results

Fetal cardiac cine MRI was successful in 23 fetuses (92%), with two studies excluded due to extensive fetal motion. The image quality of bSSFP DL cine reconstructions was rated superior to standard bSSFP CS cine images in terms of contrast [3 (interquartile range: 2-4) vs. 5 (4-5), P < 0.001] and endocardial edge definition [3 (2-4) vs. 4 (4-5), P < 0.001], while the extent of artifacts was found to be comparable [4 (3-4.75) vs. 4 (3-4), P = 0.40]. bSSFP DL images had higher aSNR and aCNR compared with the bSSFP CS images (aSNR: 13.4 ± 6.9 vs. 8.3 ± 3.6, P < 0.001; aCNR: 26.6 ± 15.8 vs. 14.4 ± 6.8, P < 0.001). Diagnostic confidence of the bSSFP DL images was superior for the evaluation of cardiovascular structures (e.g., atria and ventricles: P = 0.003).

Conclusion

DL image denoising provides superior quality for DUS-gated fetal cardiac cine imaging of CHD compared to standard CS image reconstruction.

Present and Future Innovations in AI and Cardiac MRI

Cardiac MRI is used to diagnose and treat patients with a multitude of cardiovascular diseases. Despite the growth of clinical cardiac MRI, complicated image prescriptions and long acquisition protocols limit the specialty and restrain its impact on the practice of medicine. Artificial intelligence (AI)-the ability to mimic human intelligence in learning and performing tasks-will impact nearly all aspects of MRI. Deep learning (DL) primarily uses an artificial neural network to learn a specific task from example data sets. Self-driving scanners are increasingly available, where AI automatically controls cardiac image prescriptions. These scanners offer faster image collection with higher spatial and temporal resolution, eliminating the need for cardiac triggering or breath holding. In the future, fully automated inline image analysis will most likely provide all contour drawings and initial measurements to the reader. Advanced analysis using radiomic or DL features may provide new insights and information not typically extracted in the current analysis workflow. AI may further help integrate these features with clinical, genetic, wearable-device, and "omics" data to improve patient outcomes. This article presents an overview of AI and its application in cardiac MRI, including in image acquisition, reconstruction, and processing, and opportunities for more personalized cardiovascular care through extraction of novel imaging markers.

Feasibility study of clinical target volume definition for soft-tissue sarcoma using muscle fiber orientations derived from diffusion tensor imaging

Objective. Soft-tissue sarcoma spreads preferentially along muscle fibers. We explore the utility of deriving muscle fiber orientations from diffusion tensor MRI (DT-MRI) for defining the boundary of the clinical target volume (CTV) in muscle tissue. Approach. We recruited eight healthy volunteers to acquire MR images of the left and right thigh. The imaging session consisted of (a) two MRI spin-echo-based scans, T1- and T2-weighted; (b) a diffusion weighted (DW) spin-echo-based scan using an echo planar acquisition with fat suppression. The thigh muscles were auto-segmented using the convolutional neural network. DT-MRI data were used as a geometry encoding input to solve the anisotropic Eikonal equation with the Hamiltonian Fast-Marching method. The isosurfaces of the solution modeled the CTV boundary. Main results. The auto-segmented muscles of the thigh agreed with manually delineated with the Dice score ranging from 0.8 to 0.94 for different muscles. To validate our method of deriving muscle fiber orientations, we compared anisotropy of the isosurfaces across muscles with different anatomical orientations within a thigh, between muscles in the left and right thighs of each subject, and between different subjects. The fiber orientations were identified reproducibly across all comparisons. We identified two controlling parameters, the distance from the gross tumor volume to the isosurface and the eigenvalues ratio, to tailor the proposed CTV to the satisfaction of the clinician. Significance. Our feasibility study with healthy volunteers shows the promise of using muscle fiber orientations derived from DW MRI data for automated generation of anisotropic CTV boundary in soft tissue sarcoma. Our contribution is significant as it serves as a proof of principle for combining DT-MRI information with tumor spread modeling, in contrast to using moderately informative 2D CT planes for the CTV delineation. Such improvements will positively impact the cancer centers with a small volume of sarcoma patients.

AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography

(1) To investigate whether interventional cone-beam computed tomography (cbCT) could benefit from AI denoising, particularly with respect to patient body mass index (BMI); (2) From 1 January 2016 to 1 January 2022, 100 patients with liver-directed interventions and peri-procedural cbCT were included. The unenhanced mask run and the contrast-enhanced fill run of the cbCT were reconstructed using weighted filtered back projection. Additionally, each dataset was post-processed using a novel denoising software solution. Place-consistent regions of interest measured signal-to-noise ratio (SNR) per dataset. Corrected mixed-effects analysis with BMI subgroup analyses compared objective image quality. Multiple linear regression measured the contribution of “Radiation Dose”, “Body-Mass-Index”, and “Mode” to SNR. Two radiologists independently rated diagnostic confidence. Inter-rater agreement was measured using Spearman correlation (r); (3) SNR was significantly higher in the denoised datasets than in the regular datasets (p < 0.001). Furthermore, BMI subgroup analysis showed significant SNR deteriorations in the regular datasets for higher patient BMI (p < 0.001), but stable results for denoising (p > 0.999). In regression, only denoising contributed positively towards SNR (0.6191; 95%CI 0.6096 to 0.6286; p < 0.001). The denoised datasets received overall significantly higher diagnostic confidence grades (p = 0.010), with good inter-rater agreement (r ≥ 0.795, p < 0.001). In a subgroup analysis, diagnostic confidence deteriorated significantly for higher patient BMI (p < 0.001) in the regular datasets but was stable in the denoised datasets (p ≥ 0.103).; (4) AI denoising can significantly enhance image quality in interventional cone-beam CT and effectively mitigate diagnostic confidence deterioration for rising patient BMI.