Deep learning-based velocity antialiasing of 4D-flow MRI

Improving the efficiency and accuracy of CMR with AI - review of evidence and proposition of a roadmap to clinical translation

Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment of heart disease; however, limitations of CMR include long exam times and high complexity compared to other cardiac imaging modalities. Recently advancements in artificial intelligence (AI) technology have shown great potential to address many CMR limitations. While the developments are remarkable, translation of AI-based methods into real-world CMR clinical practice remains at a nascent stage and much work lies ahead to realize the full potential of AI for CMR. Herein we review recent cutting-edge and representative examples demonstrating how AI can advance CMR in areas such as exam planning, accelerated image reconstruction, post-processing, quality control, classification and diagnosis. These advances can be applied to speed up and simplify essentially every application including cine, strain, late gadolinium enhancement, parametric mapping, 3D whole heart, flow, perfusion and others. AI is a unique technology based on training models using data. Beyond reviewing the literature, this paper discusses important AI-specific issues in the context of CMR, including (1) properties and characteristics of datasets for training and validation, (2) previously published guidelines for reporting CMR AI research, (3) considerations around clinical deployment, (4) responsibilities of clinicians and the need for multi-disciplinary teams in the development and deployment of AI in CMR, (5) industry considerations, and (6) regulatory perspectives. Understanding and consideration of all these factors will contribute to the effective and ethical deployment of AI to improve clinical CMR.

Multiyear Interval Changes in Aortic Wall Shear Stress in Patients with Bicuspid Aortic Valve Assessed by 4D Flow MRI

BACKGROUND

In patients with bicuspid aortic valve (BAV), 4D flow MRI can quantify regions exposed to abnormal aortic hemodynamics, including high wall shear stress (WSS), a known stimulus for arterial wall dysfunction. However, the long-term multiscan reproducibility of 4D flow MRI-derived hemodynamic parameters is unknown.

PURPOSE

To investigate the long-term stability of 4D flow MRI-derived peak velocity, WSS, and WSS-derived heatmaps in patients with BAV undergoing multiyear surveillance imaging.

STUDY TYPE

Retrospective.

POPULATION

20 BAV patients (mean age 48.4 ± 13.9 years; 14 males) with five 4D flow MRI scans, with intervals of at least 6 months between scans, and 125 controls (mean age: 50.7 ± 15.8 years; 67 males).

FIELD STRENGTH/SEQUENCE

1.5 and 3.0T, prospectively ECG and respiratory navigator-gated aortic 4D flow MRI.

ASSESSMENT

Automated AI-based 4D flow analysis pipelines were used for data preprocessing, aorta 3D segmentation, and quantification of ascending aorta (AAo) peak velocity, peak systolic WSS, and heatmap-derived relative area of elevated WSS compared to WSS ranges in age and sex-matched normative control populations. Growth rate was derived from the maximum AAo diameters measured on the first and fifth MRI scans.

STATISTICAL TESTS

One-way repeated measures analysis of variance. P < 0.05 indicated significance.

RESULTS

One hundred 4D flow MRI exams (five per patient) were analyzed. The mean total follow-up duration was 5.5 ± 1.1 years, and the average growth rate was 0.3 ± 0.2 mm/year. Peak velocity, peak systolic WSS, and relative area of elevated WSS did not change significantly over the follow-up period (P = 0.64, P = 0.69, and P = 0.35, respectively). The patterns and areas of elevated WSS demonstrated good reproducibility on semiquantitative assessment.

CONCLUSION

4D flow MRI-derived peak velocity, WSS, and WSS-derived heatmaps showed good multiyear and multiscan stability in BAV patients with low aortic growth rates. These findings underscore the reliability of these metrics in monitoring BAV patients for potential risk of dilation.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 1.

Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images

Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden's index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.

4Dflow-VP-Net: A deep convolutional neural network for noninvasive estimation of relative pressures in stenotic flows from 4D flow MRI

PURPOSE

To estimate relative transvalvular pressure gradient (TVPG) noninvasively from 4D flow MRI.

METHODS

A novel deep learning-based approach is proposed to estimate pressure gradient across stenosis from four-dimensional flow MRI (4D flow MRI) velocities. A deep neural network 4D flow Velocity-to-Presure Network (4Dflow-VP-Net) was trained to learn the spatiotemporal relationship between velocities and pressure in stenotic vessels. Training data were simulated by computational fluid dynamics (CFD) for different pulsatile flow conditions under an aortic flow waveform. The network was tested to predict pressure from CFD-simulated velocity data, in vitro 4D flow MRI data, and in vivo 4D flow MRI data of patients with both moderate and severe aortic stenosis. TVPG derived from 4Dflow-VP-Net was compared to catheter-based pressure measurements for available flow rates, in vitro and Doppler echocardiography-based pressure measurement, in vivo.

RESULTS

Relative pressures calculated by 4Dflow-VP-Net and in vitro pressure catheterization revealed strong correlation (r2  = 0.91). Correlations analysis of TVPG from reference CFD and 4Dflow-VP-Net for 450 simulated flow conditions showed strong correlation (r2  = 0.99). TVPG from in vitro MRI had a correlation coefficient of r2  = 0.98 with reference CFD. 4Dflow-VP-Net, applied to 4D flow MRI in 16 patients, showed comparable TVPG measurement with Doppler echocardiography (r2  = 0.85). Bland-Altman analysis of TVPG measurements showed mean bias and limits of agreement of -0.20 ± 2.07 mmHg and 0.19 ± 0.45 mmHg for CFD-simulated velocities and in vitro 4D flow velocities. In patients, overestimation of Doppler echocardiography relative to TVPG from 4Dflow-VP-Net (10.99 ± 6.77 mmHg) was observed.

CONCLUSION

The proposed approach can predict relative pressure in both in vitro and in vivo 4D flow MRI of aortic stenotic patients with high fidelity.

4D Flow cardiovascular magnetic resonance consensus statement: 2023 update

Hemodynamic assessment is an integral part of the diagnosis and management of cardiovascular disease. Four-dimensional cardiovascular magnetic resonance flow imaging (4D Flow CMR) allows comprehensive and accurate assessment of flow in a single acquisition. This consensus paper is an update from the 2015 '4D Flow CMR Consensus Statement'. We elaborate on 4D Flow CMR sequence options and imaging considerations. The document aims to assist centers starting out with 4D Flow CMR of the heart and great vessels with advice on acquisition parameters, post-processing workflows and integration into clinical practice. Furthermore, we define minimum quality assurance and validation standards for clinical centers. We also address the challenges faced in quality assurance and validation in the research setting. We also include a checklist for recommended publication standards, specifically for 4D Flow CMR. Finally, we discuss the current limitations and the future of 4D Flow CMR. This updated consensus paper will further facilitate widespread adoption of 4D Flow CMR in the clinical workflow across the globe and aid consistently high-quality publication standards.

Systolic reverse flow derived from 4D flow cardiovascular magnetic resonance in bicuspid aortic valve is associated with aortic dilation and aortic valve stenosis: a cross sectional study in 655 subjects

BACKGROUND

Bicuspid aortic valve (BAV) disease is associated with increased risk of aortopathy. In addition to current intervention guidelines, BAV mediated changes in aortic 3D hemodynamics have been considered as risk stratification measures. We aimed to evaluate the association of 4D flow cardiovascular magnetic resonance (CMR) derived voxel-wise aortic reverse flow with aortic dilation and to investigate the role of aortic valve regurgitation (AR) and stenosis (AS) on reverse flow in systole and diastole.

METHODS

510 patients with BAV (52 ± 14 years) and 120 patients with trileaflet aortic valve (TAV) (61 ± 11 years) and mid-ascending aorta diameter (MAAD) > 35 mm who underwent CMR including 4D flow CMR were retrospectively included. An age and sex-matched healthy control cohort (n = 25, 49 ± 12 years) was selected. Voxel-wise reverse flow was calculated in the aorta and quantified by the mean reverse flow in the ascending aorta (AAo) during systole and diastole.

RESULTS

BAV patients without AS and AR demonstrated significantly increased systolic and diastolic reverse flow (222% and 13% increases respectively, p < 0.01) compared to healthy controls and also had significantly increased systolic reverse flow compared to TAV patients with aortic dilation (79% increase, p < 0.01). In patients with isolated AR, systolic and diastolic AAo reverse flow increased significantly with AR severity (c = - 83.2 and c = - 205.6, p < 0.001). In patients with isolated AS, AS severity was associated with an increase in both systolic (c = - 253.1, p < 0.001) and diastolic (c = - 87.0, p = 0.02) AAo reverse flow. Right and left/right and non-coronary fusion phenotype showed elevated systolic reverse flow (> 17% increase, p < 0.01). Right and non-coronary fusion phenotype showed decreased diastolic reverse flow (> 27% decrease, p < 0.01). MAAD was an independent predictor of systolic (p < 0.001), but not diastolic, reverse flow (p > 0.1).

CONCLUSION

4D flow CMR derived reverse flow associated with BAV was successfully captured even in the absence of AR or AS and in comparison to TAV patients with aortic dilation. Diastolic AAo reverse flow increased with AR severity while AS severity strongly correlated with increased systolic reverse flow in the AAo. Additionally, increasing MAAD was independently associated with increasing systolic AAo reverse flow. Thus, systolic AAo reverse flow may be a valuable metric for evaluating disease severity in future longitudinal outcome studies.

Advances in machine learning applications for cardiovascular 4D flow MRI

Four-dimensional flow magnetic resonance imaging (MRI) has evolved as a non-invasive imaging technique to visualize and quantify blood flow in the heart and vessels. Hemodynamic parameters derived from 4D flow MRI, such as net flow and peak velocities, but also kinetic energy, turbulent kinetic energy, viscous energy loss, and wall shear stress have shown to be of diagnostic relevance for cardiovascular diseases. 4D flow MRI, however, has several limitations. Its long acquisition times and its limited spatio-temporal resolutions lead to inaccuracies in velocity measurements in small and low-flow vessels and near the vessel wall. Additionally, 4D flow MRI requires long post-processing times, since inaccuracies due to the measurement process need to be corrected for and parameter quantification requires 2D and 3D contour drawing. Several machine learning (ML) techniques have been proposed to overcome these limitations. Existing scan acceleration methods have been extended using ML for image reconstruction and ML based super-resolution methods have been used to assimilate high-resolution computational fluid dynamic simulations and 4D flow MRI, which leads to more realistic velocity results. ML efforts have also focused on the automation of other post-processing steps, by learning phase corrections and anti-aliasing. To automate contour drawing and 3D segmentation, networks such as the U-Net have been widely applied. This review summarizes the latest ML advances in 4D flow MRI with a focus on technical aspects and applications. It is divided into the current status of fast and accurate 4D flow MRI data generation, ML based post-processing tools for phase correction and vessel delineation and the statistical evaluation of blood flow.