From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Motion-robust free-running volumetric cardiovascular MRI

PURPOSE

To present and assess an outlier mitigation method that makes free-running volumetric cardiovascular MRI (CMR) more robust to motion.

METHODS

The proposed method, called compressive recovery with outlier rejection (CORe), models outliers in the measured data as an additive auxiliary variable. We enforce MR physics-guided group sparsity on the auxiliary variable, and jointly estimate it along with the image using an iterative algorithm. For evaluation, CORe is first compared to traditional compressed sensing (CS), robust regression (RR), and an existing outlier rejection method using two simulation studies. Then, CORe is compared to CS using seven three-dimensional (3D) cine, 12 rest four-dimensional (4D) flow, and eight stress 4D flow imaging datasets.

RESULTS

Our simulation studies show that CORe outperforms CS, RR, and the existing outlier rejection method in terms of normalized mean square error and structural similarity index across 55 different realizations. The expert reader evaluation of 3D cine images demonstrates that CORe is more effective in suppressing artifacts while maintaining or improving image sharpness. Finally, 4D flow images show that CORe yields more reliable and consistent flow measurements, especially in the presence of involuntary subject motion or exercise stress.

CONCLUSION

An outlier rejection method is presented and tested using simulated and measured data. This method can help suppress motion artifacts in a wide range of free-running CMR applications.

Accelerated Cine Cardiac MRI Using Deep Learning-Based Reconstruction: A Systematic Evaluation

BACKGROUND

Breath-holding (BH) for cine balanced steady state free precession (bSSFP) imaging is challenging for patients with impaired BH capacity. Deep learning-based reconstruction (DLR) of undersampled k-space promises to shorten BHs while preserving image quality and accuracy of ventricular assessment.

PURPOSE

To perform a systematic evaluation of DLR of cine bSSFP images from undersampled k-space over a range of acceleration factors.

STUDY TYPE

Retrospective.

SUBJECTS

Fifteen pectus excavatum patients (mean age 16.8 ± 5.4 years, 20% female) with normal cardiac anatomy and function and 12-second BH capability.

FIELD STRENGTH/SEQUENCE

1.5-T, cine bSSFP.

ASSESSMENT

Retrospective DLR was conducted by applying compressed sensitivity encoding (C-SENSE) acceleration to systematically undersample fully sampled k-space cine bSSFP acquisition data over an acceleration/undersampling factor (R) considering a range of 2 to 8. Quality imperceptibility (QI) measures, including structural similarity index measure, were calculated using images reconstructed from fully sampled k-space as a reference. Image quality, including contrast and edge definition, was evaluated for diagnostic adequacy by three readers with varying levels of experience in cardiac MRI (>4 years, >18 years, and 1 year). Automated DL-based biventricular segmentation was performed commercially available software by cardiac radiologists with more than 4 years of experience.

STATISTICAL TESTS

Tukey box plots, linear mixed effects model, analysis of variance (ANOVA), weighted kappa, Kruskal-Wallis test, and Wilcoxon signed-rank test were employed as appropriate. A P-value <0.05 was considered statistically significant.

RESULTS

There was a significant decrease in the QI values and edge definition scores as R increased. Diagnostically adequate image quality was observed up to R = 5. The effect of R on all biventricular volumetric indices was non-significant (P = 0.447).

DATA CONCLUSION

The biventricular volumetric indices obtained from the reconstruction of fully sampled cine bSSFP acquisitions and DLR of the same k-space data undersampled by C-SENSE up to R = 5 may be comparable.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 1.

Deep learning for accelerated and robust MRI reconstruction

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices.Affiliations [3 and 6] has been split into two different affiliations. Please check if action taken is appropriate and amend if necessary.looks good.

Use of Artificial Intelligence Including Multimodal Systems to Improve the Management of Cardiovascular Disease

The rising prevalence of cardiovascular disease presents an escalating challenge for current health services, which are grappling with increasing demands. Innovative changes are imperative to sustain the delivery of high-quality patient care. Recent technological advances have resulted in the emergence of artificial intelligence as a viable solution. Advanced algorithms are now capable of performing complex analysis of large volumes of data in rapid time with exceptional accuracy. Multimodality artificial intelligence systems that leverage a diverse range of data including images, text, video, and audio. Compared to single modality systems, multimodal artificial intelligence systems appear to hold promise for enhancing overall performance and enabling smoother integration into existing workflows. Such systems can empower physicians with clinical decision support and enhanced efficiency. However, truly multimodal artificial intelligence is still scarce in the management of cardiovascular disease, a result of the complexity of the area. This opinion article aims to cover current research, emerging trends, and the future utilisation of artificial intelligence in the management of cardiovascular disease with a focus on multimodality systems.

Bringing MRI to low- and middle-income countries: Directions, challenges and potential solutions

The global disparity of magnetic resonance imaging (MRI) is a major challenge, with many low- and middle-income countries (LMICs) experiencing limited access to MRI. The reasons for limited access are technological, economic and social. With the advancement of MRI technology, we explore why these challenges still prevail, highlighting the importance of MRI as the epidemiology of disease changes in LMICs. In this paper, we establish a framework to develop MRI with these challenges in mind and discuss the different aspects of MRI development, including maximising image quality using cost-effective components, integrating local technology and infrastructure and implementing sustainable practices. We also highlight the current solutions-including teleradiology, artificial intelligence and doctor and patient education strategies-and how these might be further improved to achieve greater access to MRI.

The beating heart: artificial intelligence for cardiovascular application in the clinic

Artificial intelligence (AI) integration in cardiac magnetic resonance imaging presents new and exciting avenues for advancing patient care, automating post-processing tasks, and enhancing diagnostic precision and outcomes. The use of AI significantly streamlines the examination workflow through the reduction of acquisition and postprocessing durations, coupled with the automation of scan planning and acquisition parameters selection. This has led to a notable improvement in examination workflow efficiency, a reduction in operator variability, and an enhancement in overall image quality. Importantly, AI unlocks new possibilities to achieve spatial resolutions that were previously unattainable in patients. Furthermore, the potential for low-dose and contrast-agent-free imaging represents a stride toward safer and more patient-friendly diagnostic procedures. Beyond these benefits, AI facilitates precise risk stratification and prognosis evaluation by adeptly analysing extensive datasets. This comprehensive review article explores recent applications of AI in the realm of cardiac magnetic resonance imaging, offering insights into its transformative potential in the field.

Advanced deep learning-based image reconstruction in lumbar spine MRI at 0.55 T - Effects on image quality and acquisition time in comparison to conventional deep learning-based reconstruction

Objectives

To evaluate an optimized deep leaning-based image post-processing technique in lumbar spine MRI at 0.55 T in terms of image quality and image acquisition time.

Materials and methods

Lumbar spine imaging was conducted on 18 patients using a 0.55 T MRI scanner, employing conventional (CDLR) and advanced (ADLR) deep learning-based post-processing techniques. Two musculoskeletal radiologists visually evaluated the images using a 5-point Likert scale to assess image quality and resolution. Quantitative assessment in terms of signal intensities (SI) and contrast ratios was performed by region of interest measurements in different body-tissues (vertebral bone, intervertebral disc, spinal cord, cerebrospinal fluid and autochthonous back muscles) to investigate differences between CDLR and ADLR sequences.

Results

The images processed with the advanced technique (ADLR) were rated superior to the conventional technique (CDLR) in terms of signal/contrast, resolution, and assessability of the spinal canal and neural foramen. The interrater agreement was moderate for signal/contrast (ICC = 0.68) and good for resolution (ICC = 0.77), but moderate for spinal canal and neuroforaminal assessability (ICC = 0.55). Quantitative assessment showed a higher contrast ratio for fluid-sensitive sequences in the ADLR images. The use of ADLR reduced image acquisition time by 44.4%, from 14:22 min to 07:59 min.

Conclusions

Advanced deep learning-based image reconstruction algorithms improve the visually perceived image quality in lumbar spine imaging at 0.55 T while simultaneously allowing to substantially decrease image acquisition times.

Clinical relevance

Advanced deep learning-based image post-processing techniques (ADLR) in lumbar spine MRI at 0.55 T significantly improves image quality while reducing image acquisition time.

Fast MRI Reconstruction Using Deep Learning-based Compressed Sensing: A Systematic Review

Magnetic resonance imaging (MRI) has revolutionized medical imaging, providing a non-invasive and highly detailed look into the human body. However, the long acquisition times of MRI present challenges, causing patient discomfort, motion artifacts, and limiting real-time applications. To address these challenges, researchers are exploring various techniques to reduce acquisition time and improve the overall efficiency of MRI. One such technique is compressed sensing (CS), which reduces data acquisition by leveraging image sparsity in transformed spaces. In recent years, deep learning (DL) has been integrated with CS-MRI, leading to a new framework that has seen remarkable growth. DL-based CS-MRI approaches are proving to be highly effective in accelerating MR imaging without compromising image quality. This review comprehensively examines DL-based CS-MRI techniques, focusing on their role in increasing MR imaging speed. We provide a detailed analysis of each category of DL-based CS-MRI including end-to-end, unroll optimization, self-supervised, and federated learning. Our systematic review highlights significant contributions and underscores the exciting potential of DL in CS-MRI. Additionally, our systematic review efficiently summarizes key results and trends in DL-based CS-MRI including quantitative metrics, the dataset used, acceleration factors, and the progress of and research interest in DL techniques over time. Finally, we discuss potential future directions and the importance of DL-based CS-MRI in the advancement of medical imaging. To facilitate further research in this area, we provide a GitHub repository that includes up-to-date DL-based CS-MRI publications and publicly available datasets - https://github.com/mosaf/Awesome-DL-based-CS-MRI.

Computer-aided analysis of radiological images for cancer diagnosis: performance analysis on benchmark datasets, challenges, and directions

Radiological image analysis using machine learning has been extensively applied to enhance biopsy diagnosis accuracy and assist radiologists with precise cures. With improvements in the medical industry and its technology, computer-aided diagnosis (CAD) systems have been essential in detecting early cancer signs in patients that could not be observed physically, exclusive of introducing errors. CAD is a detection system that combines artificially intelligent techniques with image processing applications thru computer vision. Several manual procedures are reported in state of the art for cancer diagnosis. Still, they are costly, time-consuming and diagnose cancer in late stages such as CT scans, radiography, and MRI scan. In this research, numerous state-of-the-art approaches on multi-organs detection using clinical practices are evaluated, such as cancer, neurological, psychiatric, cardiovascular and abdominal imaging. Additionally, numerous sound approaches are clustered together and their results are assessed and compared on benchmark datasets. Standard metrics such as accuracy, sensitivity, specificity and false-positive rate are employed to check the validity of the current models reported in the literature. Finally, existing issues are highlighted and possible directions for future work are also suggested.

A motion-corrected deep-learning reconstruction framework for accelerating whole-heart magnetic resonance imaging in patients with congenital heart disease

BACKGROUND

Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment and management of adult patients with congenital heart disease (CHD). However, conventional techniques for three-dimensional (3D) whole-heart acquisition involve long and unpredictable scan times and methods that accelerate scans via k-space undersampling often rely on long iterative reconstructions. Deep-learning-based reconstruction methods have recently attracted much interest due to their capacity to provide fast reconstructions while often outperforming existing state-of-the-art methods. In this study, we sought to adapt and validate a non-rigid motion-corrected model-based deep learning (MoCo-MoDL) reconstruction framework for 3D whole-heart MRI in a CHD patient cohort.

METHODS

The previously proposed deep-learning reconstruction framework MoCo-MoDL, which incorporates a non-rigid motion-estimation network and a denoising regularization network within an unrolled iterative reconstruction, was trained in an end-to-end manner using 39 CHD patient datasets. Once trained, the framework was evaluated in eight CHD patient datasets acquired with seven-fold prospective undersampling. Reconstruction quality was compared with the state-of-the-art non-rigid motion-corrected patch-based low-rank reconstruction method (NR-PROST) and against reference images (acquired with three-or-four-fold undersampling and reconstructed with NR-PROST).

RESULTS

Seven-fold undersampled scan times were 2.1 ± 0.3 minutes and reconstruction times were ∼30 seconds, approximately 240 times faster than an NR-PROST reconstruction. Image quality comparable to the reference images was achieved using the proposed MoCo-MoDL framework, with no statistically significant differences found in any of the assessed quantitative or qualitative image quality measures. Additionally, expert image quality scores indicated the MoCo-MoDL reconstructions were consistently of a higher quality than the NR-PROST reconstructions of the same data, with the differences in 12 of the 22 scores measured for individual vascular structures found to be statistically significant.

CONCLUSION

The MoCo-MoDL framework was applied to an adult CHD patient cohort, achieving good quality 3D whole-heart images from ∼2-minute scans with reconstruction times of ∼30 seconds.

Accelerated 3D MR neurography of the brachial plexus using deep learning-constrained compressed sensing

OBJECTIVES

To explore the use of deep learning-constrained compressed sensing (DLCS) in improving image quality and acquisition time for 3D MRI of the brachial plexus.

METHODS

Fifty-four participants who underwent contrast-enhanced imaging and forty-one participants who underwent unenhanced imaging were included. Sensitivity encoding with an acceleration of 2 × 2 (SENSE4x), CS with an acceleration of 4 (CS4x), and DLCS with acceleration of 4 (DLCS4x) and 8 (DLCS8x) were used for MRI of the brachial plexus. Apparent signal-to-noise ratios (aSNRs), apparent contrast-to-noise ratios (aCNRs), and qualitative scores on a 4-point scale were evaluated and compared by ANOVA and the Friedman test. Interobserver agreement was evaluated by calculating the intraclass correlation coefficients.

RESULTS

DLCS4x achieved higher aSNR and aCNR than SENSE4x, CS4x, and DLCS8x (all p < 0.05). For the root segment of the brachial plexus, no statistically significant differences in the qualitative scores were found among the four sequences. For the trunk segment, DLCS4x had higher scores than SENSE4x (p = 0.04) in the contrast-enhanced group and had higher scores than SENSE4x and DLCS8x in the unenhanced group (all p < 0.05). For the divisions, cords, and branches, DLCS4x had higher scores than SENSE4x, CS4x, and DLCS8x (all p ≤ 0.01). No overt difference was found among SENSE4x, CS4x, and DLCS8x in any segment of the brachial plexus (all p > 0.05).

CONCLUSIONS

In three-dimensional MRI for the brachial plexus, DLCS4x can improve image quality compared with SENSE4x and CS4x, and DLCS8x can maintain the image quality compared to SENSE4x and CS4x.

CLINICAL RELEVANCE STATEMENT

Deep learning-constrained compressed sensing can improve the image quality or accelerate acquisition of 3D MRI of the brachial plexus, which should be benefit in evaluating the brachial plexus and its branches in clinical practice.

KEY POINTS

•Deep learning-constrained compressed sensing showed higher aSNR, aCNR, and qualitative scores for the brachial plexus than SENSE and CS at the same acceleration factor with similar scanning time. •Deep learning-constrained compressed sensing at acceleration factor of 8 had comparable aSNR, aCNR, and qualitative scores to SENSE4x and CS4x with approximately half the examination time. •Deep learning-constrained compressed sensing may be helpful in clinical practice for improving image quality and acquisition time in three-dimensional MRI of the brachial plexus.

An applicability study of rapid artificial intelligence-assisted compressed sensing (ACS) in anal fistula magnetic resonance imaging

Objective

To evaluate the applicability of artificial intelligence-assisted compressed sensing (ACS) to anal fistula magnetic resonance imaging (MRI).

Methods

51 patients were included in this study and underwent T2-weighted sequence of MRI examinations both with ACS and without ACS technology in a 3.0 T MR scanner. Subjective image quality scores, and objective image quality-related metrics including scanning time, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR), were evaluated and statistically compared between the images collected with and without ACS.

Results

No significant difference in the subjective image quality of lesion conspicuity was observed between the two groups. However, ACS MRI decreased the acquisition time with regard to control group (74.00 s vs. 156.00 s). Besides, SNR of perianal and muscle in the ACS group was significantly higher than that of the control group (164.07 ± 33.35 vs 130.81 ± 29.10, p < 0.001; 109.87 ± 22.01 vs 87.61 ± 17.95, p < 0.001; respectively). The CNR was significantly higher in the ACS group than in the control group (54.02 ± 23.98 vs 43.20 ± 21.00; p < 0.001). Moreover, the accuracy rate of the ACS groups in evaluating the direction and internal opening of the fistula was 88.89 %, exactly the same as that of the control group.

Conclusion

We demonstrated the applicability of using ACS to accelerate MR of anal fistulas with improved SNR and CNR. Meanwhile, the accuracy rates of the ACS group and the control were equivalent in evaluating the direction and internal opening of the fistula, based on the results of surgical exploration.

Learning to deep learning: statistics and a paradigm test in selecting a UNet architecture to enhance MRI

OBJECTIVE

This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics.

MATERIALS AND METHODS

To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters.

RESULTS

ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA.

DISCUSSION

These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.

Deep Learning-Based Acceleration of Compressed Sensing for Noncontrast-Enhanced Coronary Magnetic Resonance Angiography in Patients With Suspected Coronary Artery Disease

BACKGROUND

The clinical application of coronary MR angiography (MRA) remains limited due to its long acquisition time and often unsatisfactory image quality. A compressed sensing artificial intelligence (CSAI) framework was recently introduced to overcome these limitations, but its feasibility in coronary MRA is unknown.

PURPOSE

To evaluate the diagnostic performance of noncontrast-enhanced coronary MRA with CSAI in patients with suspected coronary artery disease (CAD).

STUDY TYPE

Prospective observational study.

POPULATION

A total of 64 consecutive patients (mean age ± standard deviation [SD]: 59 ± 10 years, 48.4% females) with suspected CAD.

FIELD STRENGTH/SEQUENCE

A 3.0-T, balanced steady-state free precession sequence.

ASSESSMENT

Three observers evaluated the image quality for 15 coronary segments of the right and left coronary arteries using a 5-point scoring system (1 = not visible; 5 = excellent). Image scores ≥3 were considered diagnostic. Furthermore, the detection of CAD with ≥50% stenosis was evaluated in comparison to reference standard coronary computed tomography angiography (CTA). Mean acquisition times for CSAI-based coronary MRA were measured.

STATISTICAL TESTS

For each patient, vessel and segment, sensitivity, specificity, and diagnostic accuracy of CSAI-based coronary MRA for detecting CAD with ≥50% stenosis according to coronary CTA were calculated. Intraclass correlation coefficients (ICCs) were used to assess the interobserver agreement.

RESULTS

The mean MR acquisition time ± SD was 8.1 ± 2.4 minutes. Twenty-five (39.1%) patients had CAD with ≥50% stenosis on coronary CTA and 29 (45.3%) patients on MRA. A total of 885 segments on the CTA images and 818/885 (92.4%) coronary MRA segments were diagnostic (image score ≥3). The sensitivity, specificity, and diagnostic accuracy were as follows: per patient (92.0%, 84.6%, and 87.5%), per vessel (82.9%, 93.4%, and 91.1%), and per segment (77.6%, 98.2%, and 96.6%), respectively. The ICCs for image quality and stenosis assessment were 0.76-0.99 and 0.66-1.00, respectively.

DATA CONCLUSION

The image quality and diagnostic performance of coronary MRA with CSAI may show good results in comparison to coronary CTA in patients with suspected CAD.

EVIDENCE LEVEL

1.

TECHNICAL EFFICACY

2.

Comprehensive assessment of molecular function, tissue characterization, and hemodynamic performance by non-invasive hybrid imaging: Potential role of cardiac PETMR

Noninvasive cardiovascular imaging plays a key role in diagnosis and patient management including monitoring treatment efficacy. The usefulness of noninvasive cardiovascular imaging has been extensively studied and shown to have high diagnostic reliability and prognostic significance, while the nondiagnostic results frequently encountered with single imaging modality require complementary or alternative imaging techniques. Hybrid cardiac imaging was initially introduced to integrate anatomical and functional information to enhance the diagnostic performance, and lately employed as a strategy for comprehensive assessment of the underlying pathophysiology of diseases. More recently, the utility of computed tomography has grown in diversity, and emerged from being an exploratory technique allowing functional measurement such as stress dynamic perfusion. Cardiac magnetic resonance imaging (CMR) is widely accepted as a robust tool for evaluation of cardiac function, fibrosis, and edema, yielding high spatial resolution and soft-tissue contrast. However, the use of intravenous contrast materials is typically required for accurate diagnosis with these imaging modalities, despite the associated risk of renal toxicity. Nuclear cardiology, established as a molecular imaging technique, has advantages in visualization of the disease-specific biological process at cellular level using numerous probes without requiring contrast materials. Various imaging modalities should be appropriately used sequentially to assess concomitant disease and the progression over time. Therefore, simultaneous evaluation combining high spatial resolution and disease-specific imaging probe is a useful approach to identify the regional activity and the stage of the disease. Given the recent advance and potential of multiparametric CMR and novel nuclide tracers, hybrid positron emission tomography MR is becoming an ideal tool for disease-specific imaging.

Compressed sensing cine imaging with higher temporal resolution for analysis of left atrial strain and strain rate by cardiac magnetic resonance feature tracking

PURPOSE

Cardiac magnetic resonance (CMR) feature tracking (FT) is more widely used in the measurement of left atrial (LA) strain and strain rate (SR). However, in recent years, researchers have attempted to improve the low temporal resolution of CMR-FT to better capture the subtle deformations of the myocardium. The technique of compressed sensing (CS) has been applied clinically, reducing scan time while increasing temporal resolution. The purpose of this study was to explore the effect of the increased temporal resolution of CS cine sequences on the analysis of LA longitudinal strain and SR.

MATERIALS AND METHODS

Twenty-nine healthy subjects were included in the study. They underwent CMR with a reference steady-state free precession cine sequence of conventional temporal resolution (standard SSFP sequence), a cine sequence of higher temporal resolution (HT sequence), and an HT cine sequence with CS (CS HT sequence) (temporal resolution: 22.1-44.3/24.9-47.1 ms, 11.1-19.4 ms, and 8.3-19.4 ms, respectively). The standard SSFP sequence, HT sequence, and CS HT sequence were acquired in all subjects during the same scanning session. LA longitudinal strain and SR, reflecting LA reservoir, conduit, and contraction booster-pump function, were measured by CMR-FT and compared among the three sequences.

RESULTS

The measurements of LASR reservoir, conduit, and booster-pump were significantly higher on the HT and CS HT sequences than on the standard SSFP sequence. The standard SSFP sequence was correlated significantly with the HT and CS HT sequences in terms of LA strain and SR analysis, respectively. The LA strain and SR measurements also showed excellent agreement between the HT and CS HT sequences.

CONCLUSION

Higher temporal resolution led to significantly higher measured LASR values in CMR-FT. Furthermore, the addition of CS reduced scan time and did not affect LA longitudinal strain or SR analysis.

Artificial Intelligence in Cardiology: An Australian Perspective

Significant advances have been made in artificial intelligence technology in recent years. Many health care applications have been investigated to assist clinicians and the technology is close to being integrated into routine clinical practice. The high prevalence of cardiac disease in Australia places overwhelming demands on the existing health care system, challenging its capacity to provide quality patient care. Artificial intelligence has emerged as a promising solution. This discussion paper provides an Australian perspective on the current state of artificial intelligence in cardiology, including the benefits and challenges of implementation. This paper highlights some current artificial intelligence applications in cardiology, while also detailing challenges such as data privacy, ethical considerations, and integration within existing health infrastructures. Overall, this paper aims to provide insights into the potential benefits of artificial intelligence in cardiology, while also acknowledging the barriers that need to be addressed to ensure safe and effective implementation into an Australian health system.

AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis

BACKGROUND

Contrast-enhancing (CE) lesions are an important finding on brain magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) but can be missed easily. Automated solutions for reliable CE lesion detection are emerging; however, independent validation of artificial intelligence (AI) tools in the clinical routine is still rare.

METHODS

A three-dimensional convolutional neural network for CE lesion segmentation was trained externally on 1488 datasets of 934 MS patients from 81 scanners using concatenated information from FLAIR and T1-weighted post-contrast imaging. This externally trained model was tested on an independent dataset comprising 504 T1-weighted post-contrast and FLAIR image datasets of MS patients from clinical routine. Two neuroradiologists (R1, R2) labeled CE lesions for gold standard definition in the clinical test dataset. The algorithmic output was evaluated on both patient- and lesion-level.

RESULTS

On a patient-level, recall, specificity, precision, and accuracy of the AI tool to predict patients with CE lesions were 0.75, 0.99, 0.91, and 0.96. The agreement between the AI tool and both readers was within the range of inter-rater agreement (Cohen's kappa; AI vs. R1: 0.69; AI vs. R2: 0.76; R1 vs. R2: 0.76). On a lesion-level, false negative lesions were predominately found in infratentorial location, significantly smaller, and at lower contrast than true positive lesions (p < 0.05).

CONCLUSIONS

AI-based identification of CE lesions on brain MRI is feasible, approaching human reader performance in independent clinical data and might be of help as a second reader in the neuroradiological assessment of active inflammation in MS patients.

CRITICAL RELEVANCE STATEMENT

Al-based detection of contrast-enhancing multiple sclerosis lesions approaches human reader performance, but careful visual inspection is still needed, especially for infratentorial, small and low-contrast lesions.

Automated T1 and T2 mapping segmentation on cardiovascular magnetic resonance imaging using deep learning

Introduction

Structural and functional heart abnormalities can be examined non-invasively with cardiac magnetic resonance imaging (CMR). Thanks to the development of MR devices, diagnostic scans can capture more and more relevant information about possible heart diseases. T1 and T2 mapping are such novel technology, providing tissue specific information even without the administration of contrast material. Artificial intelligence solutions based on deep learning have demonstrated state-of-the-art results in many application areas, including medical imaging. More specifically, automated tools applied at cine sequences have revolutionized volumetric CMR reporting in the past five years. Applying deep learning models to T1 and T2 mapping images can similarly improve the efficiency of post-processing pipelines and consequently facilitate diagnostic processes.

Methods

In this paper, we introduce a deep learning model for myocardium segmentation trained on over 7,000 raw CMR images from 262 subjects of heterogeneous disease etiology. The data were labeled by three experts. As part of the evaluation, Dice score and Hausdorff distance among experts is calculated, and the expert consensus is compared with the model's predictions.

Results

Our deep learning method achieves 86% mean Dice score, while contours provided by three experts on the same data show 90% mean Dice score. The method's accuracy is consistent across epicardial and endocardial contours, and on basal, midventricular slices, with only 5% lower results on apical slices, which are often challenging even for experts.

Conclusions

We trained and evaluated a deep learning based segmentation model on 262 heterogeneous CMR cases. Applying deep neural networks to T1 and T2 mapping could similarly improve diagnostic practices. Using the fine details of T1 and T2 mapping images and high-quality labels, the objective of this research is to approach human segmentation accuracy with deep learning.

Fully-modelled blood-focused variable inversion times for 3D late gadolinium-enhanced imaging

PURPOSE

Variable heart rate during single-cycle inversion-recovery Late Gadolinium-Enhanced (LGE) scanning degrades image quality, which can be mitigated using Variable Inversion Times (VTIs) in real-time response to R-R interval changes. We investigate in vivo and in simulations an extension of a single-cycle VTI method previously applied in 3D LGE imaging, that now fully models the longitudinal magnetisation (fmVTI).

METHODS

The VTI and fmVTI methods were used to perform 3D LGE scans for 28 3D LGE patients, with qualitative image quality scores assigned for left atrial wall clarity and total ghosting. Accompanying simulations of numerical phantom images were assessed in terms of ghosting of normal myocardium, blood, and myocardial scar.

RESULTS

The numerical simulations for fmVTI showed a significant decrease in blood ghosting (VTI: 410 ± 710, fmVTI: 68 ± 40, p < 0.0005) and scar ghosting (VTI: 830 ± 1300, fmVTI: 510 ± 730, p < 0.02). Despite this, there was no significant change in qualitative image quality scores, either for left atrial wall clarity (VTI: 2.0 ± 1.0, fmVTI: 1.8 ± 1.0, p > 0.1) or for total ghosting (VTI: 1.9 ± 1.0, fmVTI: 2.0 ± 1.0, p > 0.7).

CONCLUSIONS

Simulations indicated reduced ghosting with the fmVTI method, due to reduced Mz variability in the blood signal. However, other sources of phase-encode ghosting and blurring appeared to dominate and obscure this finding in the patient studies available.

Rapid 3D breath-hold MR cholangiopancreatography using deep learning-constrained compressed sensing reconstruction

OBJECTIVES

To compare the image quality of three-dimensional breath-hold magnetic resonance cholangiopancreatography with deep learning-based compressed sensing reconstruction (3D DL-CS-MRCP) to those of 3D breath-hold MRCP with compressed sensing (3D CS-MRCP), 3D breath-hold MRCP with gradient and spin-echo (3D GRASE-MRCP) and conventional 2D single-shot breath-hold MRCP (2D MRCP).

METHODS

In total, 102 consecutive patients who underwent MRCP at 3.0 T, including 2D MRCP, 3D GRASE-MRCP, 3D CS-MRCP, and 3D DL-CS-MRCP, were prospectively included. Two radiologists independently analyzed the overall image quality, background suppression, artifacts, and visualization of pancreaticobiliary ducts using a five-point scale. The signal-to-noise ratio (SNR) of the common bile duct (CBD), contrast-to-noise ratio (CNR) of the CBD and liver, and contrast ratio between the periductal tissue and CBD were measured. The Friedman test was performed to compare the four protocols.

RESULTS

3D DL-CS-MRCP resulted in improved SNR and CNR values compared with those in the other three protocols, and better contrast ratio compared with that in 3D CS-MRCP and 3D GRASE-MRCP (all, p < 0.05). Qualitative image analysis showed that 3D DL-CS-MRCP had better performance for second-level intrahepatic ducts and distal main pancreatic ducts compared with 3D CS-MRCP (all, p < 0.05). Compared with 2D MRCP, 3D DL-CS-MRCP demonstrated better performance for the second-order left intrahepatic duct but was inferior in assessing the main pancreatic duct (all, p < 0.05). Moreover, the image quality was significantly higher in 3D DL-CS-MRCP than in 3D GRASE-MRCP.

CONCLUSION

3D DL-CS-MRCP has superior performance compared with that of 3D CS-MRCP or 3D GRASE-MRCP. Deep learning reconstruction also provides a comparable image quality but with inferior main pancreatic duct compared with that revealed by 2D MRCP.

KEY POINTS

• 3D breath-hold MRCP with deep learning reconstruction (3D DL-CS-MRCP) demonstrated improved image quality compared with that of 3D MRCP with compressed sensing or GRASE. • Compared with 2D MRCP, 3D DL-CS-MRCP had superior performance in SNR and CNR, better visualization of the left second-level intrahepatic bile ducts, and comparable overall image quality, but an inferior main pancreatic duct.

Deep Learning-Based Reconstruction for Cardiac MRI: A Review

Cardiac magnetic resonance (CMR) is an essential clinical tool for the assessment of cardiovascular disease. Deep learning (DL) has recently revolutionized the field through image reconstruction techniques that allow unprecedented data undersampling rates. These fast acquisitions have the potential to considerably impact the diagnosis and treatment of cardiovascular disease. Herein, we provide a comprehensive review of DL-based reconstruction methods for CMR. We place special emphasis on state-of-the-art unrolled networks, which are heavily based on a conventional image reconstruction framework. We review the main DL-based methods and connect them to the relevant conventional reconstruction theory. Next, we review several methods developed to tackle specific challenges that arise from the characteristics of CMR data. Then, we focus on DL-based methods developed for specific CMR applications, including flow imaging, late gadolinium enhancement, and quantitative tissue characterization. Finally, we discuss the pitfalls and future outlook of DL-based reconstructions in CMR, focusing on the robustness, interpretability, clinical deployment, and potential for new methods.

Latest Advances in Image Acceleration: All Dimensions are Fair Game

Magnetic resonance imaging (MRI) is a versatile modality that can generate high-resolution images with a variety of tissue contrasts. However, MRI is a slow technique and requires long acquisition times, which increase with higher temporal and spatial resolution and/or when multiple contrasts and large volumetric coverage is required. In order to speedup MR data acquisition, several approaches have been introduced in the literature. Most of these techniques acquire less data than required and exploit intrinsic redundancies in the MR images to recover the information that was not sampled. This article presents a review of MR acquisition and reconstruction methods that have exploited redundancies in the temporal, spatial, and contrast/parametric dimensions to accelerate image data acquisition, focusing on cardiac and abdominal MR imaging applications. The review describes how each of these dimensions has been separately exploited for speeding up MR acquisition to then discuss more advanced techniques where multiple dimensions are exploited together for further reducing scan times. Finally, future directions for multidimensional image acceleration and remaining technical challenges are discussed. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: 1.

Self-calibrated through-time spiral GRAPPA for real-time, free-breathing evaluation of left ventricular function

PURPOSE

Through-time spiral GRAPPA is a real-time imaging technique that enables ungated, free-breathing evaluation of the left ventricle. However, it requires a separate fully-sampled calibration scan to calculate GRAPPA weights. A self-calibrated through-time spiral GRAPPA method is proposed that uses a specially designed spiral trajectory with interleaved arm ordering such that consecutive undersampled frames can be merged to form calibration data, eliminating the separate fully-sampled acquisition.

THEORY AND METHODS

The proposed method considers the time needed to acquire data at all points in a GRAPPA calibration kernel when using interleaved arm ordering. Using this metric, simulations were performed to design a spiral trajectory for self-calibrated GRAPPA. Data were acquired in healthy volunteers using the proposed method and a comparison electrocardiogram-gated and breath-held cine scan. Left ventricular functional values and image quality are compared.

RESULTS

A 12-arm spiral trajectory was designed with a temporal resolution of 32.72 ms/cardiac phase with an acceleration factor of 3. Functional values calculated using the proposed method and the gold-standard method were not statistically significantly different (paired t-test, p < 0.05). Image quality ratings were lower for the proposed method, with statistically significantly different ratings (Wilcoxon signed rank test, p < 0.05) for two of five image quality aspects rated (level of artifact, blood-myocardium contrast).

CONCLUSIONS

A self-calibrated through-time spiral GRAPPA reconstruction can enable ungated, free-breathing evaluation of the left ventricle in 71 s. Functional values are equivalent to a gold-standard cine technique, although some aspects of image quality may be inferior due to the real-time nature of the data collection.

Respiratory Motion Management in Abdominal MRI: Radiology In Training

A 96-year-old woman had a suboptimal evaluation of liver observations at abdominal MRI due to significant respiratory motion. State-of-the-art strategies to minimize respiratory motion during clinical abdominal MRI are discussed.

Variational Manifold Learning From Incomplete Data: Application to Multislice Dynamic MRI

Current deep learning-based manifold learning algorithms such as the variational autoencoder (VAE) require fully sampled data to learn the probability density of real-world datasets. However, fully sampled data is often unavailable in a variety of problems, including the recovery of dynamic and high-resolution magnetic resonance imaging (MRI). We introduce a novel variational approach to learn a manifold from undersampled data. The VAE uses a decoder fed by latent vectors, drawn from a conditional density estimated from the fully sampled images using an encoder. Since fully sampled images are not available in our setting, we approximate the conditional density of the latent vectors by a parametric model whose parameters are estimated from the undersampled measurements using back-propagation. We use the framework for the joint alignment and recovery of multi-slice free breathing and ungated cardiac MRI data from highly undersampled measurements. Experimental results demonstrate the utility of the proposed scheme in dynamic imaging alignment and reconstructions.

Cardiovascular Imaging in China: Yesterday, Today, and Tomorrow

The high prevalence and mortality of cardiovascular diseases in China's large population has increased the use of cardiovascular imaging for the assessment of conditions in recent years. In this study, we review the past 20 years of cardiovascular imaging in China, the increasingly important role played by cardiovascular computed tomography in coronary artery disease and pulmonary embolism assessment, magnetic resonance imaging's use for cardiomyopathy assessment, the development and application of artificial intelligence in cardiovascular imaging, and the future of Chinese cardiovascular imaging.

Artificial intelligence in cardiology: Hope for the future and power for the present

Cardiovascular disease (CVD) is the principal cause of mortality and morbidity globally. With the pressures for improved care and translation of the latest medical advances and knowledge to an actionable plan, clinical decision-making for cardiologists is challenging. Artificial Intelligence (AI) is a field in computer science that studies the design of intelligent agents which take the best feasible action in a situation. It incorporates the use of computational algorithms which simulate and perform tasks that traditionally require human intelligence such as problem solving and learning. Whilst medicine is arguably the last to apply AI in its everyday routine, cardiology is at the forefront of AI revolution in the medical field. The development of AI methods for accurate prediction of CVD outcomes, non-invasive diagnosis of coronary artery disease (CAD), detection of malignant arrythmias through wearables, and diagnosis, treatment strategies and prediction of outcomes for heart failure (HF) patients, demonstrates the potential of AI in future cardiology. With the advancements of AI, Internet of Things (IoT) and the promotion of precision medicine, the future of cardiology will be heavily based on these innovative digital technologies. Despite this, ethical dilemmas regarding the implementation of AI technologies in real-world are still unaddressed.

Simultaneous multi-parametric acquisition and reconstruction techniques in cardiac magnetic resonance imaging: Basic concepts and status of clinical development

Simultaneous multi-parametric acquisition and reconstruction techniques (SMART) are gaining attention for their potential to overcome some of cardiovascular magnetic resonance imaging's (CMR) clinical limitations. The major advantages of SMART lie within their ability to simultaneously capture multiple "features" such as cardiac motion, respiratory motion, T1/T2 relaxation. This review aims to summarize the overarching theory of SMART, describing key concepts that many of these techniques share to produce co-registered, high quality CMR images in less time and with less requirements for specialized personnel. Further, this review provides an overview of the recent developments in the field of SMART by describing how they work, the parameters they can acquire, their status of clinical testing and validation, and by providing examples for how their use can improve the current state of clinical CMR workflows. Many of the SMART are in early phases of development and testing, thus larger scale, controlled trials are needed to evaluate their use in clinical setting and with different cardiac pathologies.

Accelerating 3D MTC-BOOST in patients with congenital heart disease using a joint multi-scale variational neural network reconstruction

PURPOSE

Free-breathing Magnetization Transfer Contrast Bright blOOd phase SensiTive (MTC-BOOST) is a prototype balanced-Steady-State Free Precession sequence for 3D whole-heart imaging, that employs the endogenous magnetisation transfer contrast mechanism. This achieves reduction of flow and off-resonance artefacts, that often arise with the clinical T2prepared balanced-Steady-State Free Precession sequence, enabling high quality, contrast-agent free imaging of the thoracic cardiovascular anatomy. Fully-sampled MTC-BOOST acquisition requires long scan times (~10-24 min) and therefore acceleration is needed to permit its clinical incorporation. The aim of this study is to enable and clinically validate the 5-fold accelerated MTC-BOOST acquisition with joint Multi-Scale Variational Neural Network (jMS-VNN) reconstruction.

METHODS

Thirty-six patients underwent free-breathing, 3D whole-heart imaging with the MTC-BOOST sequence, which is combined with variable density spiral-like Cartesian sampling and 2D image navigators for translational motion estimation. This sequence acquires two differently weighted bright-blood volumes in an interleaved fashion, which are then joined in a phase sensitive inversion recovery reconstruction to obtain a complementary fully co-registered black-blood volume. Data from eighteen patients were used for training, whereas data from the remaining eighteen patients were used for testing/evaluation. The proposed deep-learning based approach adopts a supervised multi-scale variational neural network for joint reconstruction of the two differently weighted bright-blood volumes acquired with the 5-fold accelerated MTC-BOOST. The two contrast images are stacked as different channels in the network to exploit the shared information. The proposed approach is compared to the fully-sampled MTC-BOOST and 5-fold undersampled MTC-BOOST acquisition with Compressed Sensing (CS) reconstruction in terms of scan/reconstruction time and bright-blood image quality. Comparison against conventional 2-fold undersampled T2-prepared 3D bright-blood whole-heart clinical sequence (T2prep-3DWH) is also included.

RESULTS

Acquisition time was 3.0 ± 1.0 min for the 5-fold accelerated MTC-BOOST versus 9.0 ± 1.1 min for the fully-sampled MTC-BOOST and 11.1 ± 2.6 min for the T2prep-3DWH (p < 0.001 and p < 0.001, respectively). Reconstruction time was significantly lower with the jMS-VNN method compared to CS (10 ± 0.5 min vs 20 ± 2 s, p < 0.001). Image quality was higher for the proposed 5-fold undersampled jMS-VNN versus conventional CS, comparable or higher to the corresponding T2prep-3DWH dataset and similar to the fully-sampled MTC-BOOST.

CONCLUSION

The proposed 5-fold accelerated jMS-VNN MTC-BOOST framework provides efficient 3D whole-heart bright-blood imaging in fast acquisition and reconstruction time with concomitant reduction of flow and off-resonance artefacts, that are frequently encountered with the clinical sequence. Image quality of the cardiac anatomy and thoracic vasculature is comparable or superior to the clinical scan and 5-fold CS reconstruction in faster reconstruction time, promising potential clinical adoption.

Artificial intelligence in cardiac magnetic resonance fingerprinting

Magnetic resonance fingerprinting (MRF) is a fast MRI-based technique that allows for multiparametric quantitative characterization of the tissues of interest in a single acquisition. In particular, it has gained attention in the field of cardiac imaging due to its ability to provide simultaneous and co-registered myocardial T₁ and T₂ mapping in a single breath-held cardiac MRF scan, in addition to other parameters. Initial results in small healthy subject groups and clinical studies have demonstrated the feasibility and potential of MRF imaging. Ongoing research is being conducted to improve the accuracy, efficiency, and robustness of cardiac MRF. However, these improvements usually increase the complexity of image reconstruction and dictionary generation and introduce the need for sequence optimization. Each of these steps increase the computational demand and processing time of MRF. The latest advances in artificial intelligence (AI), including progress in deep learning and the development of neural networks for MRI, now present an opportunity to efficiently address these issues. Artificial intelligence can be used to optimize candidate sequences and reduce the memory demand and computational time required for reconstruction and post-processing. Recently, proposed machine learning-based approaches have been shown to reduce dictionary generation and reconstruction times by several orders of magnitude. Such applications of AI should help to remove these bottlenecks and speed up cardiac MRF, improving its practical utility and allowing for its potential inclusion in clinical routine. This review aims to summarize the latest developments in artificial intelligence applied to cardiac MRF. Particularly, we focus on the application of machine learning at different steps of the MRF process, such as sequence optimization, dictionary generation and image reconstruction.

Optimization of through-time radial GRAPPA with coil compression and weight sharing

PURPOSE

This work proposes principal component analysis (PCA) coil compression and weight sharing to reduce acquisition and reconstruction time of through-time radial GRAPPA.

METHODS

Through-time radial GRAPPA enables ungated free-breathing motion-resolved cardiac imaging but requires a long calibration acquisition and GRAPPA weight calculation time. PCA coil compression reduces calibration data requirements and associated acquisition time, and weight sharing reduces the number of unique GRAPPA weight sets and associated weight computation time. In vivo cardiac data reconstructed with coil compression and weight sharing are compared to a gold standard to demonstrate improvement in calibration acquisition and reconstruction performance with minimal loss of image quality.

RESULTS

Coil compression from 30 physical to 12 virtual coils (90% of signal variance) decreases requisite calibration data by 60%, reducing calibration acquisition time to 6.7 s/slice from 31.5 s/slice reported in original through-time radial GRAPPA work. Resulting images have small increase in RMS error (RMSE). Reconstruction with a weight sharing factor of 8 results in eight-fold reduction in GRAPPA weight calculation time with a comparable RMSE to reconstructions with no weight sharing. Optimized parameters for coil compression and weight sharing applied to reconstructions enables images to be collected with a temporal resolution of 66 ms/frame and spatial resolution of 2.34 × 2.34 mm while reducing calibration acquisition time from 34 to 6.7 s, weight calculation time from 200 to 3 s, and weight application time 18 to 5 s.

CONCLUSION

Coil compression and weight sharing applied to through-time radial GRAPPA enables fast free-breathing ungated cardiac cine without compromising image quality.

Feasibility of one breath-hold cardiovascular magnetic resonance compressed sensing cine for left ventricular strain analysis

Objective

To investigate the feasibility of 3D left ventricular global and regional strain by using one breath-hold (BH) compressed sensing cine (CSC) protocol and determine the agreement between CSC and conventional cine (CC) protocols.

Methods

A total of 30 volunteers were enrolled in this study. Cardiovascular magnetic resonance (CMR) images were acquired using a 1.436 T magnetic resonance imaging (MRI) system. The CSC protocols included one BH CSC and the shortest BH CSC protocols with different parameters and were only performed in short-axis (SA) view following CC protocols. Left ventricular (LV) end-diastole volume (EDV), end-systole volume (ESV), stroke volume (SV), and ejection fraction (EF) global and regional strain were calculated by CC, one BH CSC, and shortest BH CSC protocols. The intraclass correlation coefficient (ICC) and coefficient of variance (CV) of these parameters were used to determine the agreement between different acquisitions.

Results

The agreement of all volumetric variables and EF between the CC protocol and one BH CSC protocol was excellent (ICC &gt; 0.9). EDV, ESV, and SV between CC and shortest BH CSC protocols also had a remarkable coherence (ICC &gt; 0.9). The agreement of 3D LV global strain assessment between CC protocol and one BH CSC protocol was good (ICC &gt; 0.8). Most CVs of variables were also good (CV &lt; 15%). ICCs of all variables were lower than 0.8. CVs of all parameters were higher than 15% except global longitudinal strain (GLS) between CC and shortest BH CSC protocols. The agreement of regional strain between CC and BH CSC protocols was heterogeneous (-0.2 &lt; ICC &lt; 0.7). Many variables of CVs were poor.

Conclusion

Notably, one BH CSC protocol can be used for 3D global strain analysis, along with a good correlation with the CC protocol. The regional strain should continue to be computed by the CC protocol due to poor agreement and a remarkable variation between the protocols. The shortest BH CSC protocol was insufficient to replace the CC protocol for 3D global and regional strain.

Real-World and Regulatory Perspectives of Artificial Intelligence in Cardiovascular Imaging

Recent progress in digital health data recording, advances in computing power, and methodological approaches that extract information from data as artificial intelligence are expected to have a disruptive impact on technology in medicine. One of the potential benefits is the ability to extract new and essential insights from the vast amount of data generated during health care delivery every day. Cardiovascular imaging is boosted by new intelligent automatic methods to manage, process, segment, and analyze petabytes of image data exceeding historical manual capacities. Algorithms that learn from data raise new challenges for regulatory bodies. Partially autonomous behavior and adaptive modifications and a lack of transparency in deriving evidence from complex data pose considerable problems. Controlling new technologies requires new controlling techniques and ongoing regulatory research. All stakeholders must participate in the quest to find a fair balance between innovation and regulation. The regulatory approach to artificial intelligence must be risk-based and resilient. A focus on unknown emerging risks demands continuous surveillance and clinical evaluation during the total product life cycle. Since learning algorithms are data-driven, high-quality data is fundamental for good machine learning practice. Mining, processing, validation, governance, and data control must account for bias, error, inappropriate use, drifts, and shifts, particularly in real-world data. Regulators worldwide are tackling twenty-first century challenges raised by “learning” medical devices. Ethical concerns and regulatory approaches are presented. The paper concludes with a discussion on the future of responsible artificial intelligence.

Real-time cardiac MRI using an undersampled spiral k-space trajectory and a reconstruction based on a variational network

PURPOSE

Cardiac MRI represents the gold standard to determine myocardial function. However, the current clinical standard protocol, a segmented Cartesian acquisition, is time-consuming and can lead to compromised image quality in the case of arrhythmia or dyspnea. In this article, a machine learning-based reconstruction of undersampled spiral k-space data is presented to enable free breathing real-time cardiac MRI with good image quality and short reconstruction times.

METHODS

Data were acquired in free breathing with a 2D spiral trajectory corrected by the gradient system transfer function. Undersampled data were reconstructed by a variational network (VN), which was specifically adapted to the non-Cartesian sampling pattern. The network was trained with data from 11 subjects. Subsequently, the imaging technique was validated in 14 subjects by quantifying the difference to a segmented reference acquisition, an expert reader study, and by comparing derived volumes and functional parameters with values obtained using the current clinical gold standard.

RESULTS

The scan time for the entire heart was below 1 min. The VN reconstructed data in about 0.9 s per image, which is considerably shorter than conventional model-based approaches. The VN furthermore performed better than a U-Net and not inferior to a low-rank plus sparse model in terms of achieved image quality. Functional parameters agreed, on average, with reference data.

CONCLUSIONS

The proposed VN method enables real-time cardiac imaging with both high spatial and temporal resolution in free breathing and with short reconstruction time.

Compressed sensing based dynamic MR image reconstruction by using 3D-total generalized variation and tensor decomposition: k-t TGV-TD

PURPOSE

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) is a promising technique to accelerate dynamic cardiac MR imaging (DCMRI). For DCMRI, the CS-MRI usually exploits image signal sparsity and low-rank property to reconstruct dynamic images from the undersampled k-space data. In this paper, a novel CS algorithm is investigated to improve dynamic cardiac MR image reconstruction quality under the condition of minimizing the k-space recording.

METHODS

The sparse representation of 3D cardiac magnetic resonance data is implemented by synergistically integrating 3D total generalized variation (3D-TGV) algorithm and high order singular value decomposition (HOSVD) based Tensor Decomposition, termed k-t TGV-TD method. In the proposed method, the low rank structure of the 3D dynamic cardiac MR data is performed with the HOSVD method, and the localized image sparsity is achieved by the 3D-TGV method. Moreover, the Fast Composite Splitting Algorithm (FCSA) method, combining the variable splitting with operator splitting techniques, is employed to solve the low-rank and sparse problem. Two different cardiac MR datasets (cardiac perfusion and cine MR datasets) are used to evaluate the performance of the proposed method.

RESULTS

Compared with the state-of-art methods, such as k-t SLR, 3D-TGV, HOSVD based tensor decomposition and low-rank plus sparse method, the proposed k-t TGV-TD method can offer improved reconstruction accuracy in terms of higher peak SNR (PSNR) and structural similarity index (SSIM). The proposed k-t TGV-TD method can achieve significantly better and stable reconstruction results than state-of-the-art methods in terms of both PSNR and SSIM, especially for cardiac perfusion MR dataset.

CONCLUSIONS

This work proved that the k-t TGV-TD method was an effective sparse representation way for DCMRI, which was capable of significantly improving the reconstruction accuracy with different acceleration factors.

Late Gadolinium Enhancement Cardiac Magnetic Resonance Imaging: From Basic Concepts to Emerging Methods

BACKGROUND

 Late gadolinium enhancement (LGE) is a widely used cardiac magnetic resonance imaging (MRI) technique to diagnose a broad range of ischemic and non-ischemic cardiomyopathies. Since its development and validation against histology already more than two decades ago, the clinical utility of LGE and its span of applications have increased considerably.

METHODS

 In this review we will present the basic concepts of LGE imaging and its diagnostic and prognostic value, elaborate on recent developments and emerging methods, and finally discuss future prospects.

RESULTS

 Continuous developments in 3 D imaging methods, motion correction techniques, water/fat-separated imaging, dark-blood methods, and scar quantification improved the performance and further expanded the clinical utility of LGE imaging.

CONCLUSION

 LGE imaging is the current noninvasive reference standard for the assessment of myocardial viability. Improvements in spatial resolution, scar-to-blood contrast, and water/fat-separated imaging further strengthened its position.

KEY POINTS

  · LGE MRI is the reference standard for the noninvasive assessment of myocardial viability. · LGE MRI is used to diagnose a broad range of non-ischemic cardiomyopathies in everyday clinical practice.. · Improvements in spatial resolution and scar-to-blood contrast further strengthened its position. · Continuous developments improve its performance and further expand its clinical utility.

CITATION FORMAT

· Holtackers RJ, Emrich T, Botnar RM et al. Late Gadolinium Enhancement Cardiac Magnetic Resonance Imaging: From Basic Concepts to Emerging Methods. Fortschr Röntgenstr 2022; DOI: 10.1055/a-1718-4355.

Faster and Better: How Anomaly Detection Can Accelerate and Improve Reporting of Head Computed Tomography

Background: Most artificial intelligence (AI) systems are restricted to solving a pre-defined task, thus limiting their generalizability to unselected datasets. Anomaly detection relieves this shortfall by flagging all pathologies as deviations from a learned norm. Here, we investigate whether diagnostic accuracy and reporting times can be improved by an anomaly detection tool for head computed tomography (CT), tailored to provide patient-level triage and voxel-based highlighting of pathologies. Methods: Four neuroradiologists with 1–10 years of experience each investigated a set of 80 routinely acquired head CTs containing 40 normal scans and 40 scans with common pathologies. In a random order, scans were investigated with and without AI-predictions. A 4-week wash-out period between runs was included to prevent a reminiscence effect. Performance metrics for identifying pathologies, reporting times, and subjectively assessed diagnostic confidence were determined for both runs. Results: AI-support significantly increased the share of correctly classified scans (normal/pathological) from 309/320 scans to 317/320 scans (p = 0.0045), with a corresponding sensitivity, specificity, negative- and positive- predictive value of 100%, 98.1%, 98.2% and 100%, respectively. Further, reporting was significantly accelerated with AI-support, as evidenced by the 15.7% reduction in reporting times (65.1 ± 8.9 s vs. 54.9 ± 7.1 s; p < 0.0001). Diagnostic confidence was similar in both runs. Conclusion: Our study shows that AI-based triage of CTs can improve the diagnostic accuracy and accelerate reporting for experienced and inexperienced radiologists alike. Through ad hoc identification of normal CTs, anomaly detection promises to guide clinicians towards scans requiring urgent attention.

Generative adversarial network-based post-processed image super-resolution technology for accelerating brain MRI: comparison with compressed sensing

BACKGROUND

It is unclear whether deep-learning-based super-resolution technology (SR) or compressed sensing technology (CS) can accelerate magnetic resonance imaging (MRI) .

PURPOSE

To compare SR accelerated images with CS images regarding the image similarity to reference 2D- and 3D gradient-echo sequence (GRE) brain MRI.

MATERIAL AND METHODS

We prospectively acquired 1.3× and 2.0× faster 2D and 3D GRE images of 20 volunteers from the reference time by reducing the matrix size or increasing the CS factor. For SR, we trained the generative adversarial network (GAN), upscaling the low-resolution images to the reference images with twofold cross-validation. We compared the structural similarity (SSIM) index of accelerated images to the reference image. The rate of incorrect answers of a radiologist discriminating faster and reference image was used as a subjective image similarity (ISM) index.

RESULTS

The SR demonstrated significantly higher SSIM than the CS (SSIM=0.9993-0.999 vs. 0.9947-0.9986; P < 0.001). In 2D GRE, it was challenging to discriminate the SR image from the reference image, compared to the CS (ISM index 40% vs. 17.5% in 1.3×; P = 0.039 and 17.5% vs. 2.5% in 2.0×; P = 0.034). In 3D GRE, the CS revealed a significantly higher ISM index than the SR (22.5% vs. 2.5%; P = 0.011) in 2.0 × faster images. However, the ISM index was identical for the 2.0× CS and 1.3× SR (22.5% vs. 27.5%; P = 0.62) with comparable time costs.

CONCLUSION

The GAN-based SR outperformed CS in image similarity with 2D GRE for MRI acceleration. In addition, CS was more advantageous in 3D GRE than SR.

Artificial intelligence development in pediatric body magnetic resonance imaging: best ideas to adapt from adults

Emerging manifestations of artificial intelligence (AI) have featured prominently in virtually all industries and facets of our lives. Within the radiology literature, AI has shown great promise in improving and augmenting radiologist workflow. In pediatric imaging, while greatest AI inroads have been made in musculoskeletal radiographs, there are certainly opportunities within thoracoabdominal MRI for AI to add significant value. In this paper, we briefly review non-interpretive and interpretive data science, with emphasis on potential avenues for advancement in pediatric body MRI based on similar work in adults. The discussion focuses on MRI image optimization, abdominal organ segmentation, and osseous lesion detection encountered during body MRI in children.

Free-Breathing Three-Dimensional Isotropic-Resolution MR sequence for simultaneous vessel wall imaging of bilateral renal arteries and abdominal aorta: Feasibility and reproducibility

PURPOSE

Many diseases can simultaneously involve renal arteries and the adjacent abdominal aorta. The study proposed a free-breathing three-dimensional (3D) isotropic-resolution MR sequence for simultaneous vessel wall imaging of bilateral renal arteries and adjacent abdominal aorta.

METHODS

A respiratory triggered isotropic-resolution sequence which combined the improved motion-sensitized driven-equilibrium (iMSDE) preparation with the spoiled gradient recalled (SPGR) readout (iMSDE-SPGR) was proposed for simultaneous vessel wall imaging of renal arteries and abdominal aorta. The proposed iMSDE-SPGR sequence was optimized by positioning spatial saturation pulses (i.e. REST slabs) elaborately to further alleviate respiratory and gastrointestinal motion artifacts and selecting appropriate first-order gradient moment (m₁ ) of the iMSDE preparation. Thirteen healthy subjects and thirteen patients with renal artery stenosis (RAS) underwent simultaneous vessel wall imaging with the optimized iMSDE-SPGR sequence at 3.0T. Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and morphology of renal arterial wall and aortic wall were measured. Reproducibility of intra-observer, inter-observer and scan-rescan (n = 13 healthy subjects) in measuring SNR, CNR and morphology was evaluated. For the reproducibility test, the agreement was determined using intraclass correlation coefficients (ICC) and the differences were compared using paired-t test or non-parametric Wilcoxon test when appropriate. Bland-Altman plots were used to calculate the bias between observers and between scans.

RESULTS

The proposed iMSDE-SPGR sequence was feasible for simultaneous vessel wall imaging both in the healthy subjects and the patients. The sequence showed good to excellent inter-observer (ICC:0.615-0.999), excellent intra-observer (ICC:0.801-0.998) and scan-rescan (ICC:0.768-0.998) reproducibility in measuring morphology, SNR and CNR. There were no significant differences in SNR, CNR and morphology measurements between observers and between scans (all P>0.05). Bland-Altman plots showed small bias in assessing SNR, CNR and morphology.

DATA CONCLUSION

The proposed free-breathing 3D isotropic-resolution iMSDE-SPGR technique is feasible and reproducible for simultaneous vessel wall imaging of bilateral renal arteries and adjacent abdominal aorta. This article is protected by copyright. All rights reserved.

Compressed Sensing in Sodium Magnetic Resonance Imaging: Techniques, Applications, and Future Prospects

Sodium (²³ Na) yields the second strongest nuclear magnetic resonance (NMR) signal in biological tissues and plays a vital role in cell physiology. Sodium magnetic resonance imaging (MRI) can provide insights into cell integrity and tissue viability relative to pathologies without significant anatomical alternations, and thus it is considered to be a potential surrogate biomarker that provides complementary information for standard hydrogen (¹ H) MRI in a noninvasive and quantitative manner. However, sodium MRI suffers from a relatively low signal-to-noise ratio and long acquisition times due to its relatively low NMR sensitivity. Compressed sensing-based (CS-based) methods have been shown to accelerate sodium imaging and/or improve sodium image quality significantly. In this manuscript, the basic concepts of CS and how CS might be applied to improve sodium MRI are described, and the historical milestones of CS-based sodium MRI are briefly presented. Representative advanced techniques and evaluation methods are discussed in detail, followed by an expose of clinical applications in multiple anatomical regions and diseases as well as thoughts and suggestions on potential future research prospects of CS in sodium MRI. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 1.

Joint reconstruction framework of compressed sensing and nonlinear parallel imaging for dynamic cardiac magnetic resonance imaging

Compressed Sensing (CS) and parallel imaging are two promising techniques that accelerate the MRI acquisition process. Combining these two techniques is of great interest due to the complementary information used in each. In this study, we proposed a novel reconstruction framework that effectively combined compressed sensing and nonlinear parallel imaging technique for dynamic cardiac imaging. Specifically, the proposed method decouples the reconstruction process into two sequential steps: In the first step, a series of aliased dynamic images were reconstructed from the highly undersampled k-space data using compressed sensing; In the second step, nonlinear parallel imaging technique, i.e. nonlinear GRAPPA, was utilized to reconstruct the original dynamic images from the reconstructed k-space data obtained from the first step. In addition, we also proposed a tailored k-space down-sampling scheme that satisfies both the incoherent undersampling requirement for CS and the structured undersampling requirement for nonlinear parallel imaging. The proposed method was validated using four in vivo experiments of dynamic cardiac cine MRI with retrospective undersampling. Experimental results showed that the proposed method is superior at reducing aliasing artifacts and preserving the spatial details and temporal variations, compared with the competing k-t FOCUSS and k-t FOCUSS with sensitivity encoding methods, with the same numbers of measurements.

Deep-learning based super-resolution for 3D isotropic coronary MR angiography in less than a minute

PURPOSE

To develop and evaluate a novel and generalizable super-resolution (SR) deep-learning framework for motion-compensated isotropic 3D coronary MR angiography (CMRA), which allows free-breathing acquisitions in less than a minute.

METHODS

Undersampled motion-corrected reconstructions have enabled free-breathing isotropic 3D CMRA in ~5-10 min acquisition times. In this work, we propose a deep-learning-based SR framework, combined with non-rigid respiratory motion compensation, to shorten the acquisition time to less than 1 min. A generative adversarial network (GAN) is proposed consisting of two cascaded Enhanced Deep Residual Network generator, a trainable discriminator, and a perceptual loss network. A 16-fold increase in spatial resolution is achieved by reconstructing a high-resolution (HR) isotropic CMRA (0.9 mm3 or 1.2 mm3 ) from a low-resolution (LR) anisotropic CMRA (0.9 × 3.6 × 3.6 mm3 or 1.2 × 4.8 × 4.8 mm3 ). The impact and generalization of the proposed SRGAN approach to different input resolutions and operation on image and patch-level is investigated. SRGAN was evaluated on a retrospective downsampled cohort of 50 patients and on 16 prospective patients that were scanned with LR-CMRA in ~50 s under free-breathing. Vessel sharpness and length of the coronary arteries from the SR-CMRA is compared against the HR-CMRA.

RESULTS

SR-CMRA showed statistically significant (P < .001) improved vessel sharpness 34.1% ± 12.3% and length 41.5% ± 8.1% compared with LR-CMRA. Good generalization to input resolution and image/patch-level processing was found. SR-CMRA enabled recovery of coronary stenosis similar to HR-CMRA with comparable qualitative performance.

CONCLUSION

The proposed SR-CMRA provides a 16-fold increase in spatial resolution with comparable image quality to HR-CMRA while reducing the predictable scan time to <1 min.

Dynamic Imaging Using a Deep Generative SToRM (Gen-SToRM) Model

We introduce a generative smoothness regularization on manifolds (SToRM) model for the recovery of dynamic image data from highly undersampled measurements. The model assumes that the images in the dataset are non-linear mappings of low-dimensional latent vectors. We use the deep convolutional neural network (CNN) to represent the non-linear transformation. The parameters of the generator as well as the low-dimensional latent vectors are jointly estimated only from the undersampled measurements. This approach is different from traditional CNN approaches that require extensive fully sampled training data. We penalize the norm of the gradients of the non-linear mapping to constrain the manifold to be smooth, while temporal gradients of the latent vectors are penalized to obtain a smoothly varying time-series. The proposed scheme brings in the spatial regularization provided by the convolutional network. The main benefit of the proposed scheme is the improvement in image quality and the orders-of-magnitude reduction in memory demand compared to traditional manifold models. To minimize the computational complexity of the algorithm, we introduce an efficient progressive training-in-time approach and an approximate cost function. These approaches speed up the image reconstructions and offers better reconstruction performance.

End-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRA

PURPOSE

To develop an end-to-end deep learning technique for nonrigid motion-corrected (MoCo) reconstruction of ninefold undersampled free-breathing whole-heart coronary MRA (CMRA).

METHODS

A novel deep learning framework was developed consisting of a diffeomorphic registration network and a motion-informed model-based deep learning (MoDL) reconstruction network. The registration network receives as input highly undersampled (~22×) respiratory-resolved images and outputs 3D nonrigid respiratory motion fields between the images. The motion-informed MoDL performs MoCo reconstruction from undersampled data using the predicted motion fields. The whole deep learning framework, termed as MoCo-MoDL, was trained end-to-end in a supervised manner for simultaneous 3D nonrigid motion estimation and MoCo reconstruction. MoCo-MoDL was compared with a state-of-the-art nonrigid MoCo CMRA reconstruction technique in 15 retrospectively undersampled datasets and 9 prospectively undersampled acquisitions.

RESULTS

The acquisition time for ninefold accelerated CMRA was ~2.5 min. The reconstruction time was ~22 s for the proposed MoCo-MoDL and ~35 min for the conventional approach. MoCo-MoDL achieved higher peak SNR (27.86 ± 3.00 vs. 26.71 ± 2.79; P < .05) and structural similarity (0.78 ± 0.06 vs. 0.75 ± 0.06; P < .05) than the conventional approach. Similar vessel length and visual image quality score were obtained with the 2 methods, whereas improved vessel sharpness was observed with MoCo-MoDL.

CONCLUSION

An end-to-end deep learning approach was introduced for simultaneous nonrigid motion estimation and MoCo reconstruction of highly undersampled free-breathing whole-heart CMRA. The rapid free-breathing CMRA acquisition together with the fast reconstruction of the proposed approach promises easy integration into clinical workflow.