Comparison of cardiac volumetry using real-time MRI during free-breathing with standard cine MRI during breath-hold in children

Deep learning-based automated segmentation of cardiac real-time MRI in non-human primates

Advanced imaging techniques, like magnetic resonance imaging (MRI), have revolutionised cardiovascular disease diagnosis and monitoring in humans and animal models. Real-time (RT) MRI, which can capture a single slice during each consecutive heartbeat while the animal or patient breathes continuously, generates large data sets that necessitate automatic myocardium segmentation to fully exploit these technological advancements. While automatic segmentation is common in human adults, it remains underdeveloped in preclinical animal models. In this study, we developed and trained a fully automated 2D convolutional neural network (CNN) for segmenting the left and right ventricles and the myocardium in non-human primates (NHPs) using RT cardiac MR images of rhesus macaques, in the following referred to as PrimUNet. Based on the U-Net framework, PrimUNet achieved optimal performance with a learning rate of 0.0001, an initial kernel size of 64, a final kernel size of 512, and a batch size of 32. It attained an average Dice score of 0.9, comparable to human studies. Testing PrimUNet on additional RT MRI data from rhesus macaques demonstrated strong agreement with manual segmentation for left ventricular end-diastolic volume (LVEDV), left ventricular end-systolic volume (LVESV), and left ventricular myocardial volume (LVMV). It also performs well on cine MRI data of rhesus macaques and acceptably on those of baboons. PrimUNet is well-suited for automatically segmenting extensive RT MRI data, facilitating strain analyses of individual heartbeats. By eliminating human observer variability, PrimUNet enhances the reliability and reproducibility of data analysis in animal research, thereby advancing translational cardiovascular studies.

Fast and Robust Single-Shot Cine Cardiac MRI Using Deep Learning Super-Resolution Reconstruction

OBJECTIVE

The aim of the study was to compare the diagnostic quality of deep learning (DL) reconstructed balanced steady-state free precession (bSSFP) single-shot (SSH) cine images with standard, multishot (also: segmented) bSSFP cine (standard cine) in cardiac MRI.

METHODS AND MATERIALS

This prospective study was performed in a cohort of participants with clinical indication for cardiac MRI. SSH compressed-sensing bSSFP cine and standard multishot cine were acquired with breath-holding and electrocardiogram-gating in short-axis view at 1.5 Tesla. SSH cine images were reconstructed using an industry-developed DL super-resolution algorithm (DL-SSH cine). Two readers evaluated diagnostic quality (endocardial edge definition, blood pool to myocardium contrast and artifact burden) from 1 (nondiagnostic) to 5 (excellent). Functional left ventricular (LV) parameters were assessed in both sequences. Edge rise distance, apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio were calculated. Statistical analysis for the comparison of DL-SSH cine and standard cine included the Student's t-test, Wilcoxon signed-rank test, Bland-Altman analysis, and Pearson correlation.

RESULTS

Forty-five participants (mean age: 50 years ±18; 30 men) were included. Mean total scan time was 65% lower for DL-SSH cine compared to standard cine (92 ± 8 s vs 265 ± 33 s; P < 0.0001). DL-SSH cine showed high ratings for subjective image quality (eg, contrast: 5 [interquartile range {IQR}, 5-5] vs 5 [IQR, 5-5], P = 0.01; artifacts: 4.5 [IQR, 4-5] vs 5 [IQR, 4-5], P = 0.26), with superior values for sharpness parameters (endocardial edge definition: 5 [IQR, 5-5] vs 5 [IQR, 4-5], P < 0.0001; edge rise distance: 1.9 [IQR, 1.8-2.3] vs 2.5 [IQR, 2.3-2.6], P < 0.0001) compared to standard cine. No significant differences were found in the comparison of objective metrics between DL-SSH and standard cine (eg, aSNR: 49 [IQR, 38.5-70] vs 52 [IQR, 38-66.5], P = 0.74). Strong correlation was found between DL-SSH cine and standard cine for the assessment of functional LV parameters (eg, ejection fraction: r = 0.95). Subgroup analysis of participants with arrhythmia or unreliable breath-holding (n = 14/45, 31%) showed better image quality ratings for DL-SSH cine compared to standard cine (eg, artifacts: 4 [IQR, 4-5] vs 4 [IQR, 3-5], P = 0.04).

CONCLUSIONS

DL reconstruction of SSH cine sequence in cardiac MRI enabled accelerated acquisition times and noninferior diagnostic quality compared to standard cine imaging, with even superior diagnostic quality in participants with arrhythmia or unreliable breath-holding.

Free-breathing, Highly Accelerated, Single-beat, Multisection Cardiac Cine MRI with Generative Artificial Intelligence

Purpose To develop and evaluate a free-breathing, highly accelerated, multisection, single-beat cine sequence for cardiac MRI. Materials and Methods This prospective study, conducted from July 2022 to December 2023, included participants with various cardiac conditions as well as healthy participants who were imaged using a 3-T MRI system. A single-beat sequence was implemented, collecting data for each section in one heartbeat. Images were acquired with an in-plane spatiotemporal resolution of 1.9 × 1.9 mm2 and 37 msec and reconstructed using resolution enhancement generative adversarial inline neural network (REGAIN), a deep learning model. Multibreath-hold k-space-segmented (4.2-fold acceleration) and free-breathing single-beat (14.8-fold acceleration) cine images were collected, both reconstructed with REGAIN. Left ventricular (LV) and right ventricular (RV) parameters between the two methods were evaluated with linear regression, Bland-Altman analysis, and Pearson correlation. Three expert cardiologists independently scored diagnostic and image quality. Scan and rescan reproducibility was evaluated in a subset of participants 1 year apart using the intraclass correlation coefficient (ICC). Results This study included 136 participants (mean age [SD], 54 years ± 15; 69 female, 67 male), 40 healthy and 96 with cardiac conditions. k-Space-segmented and single-beat scan times were 2.6 minutes ± 0.8 and 0.5 minute ± 0.1, respectively. Strong correlations (P < .001) were observed between k-space-segmented and single-beat cine parameters in both LV (r = 0.97-0.99) and RV (r = 0.89-0.98). Scan and rescan reproducibility of single-beat cine was excellent (ICC, 0.97-1.0). Agreement among readers was high, with 125 of 136 (92%) images consistently assessed as diagnostic and 133 of 136 (98%) consistently rated as having good image quality by all readers. Conclusion Free-breathing 30-second single-beat cardiac cine MRI yielded accurate biventricular measurements, reduced scan time, and maintained high diagnostic and image quality compared with conventional multibreath-hold k-space-segmented cine images. Keywords: MR-Imaging, Cardiac, Heart, Imaging Sequences, Comparative Studies, Technology Assessment Supplemental material is available for this article. © RSNA, 2025.

Virtual MOLLI Target: Generative Adversarial Networks Toward Improved Motion Correction in MRI Myocardial T1 Mapping

BACKGROUND

The modified Look-Locker inversion recovery (MOLLI) sequence is commonly used for myocardial T1 mapping. However, it acquires images with different inversion times, which causes difficulty in motion correction for respiratory-induced misregistration to a given target image.

HYPOTHESIS

Using a generative adversarial network (GAN) to produce virtual MOLLI images with consistent heart positions can reduce respiratory-induced misregistration of MOLLI datasets.

STUDY TYPE

Retrospective.

POPULATION

1071 MOLLI datasets from 392 human participants.

FIELD STRENGTH/SEQUENCE

Modified Look-Locker inversion recovery sequence at 3 T.

ASSESSMENT

A GAN model with a single inversion time image as input was trained to generate virtual MOLLI target (VMT) images at different inversion times which were subsequently used in an image registration algorithm. Four VMT models were investigated and the best performing model compared with the standard vendor-provided motion correction (MOCO) technique.

STATISTICAL TESTS

The effectiveness of the motion correction technique was assessed using the fitting quality index (FQI), mutual information (MI), and Dice coefficients of motion-corrected images, plus subjective quality evaluation of T1 maps by three independent readers using Likert score. Wilcoxon signed-rank test with Bonferroni correction for multiple comparison. Significance levels were defined as P < 0.01 for highly significant differences and P < 0.05 for significant differences.

RESULTS

The best performing VMT model with iterative registration demonstrated significantly better performance (FQI 0.88 ± 0.03, MI 1.78 ± 0.20, Dice 0.84 ± 0.23, quality score 2.26 ± 0.95) compared to other approaches, including the vendor-provided MOCO method (FQI 0.86 ± 0.04, MI 1.69 ± 0.25, Dice 0.80 ± 0.27, quality score 2.16 ± 1.01).

DATA CONCLUSION

Our GAN model generating VMT images improved motion correction, which may assist reliable T1 mapping in the presence of respiratory motion. Its robust performance, even with considerable respiratory-induced heart displacements, may be beneficial for patients with difficulties in breath-holding.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 1.

Deep learning methods for 3D magnetic resonance image denoising, bias field and motion artifact correction: a comprehensive review

Magnetic resonance imaging (MRI) provides detailed structural information of the internal body organs and soft tissue regions of a patient in clinical diagnosis for disease detection, localization, and progress monitoring. MRI scanner hardware manufacturers incorporate various post-acquisition image-processing techniques into the scanner's computer software tools for different post-processing tasks. These tools provide a final image of adequate quality and essential features for accurate clinical reporting and predictive interpretation for better treatment planning. Different post-acquisition image-processing tasks for MRI quality enhancement include noise removal, motion artifact reduction, magnetic bias field correction, and eddy electric current effect removal. Recently, deep learning (DL) methods have shown great success in many research fields, including image and video applications. DL-based data-driven feature-learning approaches have great potential for MR image denoising and image-quality-degrading artifact correction. Recent studies have demonstrated significant improvements in image-analysis tasks using DL-based convolutional neural network techniques. The promising capabilities and performance of DL techniques in various problem-solving domains have motivated researchers to adapt DL methods to medical image analysis and quality enhancement tasks. This paper presents a comprehensive review of DL-based state-of-the-art MRI quality enhancement and artifact removal methods for regenerating high-quality images while preserving essential anatomical and physiological feature maps without destroying important image information. Existing research gaps and future directions have also been provided by highlighting potential research areas for future developments, along with their importance and advantages in medical imaging.

Accelerated cardiac magnetic resonance imaging using deep learning for volumetric assessment in children

BACKGROUND

Ventricular volumetry using a short-axis stack of two-dimensional (D) cine balanced steady-state free precession (bSSFP) sequences is crucial in any cardiac magnetic resonance imaging (MRI) examination. This task becomes particularly challenging in children due to multiple breath-holds.

OBJECTIVE

To assess the diagnostic performance of accelerated 3-RR cine MRI sequences using deep learning reconstruction compared with standard 2-D cine bSSFP sequences.

MATERIAL AND METHODS

Twenty-nine consecutive patients (mean age 11 ± 5, median 12, range 1-17 years) undergoing cardiac MRI were scanned with a conventional segmented 2-D cine and a deep learning accelerated cine (three heartbeats) acquisition on a 1.5-tesla scanner. Short-axis volumetrics were performed (semi-)automatically in both datasets retrospectively by two experienced readers who visually assessed image quality employing a 4-point grading scale. Scan times and image quality were compared using the Wilcoxon rank-sum test. Volumetrics were assessed with linear regression and Bland-Altman analyses, and measurement agreement with intraclass correlation coefficient (ICC).

RESULTS

Mean acquisition time was significantly reduced with the 3-RR deep learning cine compared to the standard cine sequence (45.5 ± 13.8 s vs. 218.3 ± 44.8 s; P < 0.001). No significant differences in biventricular volumetrics were found. Left ventricular (LV) mass was increased in the deep learning cine compared with the standard cine sequence (71.4 ± 33.1 g vs. 69.9 ± 32.5 g; P < 0.05). All volumetric measurements had an excellent agreement with ICC > 0.9 except for ejection fraction (EF) (LVEF 0.81, RVEF 0.73). The image quality of deep learning cine images was decreased for end-diastolic and end-systolic contours, papillary muscles, and valve depiction (2.9 ± 0.5 vs. 3.5 ± 0.4; P < 0.05).

CONCLUSION

Deep learning cine volumetrics did not differ significantly from standard cine results except for LV mass, which was slightly overestimated with deep learning cine. Deep learning cine sequences result in a significant reduction in scan time with only slightly lower image quality.

Assessment of the cardiac output at rest and during exercise stress using real-time cardiovascular magnetic resonance imaging in HFpEF-patients

This methodological study aimed to validate the cardiac output (CO) measured by exercise-stress real-time phase-contrast cardiovascular magnetic resonance imaging (CMR) in patients with heart failure and preserved ejection fraction (HFpEF). 68 patients with dyspnea on exertion (NYHA ≥ II) and echocardiographic signs of diastolic dysfunction underwent rest and exercise stress right heart catheterization (RHC) and CMR within 24 h. Patients were diagnosed as overt HFpEF (pulmonary capillary wedge pressure (PCWP) ≥ 15mmHg at rest), masked HFpEF (PCWP ≥ 25mmHg during exercise stress but < 15mmHg at rest) and non-cardiac dyspnea. CO was calculated using RHC as the reference standard, and in CMR by the volumetric stroke volume, conventional phase-contrast and rest and stress real-time phase-contrast imaging. At rest, the CMR based CO showed good agreement with RHC with an ICC of 0.772 for conventional phase-contrast, and 0.872 for real-time phase-contrast measurements. During exercise stress, the agreement of real-time CMR and RHC was good with an ICC of 0.805. Real-time measurements underestimated the CO at rest (Bias:0.71 L/min) and during exercise stress (Bias:1.4 L/min). Patients with overt HFpEF had a significantly lower cardiac index compared to patients with masked HFpEF and with non-cardiac dyspnea during exercise stress, but not at rest. Real-time phase-contrast CO can be assessed with good agreement with the invasive reference standard at rest and during exercise stress. While moderate underestimation of the CO needs to be considered with non-invasive testing, the CO using real-time CMR provides useful clinical information and could help to avoid unnecessary invasive procedures in HFpEF patients.

The future of CMR: All-in-one vs. real-time CMR (Part 2)

Cardiac Magnetic Resonance (CMR) protocols can be lengthy and complex, which has driven the research community to develop new technologies to make these protocols more efficient and patient-friendly. Two different approaches to improving CMR have been proposed, specifically "all-in-one" CMR, where several contrasts and/or motion states are acquired simultaneously, and "real-time" CMR, in which the examination is accelerated to avoid the need for breathholding and/or cardiac gating. The goal of this two-part manuscript is to describe these two different types of emerging rapid CMR protocols. To this end, the vision of all-in-one and real-time imaging are described, along with techniques which have been devised and tested along the pathway of clinical implementation. The pros and cons of the different methods are presented, and the remaining open needs of each are detailed. Part 1 tackles the "All-in-One" approaches, and Part 2 focuses on the "Real-Time" approaches along with an overall summary of these emerging methods.

Major pneumothorax during pediatric cardiac MRI procedure under general anesthesia: step-by-step analysis and importance of a well-known environment and material

BACKGROUND

To perform step-by-step analysis of the different factors (material, anesthesia technique, human, and location) that led to major pneumothorax during an infrequent pediatric cardiac MRI and to prevent its occurrence in the future. Anesthesia equipment used in a remote location is often different than those in operating rooms. For magnetic resonance imaging (MRI), ventilation devices and monitors must be compatible with the magnetic fields. During cardiac MRI numerous apneas are required and, visual contact with the patient is limited for clinical evaluation. Anesthesia-related barotrauma and pneumothorax are rare in children and the first symptoms can be masked.

CASE PRESENTATION

A 3-year-old boy with atrial septal defect (ASD) and suspicious partial anomalous pulmonary venous return was anesthetized and intubated to perform a follow up with MRI. Sevoflurane maintenance and ventilation were performed using a circular CO2 absorber device, co-axial circuit, and 500 mL pediatric silicone balloon. Apneas were facilitated by Alfentanyl boluses and hyperventilation. A few moderated desaturations occurred during the imaging sequences without hemodynamic changes. At the end of the MRI, facial subcutaneous emphysema was observed by swollen eyelids and crackling snow neck palpation. A complete left pneumothorax was diagnosed by auscultation, sonography examination, and chest radiograph. Pneumo-mediastinum, -pericardium and -peritoneum were present. A chest drain was placed, and the child was extubated and transferred to the pediatric intensive care unit (PICU). Despite the anesthesiologist's belief that PEEP was minimal, critical analysis revealed that PEEP was maintained at a high level throughout anesthesia. After the initial barotrauma, repeated exposure to high pressure led to the diffusion of air from the pleura to subcutaneous tissues and mediastinal and peritoneal cavities. Equipment check revealed a functional circular circuit; however, the plastic adjustable pressure-limiting valve (APL) closed within the last 30° rotation. The balloon was found to be more rigid and demonstrated significantly reduced compliance.

CONCLUSIONS

Anesthetists require proficiency is using equipment in non-OR locations and this equipment must be properly maintained and checked for malfunctions. Controlling the human factor risks by implementing checklists, formations, and alarms allows us to reduce errors. The number of pediatric anesthesia performed routinely appeared to be essential for limiting risks and reporting our mistakes will be a benefit for all who care about patients.

First experience with real-time magnetic resonance imaging-based investigation of respiratory influence on cardiac function in pediatric congenital heart disease patients with chronic right ventricular volume overload

BACKGROUND

Congenital heart disease (CHD) is often associated with chronic right ventricular (RV) volume overload. Real-time magnetic resonance imaging (MRI) enables the analysis of cardiac function during free breathing.

OBJECTIVE

To evaluate the influence of respiration in pediatric patients with CHD and chronic RV volume overload.

METHODS AND MATERIALS

RV volume overload patients (n=6) and controls (n=6) were recruited for cardiac real-time MRI at 1.5 tesla during free breathing. Breathing curves from regions of interest reflecting the position of the diaphragm served for binning images in four different tidal volume classes, each in inspiration and expiration. Tidal volumes were estimated from these curves by data previously obtained by magnetic resonance-compatible spirometry. Ventricular volumes indexed to body surface area and Frank-Starling relationships referenced to the typical tidal volume indexed to body height (TTVi) were compared.

RESULTS

Indexed RV end-diastolic volume (RV-EDVi) and indexed RV stroke volume (RV-SVi) increased during inspiration (RV-EDVi/TTVi: RV load: + 16 ± 4%; controls: + 22 ± 13%; RV-SVi/TTVi: RV load: + 21 ± 6%; controls: + 35 ± 17%; non-significant for comparison). The increase in RV ejection fraction during inspiration was significantly lower in RV load patients (RV load: + 1.1 ± 2.2%; controls: + 6.1 ± 1.5%; P=0.01). The Frank-Starling relationship of the RV provided a significantly reduced slope estimate in RV load patients (inspiration: RV load: 0.75 ± 0.11; controls: 0.92 ± 0.02; P=0.02).

CONCLUSION

In pediatric patients with CHD and chronic RV volume overload, cardiac real-time MRI during free breathing in combination with respiratory-based binning indicates an impaired Frank-Starling relationship of the RV.

Real-time MRI: a new tool of radiologic imaging in small children

Real-time MRI (rt-MRI) in children is a new imaging technique that combines the advantages of US - at frame rates of up to 50 images per second - with the quality and features of MRI. Although still subject of research, it has become a standard tool in the diagnostic portfolio of two pediatric radiology departments in Germany. Based on ultrashort acquisition times, any detrimental effects of macroscopic movements of the child and the physiological movements of the organs are negligible. Especially in pediatric brain imaging, rt-MRI has already proven its value. With suitable indications, rt-MRI can reduce anesthesia and sedation examinations in children below 6 years of age by 40% due to its very short examination time and its robustness to motion. There is a high level of acceptance among parents and referrers when diagnostic possibilities and limitations are communicated correctly.

CONCLUSION

Completely new diagnostic possibilities arise in the imaging of the moving lung, the beating heart, joint movements, and speaking and swallowing, as demonstrated in this video-backed review.

WHAT IS KNOWN

• MRI in moving children has been burdened with severe artifacts. • Gross motion usually has to be handled by sedation and periodic motion of the heart and lungs has to be compensated with time-consuming techniques until now.

WHAT IS NEW

• Real-time MRI allows image acquisition with up to 50 frames per second similar to ultrasound frame rate. • Real-time MRI proofs to be very promising for imaging children, reducing examination time and sedation rate drastically.

External Hardware and Sensors, for Improved MRI

Complex engineered systems are often equipped with suites of sensors and ancillary devices that monitor their performance and maintenance needs. MRI scanners are no different in this regard. Some of the ancillary devices available to support MRI equipment, the ones of particular interest here, have the distinction of actually participating in the image acquisition process itself. Most commonly, such devices are used to monitor physiological motion or variations in the scanner's imaging fields, allowing the imaging and/or reconstruction process to adapt as imaging conditions change. "Classic" examples include electrocardiography (ECG) leads and respiratory bellows to monitor cardiac and respiratory motion, which have been standard equipment in scan rooms since the early days of MRI. Since then, many additional sensors and devices have been proposed to support MRI acquisitions. The main physical properties that they measure may be primarily "mechanical" (eg acceleration, speed, and torque), "acoustic" (sound and ultrasound), "optical" (light and infrared), or "electromagnetic" in nature. A review of these ancillary devices, as currently available in clinical and research settings, is presented here. In our opinion, these devices are not in competition with each other: as long as they provide useful and unique information, do not interfere with each other and are not prohibitively cumbersome to use, they might find their proper place in future suites of sensors. In time, MRI acquisitions will likely include a plurality of complementary signals. A little like the microbiome that provides genetic diversity to organisms, these devices can provide signal diversity to MRI acquisitions and enrich measurements. Machine-learning (ML) algorithms are well suited at combining diverse input signals toward coherent outputs, and they could make use of all such information toward improved MRI capabilities. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 1.