Scanner-Independent MyoMapNet for Accelerated Cardiac MRI T1 Mapping Across Vendors and Field Strengths.

BACKGROUND: In cardiac T1 mapping, a series of T1 -weighted (T1 w) images are collected and numerically fitted to a two or three-parameter model of the signal recovery to estimate voxel-wise T1 values. To reduce the scan time, one can collect fewer T1 w images, albeit at the cost of precision or/and accuracy. Recently, the feasibility of using a neural network instead of conventional two- or three-parameter fit modeling has been demonstrated. However, prior studies used data from a single vendor and field strength; therefore, the generalizability of the models has not been established. PURPOSE: To develop and evaluate an accelerated cardiac T1 mapping approach based on MyoMapNet, a convolution neural network T1 estimator that can be used across different vendors and field strengths by incorporating the relevant scanner information as additional inputs to the model. STUDY TYPE: Retrospective, multicenter. POPULATION: A total of 1423 patients with known or suspected cardiac disease (808 male, 57 ± 16 years), from three centers, two vendors (Siemens, Philips), and two field strengths (1.5 T, 3 T). The data were randomly split into 60% training, 20% validation, and 20% testing. FIELD STRENGTH/SEQUENCE: A 1.5 T and 3 T, Modified Look-Locker inversion recovery (MOLLI) for native and postcontrast T1 . ASSESSMENT: Scanner-independent MyoMapNet (SI-MyoMapNet) was developed by altering the deep learning (DL) architecture of MyoMapNet to incorporate scanner vendor and field strength as inputs. Epicardial and endocardial contours and blood pool (by manually drawing a large region of interest in the blood pool) of the left ventricle were manually delineated by three readers, with 2, 8, and 9 years of experience, and SI-MyoMapNet myocardial and blood pool T1 values (calculated from four T1 w images) were compared with conventional MOLLI T1 values (calculated from 8 to 11 T1 w images). STATISTICAL TESTS: Equivalency test with 95% confidence interval (CI), linear regression slope, Pearson correlation coefficient (r), Bland-Altman analysis. RESULTS: The proposed SI-MyoMapNet successfully created T1 maps. Native and postcontrast T1 values measured from SI-MyoMapNet were strongly correlated with MOLLI, despite using only four T1 w images, at both field-strengths and vendors (all r > 0.86). For native T1 , SI-MyoMapNet and MOLLI were in good agreement for myocardial and blood T1 values in institution 1 (myocardium: 5 msec, 95% CI [3, 8]; blood: -10 msec, 95%CI [-16, -4]), in institution 2 (myocardium: 6 msec, 95% CI [0, 11]; blood: 0 msec, [-18, 17]), and in institution 3 (myocardium: 7 msec, 95% CI [-8, 22]; blood: 8 msec, [-14, 30]). Similar results were observed for postcontrast T1 . DATA CONCLUSION: Inclusion of field strength and vendor as additional inputs to the DL architecture allows generalizability of MyoMapNet across different vendors or field strength. EVIDENCE LEVEL: 2. TECHNICAL EFFICACY: Stage 2.

Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis.

BACKGROUND: Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge. METHODS: Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.). RESULTS: The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005). CONCLUSIONS: The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.

SCMR expert consensus statement for cardiovascular magnetic resonance of patients with a cardiac implantable electronic device.

Cardiovascular magnetic resonance (CMR) is a proven imaging modality for informing diagnosis and prognosis, guiding therapeutic decisions, and risk stratifying surgical intervention. Patients with a cardiac implantable electronic device (CIED) would be expected to derive particular benefit from CMR given high prevalence of cardiomyopathy and arrhythmia. While several guidelines have been published over the last 16 years, it is important to recognize that both the CIED and CMR technologies, as well as our knowledge in MR safety, have evolved rapidly during that period. Given increasing utilization of CIED over the past decades, there is an unmet need to establish a consensus statement that integrates latest evidence concerning MR safety and CIED and CMR technologies. While experienced centers currently perform CMR in CIED patients, broad availability of CMR in this population is lacking, partially due to limited availability of resources for programming devices and appropriate monitoring, but also related to knowledge gaps regarding the risk-benefit ratio of CMR in this growing population. To address the knowledge gaps, this SCMR Expert Consensus Statement integrates consensus guidelines, primary data, and opinions from experts across disparate fields towards the shared goal of informing evidenced-based decision-making regarding the risk-benefit ratio of CMR for patients with CIEDs.

The Society for Cardiovascular Magnetic Resonance Registry at 150,000.

BACKGROUND: Cardiovascular magnetic resonance (CMR) is increasingly utilized to evaluate expanding cardiovascular conditions. The Society for Cardiovascular Magnetic Resonance (SCMR) Registry is a central repository for real-world clinical data to support cardiovascular research, including those relating to outcomes, quality improvement, and machine learning. The SCMR Registry is built on a regulatory-compliant, cloud-based infrastructure that houses searchable content and Digital Imaging and Communications in Medicine images. The goal of this study is to summarize the status of the SCMR Registry at 150,000 exams. METHODS: The processes for data security, data submission, and research access are outlined. We interrogated the Registry and presented a summary of its contents. RESULTS: Data were compiled from 154,458 CMR scans across 20 United States sites, containing 299,622,066 total images (∼100 terabytes of storage). Across reported values, the human subjects had an average age of 58 years (range 1 month to >90 years old), were 44% (63,070/145,275) female, 72% (69,766/98,008) Caucasian, and had a mortality rate of 8% (9,962/132,979). The most common indication was cardiomyopathy (35,369/131,581, 27%), and most frequently used current procedural terminology code was 75561 (57,195/162,901, 35%). Macrocyclic gadolinium-based contrast agents represented 89% (83,089/93,884) of contrast utilization after 2015. Short-axis cines were performed in 99% (76,859/77,871) of tagged scans, short-axis late gadolinium enhancement (LGE) in 66% (51,591/77,871), and stress perfusion sequences in 30% (23,241/77,871). Mortality data demonstrated increased mortality in patients with left ventricular ejection fraction <35%, the presence of wall motion abnormalities, stress perfusion defects, and infarct LGE, compared to those without these markers. There were 456,678 patient-years of all-cause mortality follow-up, with a median follow-up time of 3.6 years. CONCLUSION: The vision of the SCMR Registry is to promote evidence-based utilization of CMR through a collaborative effort by providing a web mechanism for centers to securely upload de-identified data and images for research, education, and quality control. The Registry quantifies changing practice over time and supports large-scale real-world multicenter observational studies of prognostic utility.

Numerical Study on the Impact of Central Venous Catheter Placement on Blood Flow in the Cavo-Atrial Junction.

An in silico study is performed to investigate fluid dynamic effects of central venous catheter (CVC) placement within patient-specific cavo-atrial junctions. Prior studies show the CVC infusing a liquid, but this study focuses on the placement without any liquid emerging from the CVC. A 7 or 15-French double-lumen CVC is placed virtually in two patient-specific models; the CVC tip location is altered to understand its effect on the venous flow field. Results show that the CVC impact is trivial on flow in the superior vena cava when the catheter-to-vein ratio ranges from 0.15 to 0.33. Results further demonstrate that when the CVC tip is directly in the right atrium, flow vortices in the right atrium result in elevated wall shear stress near the tip hole. A recirculation region characterizes a spatially variable flow field inside the CVC side hole. Furthermore, flow stagnation is present near the internal side hole corners but an elevated wall shear stress near the curvature of the side hole's exit. These results suggest that optimal CVC tip location is within the superior vena cava, so as to lower the potential for platelet activation due to elevated shear stresses and that CVC geometry and location depth in the central vein significantly influences the local CVC fluid dynamics. A thrombosis model also shows thrombus formation at the side hole and tip hole. After modifying the catheter design, the hemodynamics change, which alter thrombus formation. Future studies are warranted to study CVC design and placement location in an effort to minimize CVC-induced thrombosis incidence.

One-month DAPT with ticagrelor and aspirin for patients undergoing coronary artery bypass grafting: rationale and design of the randomised, multicentre, double-blind, placebo-controlled ODIN trial.

The optimal antiplatelet strategy after coronary artery bypass graft (CABG) surgery in patients with chronic coronary syndromes (CCS) is unclear. Adding the P2Y12 inhibitor, ticagrelor, to low-dose aspirin for 1 year is associated with a reduction in graft failure, particularly saphenous vein grafts, at the expense of an increased risk of clinically important bleeding. As the risk of thrombotic graft failure and ischaemic events is highest early after CABG surgery, a better risk-to-benefit profile may be attained with short-term dual antiplatelet therapy followed by single antiplatelet therapy. The One Month Dual Antiplatelet Therapy With Ticagrelor in Coronary Artery Bypass Graft Patients (ODIN) trial is a prospective, randomised, double-blind, placebo-controlled, international, multicentre study of 700 subjects that will evaluate the effect of short-term dual antiplatelet therapy with ticagrelor plus low-dose aspirin after CABG in patients with CCS. Patients will be randomised 1:1 to ticagrelor 90 mg twice daily or matching placebo, in addition to aspirin 75-150 mg once daily for 1 month; after the first month, antiplatelet therapy will be continued with aspirin alone. The primary endpoint is a hierarchical composite of all-cause death, stroke, myocardial infarction, revascularisation and graft failure at 1 year. The key secondary endpoint is a hierarchical composite of all-cause death, stroke, myocardial infarction, Bleeding Academic Research Consortium (BARC) type 3 bleeding, revascularisation and graft failure at 1 year (net clinical benefit). ODIN will report whether the addition of ticagrelor to low-dose aspirin for 1 month after CABG reduces ischaemic events and provides a net clinical benefit in patients with CCS. (ClinicalTrials.gov: NCT05997693).

Deformation-encoding Deep Learning Transformer for High-Frame-Rate Cardiac Cine MRI.

Purpose To develop a deep learning model for increasing cardiac cine frame rate while maintaining spatial resolution and scan time. Materials and Methods A transformer-based model was trained and tested on a retrospective sample of cine images from 5840 patients (mean age, 55 years ± 19 [SD]; 3527 male patients) referred for clinical cardiac MRI from 2003 to 2021 at nine centers; images were acquired using 1.5- and 3-T scanners from three vendors. Data from three centers were used for training and testing (4:1 ratio). The remaining data were used for external testing. Cines with downsampled frame rates were restored using linear, bicubic, and model-based interpolation. The root mean square error between interpolated and original cine images was modeled using ordinary least squares regression. In a prospective study of 49 participants referred for clinical cardiac MRI (mean age, 56 years ± 13; 25 male participants) and 12 healthy participants (mean age, 51 years ± 16; eight male participants), the model was applied to cines acquired at 25 frames per second (fps), thereby doubling the frame rate, and these interpolated cines were compared with actual 50-fps cines. The preference of two readers based on perceived temporal smoothness and image quality was evaluated using a noninferiority margin of 10%. Results The model generated artifact-free interpolated images. Ordinary least squares regression analysis accounting for vendor and field strength showed lower error (P < .001) with model-based interpolation compared with linear and bicubic interpolation in internal and external test sets. The highest proportion of reader choices was "no preference" (84 of 122) between actual and interpolated 50-fps cines. The 90% CI for the difference between reader proportions favoring collected (15 of 122) and interpolated (23 of 122) high-frame-rate cines was -0.01 to 0.14, indicating noninferiority. Conclusion A transformer-based deep learning model increased cardiac cine frame rates while preserving both spatial resolution and scan time, resulting in images with quality comparable to that of images obtained at actual high frame rates. Keywords: Functional MRI, Heart, Cardiac, Deep Learning, High Frame Rate Supplemental material is available for this article. © RSNA, 2024.

Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis.

Background: Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge. Methods: Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.). Results: The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005). Conclusions: The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.

Tissue-Based Predictors of Impaired Right Ventricular Strain in Coronary Artery Disease: A Multicenter Stress Perfusion Study.

BACKGROUND: Right ventricular (RV) dysfunction is known to impact prognosis, but its determinants in coronary artery disease are poorly understood. Stress cardiac magnetic resonance (CMR) has been used to assess ischemia and infarction in relation to the left ventricle (LV); the impact of myocardial tissue properties on RV function is unknown. METHODS: Vasodilator stress CMR was performed in patients with known coronary artery disease at 7 sites between May 2005 and October 2018. Myocardial infarction was identified on late gadolinium enhancement-CMR, and infarct transmurality was graded on a per-segment basis. Ischemia was assessed on stress CMR based on first-pass perfusion and localized by using segment partitions corresponding to cine and late gadolinium enhancement analyses. RV function was evaluated by CMR-feature tracking for primary analysis with a global longitudinal strain threshold of 20% used to define impaired RV strain (RVIS); secondary functional analysis via RV ejection fraction was also performed. RESULTS: A total of 2604 patients were studied, among whom RVIS was present in 461 patients (18%). The presence and magnitude of RVIS were strongly associated with LV dysfunction, irrespective of whether measured by LV ejection fraction or wall motion score (P<0.001 for all). Regarding tissue substrate, regions of ischemic and dysfunctional myocardium (ie, hibernating myocardium) and infarct size were each independently associated with RVIS (both P<0.001). During follow-up (median, 4.62 [interquartile range, 2.15-7.67] years), 555 deaths (21%) occurred. Kaplan-Meier analysis for patients stratified by presence and magnitude of RV dysfunction by global longitudinal strain and RV ejection fraction each demonstrated strong prognostic utility for all-cause mortality (P<0.001). RVIS conferred increased mortality risk (hazard ratio, 1.35 [95% CI, 1.11-1.66]; P=0.003) even after controlling for LV function, infarction, and ischemia. CONCLUSIONS: RVIS in patients with known coronary artery disease is associated with potentially reversible LV processes, including LV functional impairment due to ischemic and predominantly viable myocardium, which confers increased mortality risk independent of LV function and tissue substrate.