OBJECTIVES: We implemented an explainable machine learning (ML) model to gain insight into the association between cardiac magnetic resonance markers and adverse outcomes of cardiovascular hospitalization and all-cause death (composite endpoint) in patients with nonischemic dilated cardiomyopathy (NICM).
BACKGROUND: Risk stratification of patients with NICM remains challenging. An explainable ML model has the potential to provide insight into the contributions of different risk markers in the prediction model.
METHODS: An explainable ML model based on extreme gradient boosting (XGBoost) machines was developed using cardiac magnetic resonance and clinical parameters. The study cohorts consist of patients with NICM from 2 academic medical centers: Beth Israel Deaconess Medical Center (BIDMC) and Brigham and Women’s Hospital (BWH), with 328 and 214 patients, respectively. XGBoost was trained on 70% of patients from the BIDMC cohort and evaluated based on the other 30% as internal validation. The model was externally validated using the BWH cohort. To investigate the contribution of different features in our risk prediction model, we used Shapley additive explanations (SHAP) analysis.
RESULTS: During a mean follow-up duration of 40 months, 34 patients from BIDMC and 33 patients from BWH experienced the composite endpoint. The area under the curve for predicting the composite endpoint was 0.71 for the internal BIDMC validation and 0.69 for the BWH cohort. SHAP analysis identified parameters associated with right ventricular (RV) dysfunction and remodeling as primary markers of adverse outcomes. High risk thresholds were identified by SHAP analysis and thus provided thresholds for top predictive continuous clinical variables.
CONCLUSIONS: An explainable ML-based risk prediction model has the potential to identify patients with NICM at risk for cardiovascular hospitalization and all-cause death. RV ejection fraction, end-systolic and end-diastolic volumes (as indicators of RV dysfunction and remodeling) were determined to be major risk markers.
Background Exercise cardiovascular magnetic resonance (Ex-CMR) is a promising stress imaging test for coronary artery disease (CAD). However, Ex-CMR requires accelerated imaging techniques that result in significant aliasing artifacts. Our goal was to develop and evaluate a free-breathing and electrocardiogram (ECG)-free real-time cine with deep learning (DL)-based radial acceleration for Ex-CMR. Methods A 3D (2D + time) convolutional neural network was implemented to suppress artifacts from aliased radial cine images. The network was trained using synthetic real-time radial cine images simulated using breath-hold, ECG-gated segmented Cartesian k-space data acquired at 3 T from 503 patients at rest. A prototype real-time radial sequence with acceleration rate = 12 was used to collect images with inline DL reconstruction. Performance was evaluated in 8 healthy subjects in whom only rest images were collected. Subsequently, 14 subjects (6 healthy and 8 patients with suspected CAD) were prospectively recruited for an Ex-CMR to evaluate image quality. At rest (n = 22), standard breath-hold ECG-gated Cartesian segmented cine and free-breathing ECG-free real-time radial cine images were acquired. During post-exercise stress (n = 14), only real-time radial cine images were acquired. Three readers evaluated residual artifact level in all collected images on a 4-point Likert scale (1-non-diagnostic, 2-severe, 3-moderate, 4-minimal). Results The DL model substantially suppressed artifacts in real-time radial cine images acquired at rest and during post-exercise stress. In real-time images at rest, 89.4% of scores were moderate to minimal. The mean score was 3.3 ± 0.7, representing increased (P < 0.001) artifacts compared to standard cine (3.9 ± 0.3). In real-time images during post-exercise stress, 84.6% of scores were moderate to minimal, and the mean artifact level score was 3.1 ± 0.6. Comparison of left-ventricular (LV) measures derived from standard and real-time cine at rest showed differences in LV end-diastolic volume (3.0 mL [− 11.7, 17.8], P = 0.320) that were not significantly different from zero. Differences in measures of LV end-systolic volume (7.0 mL [− 1.3, 15.3], P < 0.001) and LV ejection fraction (− 5.0% [− 11.1, 1.0], P < 0.001) were significant. Total inline reconstruction time of real-time radial images was 16.6 ms per frame. Conclusions Our proof-of-concept study demonstrated the feasibility of inline real-time cine with DL-based radial acceleration for Ex-CMR.
The objective of the current study was to investigate the performance of various deep learning (DL) architectures for MyoMapNet, a DL model for T1 estimation using accelerated cardiac T1 mapping from four T1-weighted images collected after a single inversion pulse (Look-Locker 4 [LL4]). We implemented and tested three DL architectures for MyoMapNet: (a) a fully connected neural network (FC), (b) convolutional neural networks (VGG19, ResNet50), and (c) encoder-decoder networks with skip connections (ResUNet, U-Net). Modified Look-Locker inversion recovery (MOLLI) images from 749 patients at 3 T were used for training, validation, and testing. The first four T1-weighted images from MOLLI5(3)3 and/or MOLLI4(1)3(1)2 protocols were extracted to create accelerated cardiac T1 mapping data. We also prospectively collected data from 28 subjects using MOLLI and LL4 to further evaluate model performance. Despite rigorous training, conventional VGG19 and ResNet50 models failed to produce anatomically correct T1 maps, and T1 values had significant errors. While ResUNet yielded good quality maps, it significantly underestimated T1. Both FC and U-Net, however, yielded excellent image quality with good T1 accuracy for both native (FC/U-Net/MOLLI = 1217 ± 64/1208 ± 61/1199 ± 61 ms, all p < 0.05) and postcontrast myocardial T1 (FC/U-Net/MOLLI = 578 ± 57/567 ± 54/574 ± 55 ms, all p < 0.05). In terms of precision, the U-Net model yielded better T1 precision compared with the FC architecture (standard deviation of 61 vs. 67 ms for the myocardium for native [p < 0.05], and 31 vs. 38 ms [p < 0.05], for postcontrast). Similar findings were observed in prospectively collected LL4 data. It was concluded that U-Net and FC DL models in MyoMapNet enable fast myocardial T1 mapping using only four T1-weighted images collected from a single LL sequence with comparable accuracy. U-Net also provides a slight improvement in precision.
Purpose: To improve the accuracy and robustness of T1 estimation by MyoMap-Net, a deep learning–based approach using 4 inversion-recovery T1-weighted images for cardiac T1 mapping.
Methods: MyoMapNet is a fully connected neural network for T1 estimation of an accelerated cardiac T1 mapping sequence, which collects 4 T1-weighted images by a single Look-Locker inversion-recovery experiment (LL4).MyoMap-Net was originally trained using in vivo data from the modified Look-Locker inversion recovery sequence, which resulted in significant bias and sensitivity to various confounders. This study sought to train MyoMapNet using signals generated from numerical simulations and phantom MR data under multiple simulated confounders. The trained model was then evaluated by phantom data scanned using new phantom vials that differed from those used for training. The performance of the new model was compared with modified Look-Locker inversion recovery sequence and saturation-recovery single-shot acquisition for measuring native and postcontrast T1 in 25 subjects.
Results: In the phantom study, T1 values measured by LL4 with MyoMapNet were highly correlated with reference values from the spin-echo sequence. Furthermore, the estimated T1 had excellent robustness to changes in flip angle and off-resonance. Native and postcontrast myocardium T1 at 3 Tesla measured by saturation-recovery single-shot acquisition, modified Look-Locker inversion recovery sequence, and MyoMapNet were 1483±46.6 ms and 791±45.8 ms, 1169±49.0 ms and 612±36.0 ms, and 1443±57.5 ms and 700±57.5 ms, respectively. The corresponding extracellular volumes were 22.90%±3.20%, 28.88%±3.48%, and 30.65%±3.60%, respectively.
Conclusion: Training MyoMapNet with numerical simulations and phantom data will improve the estimation of myocardial T1 values and increase its robustness to confounders while also reducing the overall T1 mapping estimation time to only 4 heartbeats.
Objective To investigate the performance of various deep learning (DL) architectures for MyoMapNet, a DL model for T1 estimation using accelerated cardiac T1 mapping from four T1-weighted images collected after a single inversion pulse (Look-Locker, LL4). Methods We implemented and tested three DL architectures for MyoMapNet: (a) a fully connected neural network (FC), (b) convolutional neural networks (VGG19, ResNet50), and (c) encoder-decoder networks with skip connections (ResUNet, U-Net). Modified Look-Locker Inversion Recovery (MOLLI) images from 749 patients at 3T were used for training, validation, and testing. The first four T1-weighted images from MOLLI5(3)3 and/or MOLLI4(1)3(1)2 protocols were extracted to create accelerated cardiac T1 mapping data. We also prospectively collected data from 28 subjects using MOLLI and LL4 to further evaluate model performance. Results Despite rigorous training, conventional VGG19 and ResNet50 models failed to produce anatomically correct T1 maps, and T1 values had significant errors. While ResUNet yielded good quality maps, it significantly under-estimated T1. Both FC and U-Net, however, yielded excellent image quality with good T1 accuracy for both native (FC/U-Net/MOLLI= 1217 ± 64/ 1208 ± 61/1199 ± 61 ms, all P<0.05) and post-contrast myocardial T1 (FC/U-Net/MOLLI= 578 ± 57/ 567 ± 54/574 ± 55 ms, all P<0.05). In terms of precision, the U-Net model yielded better T1 precision compared to the FC architecture (standard deviation of 61 ms vs. 67 ms for the myocardium for native (P<0.05), and 31 ms vs. 38 ms (P<0.05), for post-contrast). Similar findings were observed in prospectively collected LL4 data. Conclusion U-Net and FC DL models in MyoMapNet enable fast myocardial T1 mapping using only four T1-weighted images collected from a single Lock-Locker sequence with comparable accuracy. U-Net also provides slight improvement in precision.
Purpose: To develop and evaluate a free breathing non-electrocardiograph (ECG) myocardial T1* mapping sequence using radial imaging to quantify the changes in myocardial T1* between rest and exercise (T1*reactivity) in exercise cardiac MRI (Ex-CMR). Methods: A free-running T1* sequence was developed using a saturation pulse followed by three Look-Locker inversion-recovery experiments. Each Look-Locker continuously acquired data as radial trajectory using a low flip-angle spoiled gradient-echo readout. Self-navigation was performed with a temporal resolution of∼100 ms for retrospectively extracting respiratory motion. The mid-diastole phase for every cardiac cycle was retrospectively detected on the recorded electrocardiogram signal using an empirical model. Multiple measurements were performed to obtain mean value to reduce effects from the free-breathing acquisition. Finally, data acquired at both mid-diastole and end-expiration are picked and reconstructed by a low-rank plus sparsity constraint algorithm. The performance of this sequence was evaluated by simulations, phantoms, and in vivo studies at rest and after physiological exercise. Results: Numerical simulation demonstrated that changes in T1* are related to the changes in T1; however, other factors such as breathing motion could influence T1* measurements. Phantom T1* values measured using free-running T1* mapping sequence had good correlation with spin-echo T1 values and was insensitive to heart rate. In the Ex-CMR study, the measured T1* reactivity was 10% immediately after exercise and declined over time.
Conclusion: The free-running T1* mapping sequence allows free-breathing non-ECG quantification of changes in myocardial T1* with physiological exercise. Although, absolute myocardial T1* value is sensitive to various confounders