Abstract:

Mechanistic cardiac electrophysiology models allow for personalized simulations of the electrical activity in the heart and the ensuing electrocardiogram (ECG) on the body surface. As such, synthetic signals possess known ground truth labels of the underlying disease and can be employed for validation of machine learning ECG analysis tools in addition to clinical signals. Recently, synthetic ECGs were used to enrich sparse clinical data or even replace them completely during training leading to improved performance on real-world clinical test data. We thus generated a novel synthetic database comprising a total of 16,900 12 lead ECGs based on electrophysiological simulations equally distributed into healthy control and 7 pathology classes. The pathological case of myocardial infraction had 6 sub-classes. A comparison of extracted features between the virtual cohort and a publicly available clinical ECG database demonstrated that the synthetic signals represent clinical ECGs for healthy and pathological subpopulations with high fidelity. The ECG database is split into training, validation, and test folds for development and objective assessment of novel machine learning algorithms.

Abstract:

Machine learning (ML) methods for the analysis of electrocardiography (ECG) data are gaining importance, substantially supported by the release of large public datasets. However, these current datasets miss important derived descriptors such as ECG features that have been devised in the past hundred years and still form the basis of most automatic ECG analysis algorithms and are critical for cardiologists' decision processes. ECG features are available from sophisticated commercial software but are not accessible to the general public. To alleviate this issue, we add ECG features from two leading commercial algorithms and an open-source implementation supplemented by a set of automatic diagnostic statements from a commercial ECG analysis software in preprocessed format. This allows the comparison of ML models trained on clinically versus automatically generated label sets. We provide an extensive technical validation of features and diagnostic statements for ML applications. We believe this release crucially enhances the usability of the PTB-XL dataset as a reference dataset for ML methods in the context of ECG data.

Abstract:

PURPOSE: To evaluate two commonly used respiratory motion correction techniques for coronary magnetic resonance angiography (MRA) regarding their dependency on motion estimation accuracy and final image quality and to compare both methods to the respiratory gating approach used in clinical practice. MATERIALS AND METHODS: Ten healthy volunteers were scanned using a non-Cartesian radial phase encoding acquisition. Respiratory motion was corrected for coronary MRA according to two motion correction techniques, image-based (IMC) and reconstruction-based (RMC) respiratory motion correction. Both motion correction approaches were compared quantitatively and qualitatively against a reference standard navigator-based respiratory gating (RG) approach. Quantitative comparisons were performed regarding visible vessel length, vessel sharpness, and total acquisition time. Two experts carried out a visual scoring of image quality. Additionally, numerical simulations were performed to evaluate the effect of motion estimation inaccuracy on RMC and IMC. RESULTS: RMC led to significantly better image quality than IMC (P's paired Student's t-test were smaller than 0.001 for vessel sharpness and visual scoring). RMC did not show a statistically significant difference compared to reference standard RG (vessel length [99% confidence interval]: 86.913 [83.097-95.015], P = 0.107; vessel sharpness: 0.640 [0.605-0.802], P = 0.012; visual scoring: 2.583 [2.410-3.424], P = 0.018) in terms of vessel visualization and image quality while reducing scan times by 56%. Simulations showed higher dependencies for RMC than for IMC on motion estimation inaccuracies. CONCLUSION: RMC provides a similar image quality as the clinically used RG approach but almost halves the scan time and is independent of subjects' breathing patterns. Clinical validation of RMC is now desirable. J. Magn. Reson. Imaging 2015.

Abstract:

In dynamic magnetic resonance imaging (MRI) studies, the motion kinetics or the contrast variability are often hard to predict, hampering an appropriate choice of the image update rate or the temporal resolution. A constant azimuthal profile spacing (111.246 degrees), based on the Golden Ratio, is investigated as optimal for image reconstruction from an arbitrary number of profiles in radial MRI. The profile order is evaluated and compared with a uniform profile distribution in terms of signal-to-noise ratio (SNR) and artifact level. The favorable characteristics of such a profile order are exemplified in two applications on healthy volunteers. First, an advanced sliding window reconstruction scheme is applied to dynamic cardiac imaging, with a reconstruction window that can be flexibly adjusted according to the extent of cardiac motion that is acceptable. Second, a contrast-enhancing k-space filter is presented that permits reconstructing an arbitrary number of images at arbitrary time points from one raw data set. The filter was utilized to depict the T1-relaxation in the brain after a single inversion prepulse. While a uniform profile distribution with a constant angle increment is optimal for a fixed and predetermined number of profiles, a profile distribution based on the Golden Ratio proved to be an appropriate solution for an arbitrary number of profiles.

Abstract:

PURPOSE: To demonstrate a rapid MR technique that combines imaging and R2* mapping based on a single radial multi-gradient-echo (rMGE) data set. The technique provides a fast method for online monitoring of the administration of (super-)paramagnetic contrast agents as well as image-guided drug delivery. MATERIALS AND METHODS: Data are acquired using an rMGE sequence, resulting in interleaved undersampled radial k-spaces representing different echo times (TEs). These data sets are reconstructed separately, yielding a series of images with different TEs used for pixelwise R2* mapping. A fast numerical algorithm implemented on a real-time reconstruction platform provides online estimation of the relaxation rate R2*. Simultaneously the images are summed for the computation of a high-resolution image. RESULTS: Convenient high-resolution R2* maps of phantoms and the liver of a healthy volunteer were obtained. In addition to stable intrinsic baseline maps, the proposed technique provides particularly accurate results for the high relaxation rates observed during the presence of (super-)paramagnetic contrast agents. Assuming that the change in R2* is proportional to the concentration of the agent, the technique offers a rough estimate for dynamic dosage. CONCLUSION: The simultaneous online display of morphological and parametric information permits convenient, quantitative surveillance of contrast-agent administration.

Abstract:

The steady-state free precessing (SSFP) sequences, widely used in MRI today, acquire data only during a short fraction of the repetition time (TR). Thus, they exhibit a poor scan efficiency. In this paper, a novel approach to extending the acquisition window for a given TR without considerably modifying the basic sequence is explored for radial SSFP sequences. The additional data are primarily employed to increase the signal-to-noise ratio, rather than to improve the temporal resolution of the imaging. The approach is analyzed regarding its effect on the image SNR (signal to noise ratio) and the reconstruction algorithm. Results are presented for phantom experiments and cardiac functions studies. The gain in SNR is most notable in rapid imaging, since SNR enhancement for a constant repetition time may be used to compensate for the increase in noise resulting from angular undersampling.

Abstract:

Cardiac electrophysiology procedures are routinely used to treat patients with rhythm disorders. The success rates of ablation procedures and cardiac resynchronization therapy are still sub-optimal. Recent advances in medical imaging, image processing and cardiac biophysical modeling have the potential to improve patient outcome. This manuscript provides an overview of how these advances have been translated into the clinical environment.