Background To validate pulmonary computed tomography (CT) perfusion in a porcine model by invasive monitoring of cardiac output (CO) using thermodilution method. Methods Animals were studied at a single center, using a Swan-Ganz catheter for invasive CO monitoring as a reference. Fifteen pigs were included. Contrast-enhanced CT perfusion of the descending aorta and right and left pulmonary artery was performed. For variation purposes, a balloon catheter was inserted to block the contralateral pulmonary vascular bed; additionally, two increased CO settings were created by intravenous administration of catecholamines. Finally, stepwise capillary occlusion was performed by intrapulmonary arterial injection of 75-μm microspheres in four stages. A semiautomatic selection of AFs and a recirculation-aware tracer-kinetics model to extract the first-pass of AFs, estimating blood flow with the Stewart-Hamilton method, was implemented. Linear mixed models (LMM) were developed to calibrate blood flow calculations accounting with individual- and cohort-level effects. Results Nine of 15 pigs had complete datasets. Strong correlations were observed between calibrated pulmonary (0.73, 95% confidence interval [CI] 0.6–0.82) and aortic blood flow measurements (0.82, 95% CI, 0.73–0.88) and the reference as well as agreements (± 2.24 L/min and ± 1.86 L/min, respectively) comparable to the state of the art, on a relatively wide range of right ventricle-CO measurements. Conclusions CT perfusion validly measures CO using LMMs at both individual and cohort levels, as demonstrated by referencing the invasive CO. Relevance statement Possible clinical applications of CT perfusion for measuring CO could be in acute pulmonary thromboembolism or to assess right ventricular function to show impairment or mismatch to the left ventricle. Key points • CT perfusion measures flow in vessels. • CT perfusion measures cumulative cardiac output in the aorta and pulmonary vessels. • CT perfusion validly measures CO using LMMs at both individual and cohort levels, as demonstrated by using the invasive CO as a reference standard. Graphical Abstract

Objective. Modern medical imaging plays a vital role in clinical practice, enabling non-invasive visualization of anatomical structures. Dynamic contrast enhancement (DCE) imaging is a technique that uses contrast agents to visualize blood flow dynamics in a time-resolved manner. It can be applied to different modalities, such as computed tomography (CT) and electrical impedance tomography (EIT). This study aims to develop a common theoretical and practical hemodynamic extraction basis for DCE modelling across modalities, based on the gamma-variate function. Approach. The study introduces a framework to generate time-intensity curves for multiple DCE imaging modalities from user-defined hemodynamic parameters. Thus, extensive datasets were simulated for both DCE-CT and EIT, representing different hemodynamic scenarios. Additionally, gamma-variate extensions to account for several physiological effects were detailed in a modality-agnostic manner, and three corresponding fitting strategies, namely nonlinear, linear, and a novel hybrid approach, were implemented and compared on the basis of accuracy of parameter estimation, first pass reconstruction, speed of computation, and failure rate. Main results. As a result, we found the linear method to be the most modality-dependent, exhibiting the greatest bias, variance and failure rates, although remaining the fastest alternative. The hybrid method at least matches the state-of-the-art nonlinear method’s accuracy, while improving its robustness and speed by 10 times. Significance. Our research suggests that the hybrid method may bring noteworthy accuracy and efficiency improvements in handling the high-dimensionality of DCE imaging in general, being a step towards real-time processing. Moreover, our generative model presents a potential asset to produce benchmarking and data augmentation datasets across modalities.

Curve fitting is the central step in extracting hemodynamic parameters from various contrast-based medical imaging modalities. Yet, using functions derived from compartment modelling principles with basic nonlinear least-squares approaches is challenging and computationally expensive. This contribution describes a novel hybrid approach to efficiently and accurately estimate blood flow and volume, which was compared against the state-of-the-art via extensive realistic simulations for computerized and electrical impedance tomography, having shown superior robustness, speed, and overall accuracy.

Abstract The accurate separation of cardiac and ventilatory contributions to electrical impedance tomography signals is crucial for complete and non-invasive cardiorespiratory monitoring. However, no consensus on a suitable source separation algorithm was achieved despite several proposals due to lacking systematic evaluation. To address this, we propose a benchmarking 4D finite element method generative model for mixed, cardiac, and ventilatory signals. Our model implements dynamic modelling of the heart, lungs, and pulmonary arteries using realistic volume and flow curve templates, along with cardiac and respiratory frequency coupling.We also employed variable alveolar and blood conductivities. The model was able to obtain long recordings faster than comparably complex models while maintaining significant physiological effects and signal properties such as non-stationarity, spatial delays, time and frequency profiles. The realistic physiological model can be used to taxonomize and evaluate source separation algorithms, as well as aid in the development and training of new ones.

Thoracic electrical impedance tomography provides a non-invasive signal that combines changes from both cardiac and respiratory events. Heart and respiratory rates are important physiological parameters to diagnose and monitor cardiorespiratory conditions, and necessary for further more sophisticated analyses. We propose a real-time, model-based approach in the time domain to estimate both heart and respiratory rates simultaneously from the electrical impedance tomography signal. We tested our method using simulated non-stationary signals with varying relative cardiac and respiratory contributions. Our method could accurately estimated heart and respiratory rates with root mean square errors as low as 0.54 and 0.86 cycles per minute, and Bland-Altman biases as low as 0.04 ± 1.04 and -0.07 ± 1.53 cycles per minute, respectively. Additionally, the algorithm ran in real-time with or without parallelization, reaching computation times of 10 ± 1.1 ms.

In the wake of Big Data, traditional Machine Learning techniques are now often integrated in the clinical workflow. Despite more capable, Deep Learning methods are not equally accepted given their unsatiated need for great amounts of training data and transversal use of the same architectures in fundamentally different areas with weakly-substantiated adaptations. To address the former, a cardiorespiratory signal synthesizer was designed by conditional sampling from a multimodally trained stochastic system of Gaussian copulas integrated in a Markov chain. With respect to the latter, a multi-branch convolutional neural network architecture was conceived to learn the best cardiac sensor-fusion strategy at every abstraction layer. The network was tailored to the tasks of cycle detection and classification for different cardiac modality combinations by a synthesizer-based data augmentation training framework and Bayesian hyperparameter optimization. The synthesizer yielded highly realistic signals in the time, frequency and phase domains for both healthy and pathological heart cycles as well as artifacts of different modalities. Benchmarking suggested that the network is able to surpass previous architectures and data augmentation provided a performance boost in realistic data availability scenarios. These included insufficient training data volume, as low as 150 cycles long, artifact contamination and absence of a classification data type in training.

The increasing need for comprehensive medical signal data has been scarcely tackled in the scope of non-classical modalities and multimodal signal. To overcome this, a data-driven, statistical approach to model cardiorespiratory signals combined with copulas to emulate inter and intramodality dependence is suggested. Gaussian Mixture Models, Fourier Series and Sum of Sines are fitted to different physiological portions of segmented heart cycles. Marginal distributions of the yielded parameters and their linear correlation are used to define a Gaussian Copula from which random sets of parameters are generated to simulate new beats. The model is applied to regular and capacitively coupled Electrocardiography (ECG-cECG) as well as a combination of ECG with blood pressure and ballistocardiography (ECG-BP-BCG) to demonstrate generation of multimodal recordings. Results show realistic wave morphologies and relevant inter and intramodality correlations with a wide range of potential applications such as testing, training and integrating signal processing algorithms.