Intraventricular vector flow mapping (iVFM) seeks to enhance and quantify color Doppler in cardiac imaging. In this study, we propose novel alternatives to the traditional iVFM optimization scheme by utilizing physics-informed neural networks (PINNs) and a physics-guided nnU-Net-based supervised approach. When evaluated on simulated color Doppler images derived from a patient-specific computational fluid dynamics model and in vivo Doppler acquisitions, both approaches demonstrate comparable reconstruction performance to the original iVFM algorithm. The efficiency of PINNs is boosted through dual-stage optimization and pre-optimized weights. On the other hand, the nnU-Net method excels in generalizability and real-time capabilities. Notably, nnU-Net shows superior robustness on sparse and truncated Doppler data while maintaining independence from explicit boundary conditions. Overall, our results highlight the effectiveness of these methods in reconstructing intraventricular vector blood flow. The study also suggests potential applications of PINNs in ultrafast color Doppler imaging and the incorporation of fluid dynamics equations to derive biomarkers for cardiovascular diseases based on blood flow.

We study viral transmission in crowds via the short-ranged airborne pathway using a purely model-based approach. Our goal is two-pronged. Firstly, we illustrate with a concrete and pedagogical case study how to estimate the risks of new viral infections by coupling pedestrian simulations with the transmission algorithm that we recently released as open-source code. The algorithm hinges on pre-computed viral concentration maps derived from computational fluid dynamics (CFD) simulations. Secondly, we investigate to what extent the transmission risk predictions depend on the pedestrian dynamics model in use. For the simple bidirectional flow under consideration, the predictions are found to be surprisingly stable across initial conditions and models, despite the different microscopic arrangements of the simulated crowd, as long as the crowd evolves in a qualitatively similarly way. On the other hand, when major changes are observed in the crowd's behaviour, notably whenever a jam occurs at the centre of the channel, the estimated risks surge drastically.