Section: New Results

Computational Physiology

Within the VP2HF project, non-invasive cardiac electrical data has been acquired at St Thomas' Hospital, London. It consists in Body Surface Potential Mapping (BSPM), which are recordings of the electrical potential on several locations on the surface of the torso. In [37], we use non-invasive data (body surface potential mapping, BSPM) to personalise complex cardiac electrical activation patterns such as multiple onset activation locations. We have used a relevance vector regression (see Figure 18) and we have evaluated our method on clinical datasets.

Figure 18. Pipeline of the non-invasive model personalisation

• We extended the multiscale 0D/3D personalisation approach previously published to build a fast, flexible and computationally efficient multifidelity personalisation. This algorithm called Multifidelity-CMA can be used to personalise hundreds of cases per day without specific manual supervision, fine-tuning of the algorithm or precomputation. The method was published in a scientific journal [24].

• We built more than 140 personalised 3D simulations in the context of two longitudinal studies. We first used personalised parameters to model short-term transient effects in digestion ([33] and a poster presentation at FIMH Conference 2016), then to analyze long-term evolution of the cardiac function in cardiomyopathies ([42] and a poster presentation at MICCAI Conference 2017). In particular we showed that the use of priors reduces considerably the variance in the population of estimated parameters leading a better conditionning of parameter values whose variability in the population only reflects physiological properties of the cases. In particular we projected personalised parameters onto the axis of a classifier which discriminates between a cohort of healthy and diseased cases, and showed that the evolution of parameter values suggests an improvement of the cardiac function under therapy since the parameters of the follow-up acquisition are closer to the healthy side of the classifier (see Figure 19).

Figure 19. Projection of personalised parameters on the main direction of a LDA classifier between the healthy cases (dark blue dots) and cardiomyopathy (other dots) cases (x-axis) and an principal orthogonal direction of this vector (y-axis). The dots in light blue, brown, orange and green correspond to 4 patients for which the data was available both at baseline (small dot) and follow-up (larger dot).