arXiv subjects

Patrick Segers

Publications and source records attributed to Patrick Segers.

4 recordsLinked to original sources

arXiv2026

Attractor Image-Based Deep Learning of Arterial Pulse Waves for Age Classification

Arterial pulse waveform morphology evolves with age, reflecting structural and functional changes in the cardiovascular system. Thus, vascular age is a valuable surrogate marker of cardiovascular health, and premature vascular ageing can indicate increased disease risk. Pulse wave analysis could support risk stratification in otherwise asymptomatic adults. We transformed pulse wave time-series data from photoplethysmography (PPG) and arterial tonometry into images, using the Symmetric Projection Attractor Reconstruction (SPAR) method. These SPAR images were used to train a convolutional neural network to classify healthy subjects into two closely spaced age groups (35-40 and 50-55 years). The model demonstrated consistent classification performance across internal and external test sets, achieving F1 scores above 70% for both PPG and tonometry signals. These results suggest that SPAR-derived pulse wave images contain discriminative morphological features even among healthy adults close in age. This proof-of-concept lays the groundwork for future research into the use of SPAR for early risk detection using smart wearables.

cs.LG↗

arXiv2025

Large deformation diffeomorphic cardiac strain mapping

Cardiac deformation is a crucial biomarker for the evaluation of cardiac function. Current methods for estimating cardiac strain might underestimate local deformation due to through-plane motion and segmental averaging. Mesh-based mapping methods are gaining interest for localized analysis of cardiac motion and strain, yet they often do not consider important properties of cardiac tissue. In this work, we propose an extension of the large deformation diffeomorphic metric mapping framework to incorporate near incompressibility into the loss function that guides the mapping. As such, our mechanically regularized mLDDMM allows for accurate and mechanically coherent estimation of volume displacement and strain tensors from time-resolved three-dimensional meshes. We benchmark our method against the results of a finite element simulation of cardiac contraction and find a very good agreement between our estimation and the simulated ground truth. Our method forms a promising technique to extract volume displacement and strain tensors from time-resolved meshes while accounting for the incompressibility of cardiac tissue.

q-bio.TO↗

arXiv2025

Unveiling sex dimorphism in the healthy cardiac anatomy: fundamental differences between male and female heart shapes

Sex-based differences in cardiovascular disease are well documented, yet the precise nature and extent of these discrepancies in cardiac anatomy remain incompletely understood. Traditional scaling models often fail to capture the interplay of age, blood pressure, and body size, prompting a more nuanced investigation. Here, we employ statistical shape modeling in a healthy subset (n=456) of the UK Biobank to explore sex-specific variations in biventricular anatomy. We reconstruct 3D meshes and perform multivariate analyses of shape coefficients, controlling for age, blood pressure, and various body size metrics. Our findings reveal that sex alone explains at least 25 percent of morphological variability, with strong discrimination between men and women (AUC=0.96-0.71) persisting even after correction for confounders. Notably, the most discriminative modes highlight pronounced differences in cardiac chamber volumes, the anterior-posterior width of the right ventricle, and the relative positioning of the cardiac chambers. These results underscore that sex has a fundamental influence on cardiac morphology, which may have important clinical implications for differing cardiac structural assessments in men and women. Future work should investigate how these anatomical differences manifest in various cardiovascular conditions, ultimately paving the way for more precise risk stratification and personalized therapeutic strategies for both men and women.

q-bio.TO↗

arXiv2018

Color-Doppler Echocardiography Flow Field Velocity Reconstruction Using a Streamfunction -Vorticity Formulation

We introduce a new method, (Doppler Velocity Reconstruction or DoVeR), for reconstructing two-component velocity fields from color Doppler scans. DoVeR employs the streamfunction-vorticity equation, which satisfies mass conservation while accurately approximating the flow rate of rotation. We validated DoVeR using artificial color Doppler images generated from computational fluid dynamics models of left ventricle (LV) flow. We compare DoVeR against the conventional intraventricular Vector Flow Mapping (iVFM1D) and reformulated iVFM (iVFM2D). LV model error analysis showed DoVeR is more robust to noise and probe placement, with noise RMS errors (nRMSE) between 3.81%-6.67%, while the iVFM methods delivered 4.16%-24.17% for iVFM1D and 4.06%-400.21% for iVFM2D. We test the DoVeR and iVFM methods using in-vivo mouse-LV ultrasound scans. DoVeR yielded more hemodynamically accurate reconstructions, suggesting that it can provide a more reliable approach for robust quantification of cardiac flow.

physics.med-ph↗