arXiv subjects

Sukirt Thakur

Publications and source records attributed to Sukirt Thakur.

7 recordsLinked to original sources

arXiv2026

From Centerlines to Hemodynamics: Anisotropic RBF Decoders for Coronary Arteries

Accurate and rapid estimation of hemodynamic metrics, such as pressure and wall shear stress (WSS), is important for assessing the severity of Coronary Artery Disease (CAD). Existing approaches, including invasive Fractional Flow Reserve (FFR) measurements and computationally expensive Computational Fluid Dynamics (CFD) simulations, face challenges in invasiveness, cost, and speed. We present a learned surrogate for fast prediction of CFD-simulated coronary hemodynamics from vessel centerline geometry. The model encodes 1D vessel centerlines together with inlet flow rate using a transformer-based encoder, and predicts continuous wall-based fields via an anisotropic Radial Basis Function (RBF) decoder aligned with vessel morphology. To support training and evaluation, we introduce two datasets with paired steady-state OpenFOAM simulations: (i) a synthetic benchmark of $4{,}200$ single-vessel geometries with controlled anatomical variations, and (ii) a multi-vessel dataset derived from ImageCAS including $4{,}800$ cases spanning both right and left coronary arteries, generated by randomly introducing stenoses and varying physiologically plausible flow rates. Across both datasets, our method achieves lower pressure and WSS errors than strong neural-operator baselines (GNOT, Transolver, and ONO) at a fraction of the computational cost of CFD. On the multi-vessel dataset, using $1{,}024$ anisotropic RBF centers our model reduces the mean relative $\ell_2$ error by $52\%$ compared to the best neural-operator baseline, while at $128$ centers it requires $13.8\times$ fewer FLOPs than GNOT and still outperforms all neural-operator baselines. The single-vessel dataset is publicly available at https://huggingface.co/datasets/angioinsight/single-vessel-flow

cs.CE↗

arXiv2026

PUNCH: Physics-informed Uncertainty-aware Network for Coronary Hemodynamics

More than 10 million coronary angiograms are performed globally each year, providing a gold standard for detecting obstructive coronary artery disease. Yet, no obstructive lesions are identified in 70% of patients evaluated for ischemic heart disease. Up to half of these patients have undiagnosed, life-limiting coronary microvascular dysfunction (CMD), which remains under-detected due to the limited availability of invasive tools required to measure coronary flow reserve (CFR). Here, we introduce PUNCH, a non-invasive, uncertainty-aware framework for estimating CFR directly from standard coronary angiography. PUNCH integrates physics-informed neural networks with variational inference to infer coronary blood flow from first-principles models of contrast transport, without requiring ground-truth flow measurements or population-level training. The pipeline runs in approximately three minutes per patient on a single GPU. Validated on synthetic angiograms with controlled noise and imaging artifacts, as well as on clinical bolus thermodilution data from 20 patients, PUNCH demonstrates accurate and uncertainty-calibrated CFR estimation. This approach establishes a new paradigm for CMD diagnosis and illustrates how physics-informed inference can substantially expand the diagnostic utility of available clinical imaging.

cs.LG↗

arXiv2025

ELPINN: Eulerian Lagrangian Physics-Informed Neural Network

Physics-Informed Neural Networks (PINNs) have gained widespread popularity for solving inverse and forward problems across a range of scientific and engineering domains. However, most existing PINN frameworks are limited to the Eulerian domain, where physical quantities are described at fixed spatial locations. In this work, we propose a novel PINN-based framework that couples Eulerian and Lagrangian perspectives by using particle trajectory data to reconstruct Eulerian velocity and pressure fields. We evaluate the performance of our method across three distinct fluid flow scenarios: two-dimensional external flow past a cylinder, two-dimensional internal flow in a confined geometry, and three-dimensional internal flow inside an airplane cabin. In all three cases, we successfully reconstruct the velocity field from Lagrangian particle data. Moreover, for the 2D external and internal flows, we recover the pressure field solely through the physics-informed learning process, without using any direct pressure measurements. We also conduct a sensitivity analysis to understand the effects of temporal resolution and particle count on the reconstruction accuracy. Our results show that smaller time-step sizes significantly improve the predictions, while the total number of particles has a comparatively smaller influence. These findings establish the potential of our coupled Eulerian-Lagrangian PINN framework as a powerful tool for enhancing experimental methods such as Particle Tracking Velocimetry (PTV). Looking ahead, this approach may be extended to infer hidden quantities such as pressure in three-dimensional flows or material properties like viscosity, opening new avenues for data-driven fluid dynamics in complex geometries.

physics.flu-dyn↗

arXiv2024

ViscoelasticNet: A physics informed neural network framework for stress discovery and model selection

Viscoelastic fluids are a class of fluids that exhibit both viscous and elastic nature. Modelling such fluids requires constitutive equations for the stress, and choosing the most appropriate constitutive relationship can be difficult. We present viscoelasticNet, a physics-informed deep learning framework that uses the velocity flow field to select the constitutive model and learn the stress field. Our framework requires data only for the velocity field, initial \& boundary conditions for the stress tensor, and the boundary condition for the pressure field. Using this information, we learn the model parameters, the pressure field, and the stress tensor. {This work considers} three commonly used non-linear viscoelastic models: Oldroyd-B, Giesekus, and linear Phan-Thien-Tanner (PTT). We demonstrate that our framework works well with noisy and sparse data. Our framework can be combined with velocity fields acquired from experimental techniques like particle image velocimetry to get the pressure \& stress fields and model parameters for the constitutive equation. Once the model has been discovered using viscoelasticNet, the fluid can be simulated and modeled for further applications.

physics.flu-dyn↗

arXiv2024

Physics-Informed Neural Network based inverse framework for time-fractional differential equations for rheology

Time-fractional differential equations offer a robust framework for capturing intricate phenomena characterized by memory effects, particularly in fields like biotransport and rheology. However, solving inverse problems involving fractional derivatives presents notable challenges, including issues related to stability and uniqueness. While Physics-Informed Neural Networks (PINNs) have emerged as effective tools for solving inverse problems, most existing PINN frameworks primarily focus on integer-ordered derivatives. In this study, we extend the application of PINNs to address inverse problems involving time-fractional derivatives, specifically targeting two problems: 1) anomalous diffusion and 2) fractional viscoelastic constitutive equation. Leveraging both numerically generated datasets and experimental data, we calibrate the concentration-dependent generalized diffusion coefficient and parameters for the fractional Maxwell model. We devise a tailored residual loss function that scales with the standard deviation of observed data. We rigorously test our framework's efficacy in handling anomalous diffusion. Even after introducing 25% Gaussian noise to the concentration dataset, our framework demonstrates remarkable robustness. Notably, the relative error in predicting the generalized diffusion coefficient and the order of the fractional derivative is less than 10% for all cases, underscoring the resilience and accuracy of our approach. In another test case, we predict relaxation moduli for three pig tissue samples, consistently achieving relative errors below 10%. Furthermore, our framework exhibits promise in modeling anomalous diffusion and non-linear fractional viscoelasticity.

cs.NE↗

arXiv2024

Inverse resolution of spatially varying diffusion coefficient using Physics-Informed neural networks

Resolving the diffusion coefficient is a key element in many biological and engineering systems, including pharmacological drug transport and fluid mechanics analyses. Additionally, these systems often have spatial variation in the diffusion coefficient which must be determined, such as for injectable drug-eluting implants into heterogeneous tissues. Unfortunately, obtaining the diffusion coefficient from images in such cases is an inverse problem with only discrete data points. The development of a robust method that can work with such noisy and ill-posed datasets to accurately determine spatially-varying diffusion coefficients is of great value across a large range of disciplines. Here, we developed an inverse solver that uses physics informed neural networks (PINNs) to calculate spatially-varying diffusion coefficients from numerical and experimental image data in varying biological and engineering applications. The residual of the transient diffusion equation for a concentration field is minimized to find the diffusion coefficient. The robustness of the method as an inverse solver was tested using both numerical and experimental datasets. The predictions show good agreement with both the numerical and experimental benchmarks; an error of less than 6.31% was obtained against all numerical benchmarks, while the diffusion coefficient calculated in experimental datasets matches the appropriate ranges of other reported literature values. Our work demonstrates the potential of using PINNs to resolve spatially-varying diffusion coefficients, which may aid a wide-range of applications, such as enabling better-designed drug-eluting implants for regenerative medicine or oncology fields.

q-bio.QM↗

arXiv2023

Temporal Consistency Loss for Physics-Informed Neural Networks

Physics-informed neural networks (PINNs) have been widely used to solve partial differential equations in a forward and inverse manner using deep neural networks. However, training these networks can be challenging for multiscale problems. While statistical methods can be employed to scale the regression loss on data, it is generally challenging to scale the loss terms for equations. This paper proposes a method for scaling the mean squared loss terms in the objective function used to train PINNs. Instead of using automatic differentiation to calculate the temporal derivative, we use backward Euler discretization. This provides us with a scaling term for the equations. In this work, we consider the two and three-dimensional Navier-Stokes equations and determine the kinematic viscosity using the spatio-temporal data on the velocity and pressure fields. We first consider numerical datasets to test our method. We test the sensitivity of our method to the time step size, the number of timesteps, noise in the data, and spatial resolution. Finally, we use the velocity field obtained using Particle Image Velocimetry (PIV) experiments to generate a reference pressure field. We then test our framework using the velocity and reference pressure field.

physics.flu-dyn↗