FlowMorph: Physics-Consistent Self-Supervision for Label-Free Single-Cell Mechanics in Microfluidic Videos

TL;DR

FlowMorph is a physics-informed self-supervised framework that accurately assesses red blood cell mechanics from microfluidic videos without labels, outperforming existing methods in shape and flow modeling.

Contribution

It introduces a novel physics-consistent self-supervised approach for label-free RBC mechanics analysis, integrating laminar flow physics with shape modeling and flow agreement.

Findings

Achieves 0.905 silhouette IoU on RBC videos with velocity fields.

Separates cell dynamics with 0.863 AUC using scalar $k$.

Predicts Young's modulus with 0.118 MPa MAE using minimal calibration.

Abstract

Mechanical properties of red blood cells (RBCs) are promising biomarkers for hematologic and systemic disease, motivating microfluidic assays that probe deformability at throughputs of $10^3$--$10^6$ cells per experiment. However, existing pipelines rely on supervised segmentation or hand-crafted kymographs and rarely encode the laminar Stokes-flow physics that governs RBC shape evolution. We introduce FlowMorph, a physics-consistent self-supervised framework that learns a label-free scalar mechanics proxy $k$ for each tracked RBC from short brightfield microfluidic videos. FlowMorph models each cell by a low-dimensional parametric contour, advances boundary points through a differentiable ''capsule-in-flow'' combining laminar advection and curvature-regularized elastic relaxation, and optimizes a loss coupling silhouette overlap, intra-cellular flow agreement, area conservation, wall constraints, and temporal smoothness, using only automatically derived silhouettes and optical flow. Across four public RBC microfluidic datasets, FlowMorph achieves a mean silhouette IoU of $0.905$ on physics-rich videos with provided velocity fields and markedly improves area conservation and wall violations over purely data-driven baselines. On $\sim 1.5\times 10^5$ centered sequences, the scalar $k$ alone separates tank-treading from flipping dynamics with an AUC of $0.863$. Using only $200$ real-time deformability cytometry (RT-DC) events for calibration, a monotone map $E=g(k)$ predicts apparent Young's modulus with a mean absolute error of $0.118$\,MPa on $600$ held-out cells and degrades gracefully under shifts in channel geometry, optics, and frame rate.