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

arXiv: https://arxiv.org/abs/2601.17947 · HTML: https://mlsanity.com/paper/2601.17947/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 25 Jan 2026.

## Builds on (most cited first, 4 of 4)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)

## Abstract (arXiv)

Mechanical properties of red blood cells (RBCs) are promising biomarkers for hematologic and systemic disease, motivating microfluidic assays that probe deformability at throughputs of 103--106 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 ~ 1.5× 105 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.