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.

翻译：红细胞（RBC）的力学特性是血液系统疾病和全身性疾病有前景的生物标志物，这推动了微流控检测技术的发展，旨在以每次实验 $10^3$--$10^6$ 个细胞的通量探测其变形能力。然而，现有流程依赖于监督式分割或手工构建的时空图，并且很少编码支配红细胞形状演化的层流斯托克斯流物理规律。我们提出了FlowMorph，一个物理一致的自监督框架，它能够从短时明场微流控视频中为每个被追踪的红细胞学习一个无标记的标量力学代理 $k$。FlowMorph通过一个低维参数化轮廓对每个细胞进行建模，通过一个结合了层流平流和曲率正则化弹性松弛的可微分"流中胶囊"模型推进边界点，并优化一个耦合了轮廓重叠度、细胞内流场一致性、面积守恒、壁面约束和时间平滑性的损失函数，仅使用自动导出的轮廓和光流信息。在四个公开的红细胞微流控数据集上，FlowMorph在具有给定速度场的富含物理信息的视频上实现了平均轮廓交并比 $0.905$，并且在面积守恒和壁面约束违反方面显著优于纯数据驱动的基线方法。在约 $1.5\times 10^5$ 个居中的细胞序列上，仅标量 $k$ 本身就能以 $0.863$ 的AUC值区分坦克履带式运动与翻转动力学。仅使用 $200$ 个实时变形性细胞术（RT-DC）事件进行校准，一个单调映射 $E=g(k)$ 即可在 $600$ 个留出细胞上以 $0.118$\,MPa 的平均绝对误差预测表观杨氏模量，并且在通道几何形状、光学系统和帧率发生变化时性能下降平缓。