摘要翻译：
人工评估、分类和计数生物物体需要花费大量的时间，而且人为的主观投入可能是误差的来源。为了研究微毛细管Poiseuille流中红细胞的形状，我们引入了一种卷积神经回归网络来实现红细胞形状的自动分类。从我们的实验中，我们期望有两种稳定的几何形状：所谓的“拖鞋”和“羊角面包”形状，这取决于主流流动条件和细胞固有参数。羊角面包大多发生在低剪切速率下，拖鞋则在较高的流速下进化。利用我们的方法，我们可以找到两个稳定形状的相之间的过渡点，这对以后的理论研究和数值模拟有很大的兴趣。使用基于统计的阈值，从我们的数据中，我们获得了所谓的相图，并与人工评估进行了比较。展望未来，我们的概念允许我们对各种流动条件的测量进行客观分析，并得到可比的结果。此外，所提出的程序能够无偏见地研究药物对单个RBCs流动特性的影响以及由此产生的全血流动行为的宏观变化。
---
英文标题：
《Classification of red blood cell shapes in flow using outlier tolerant
  machine learning》
---
作者：
Alexander Kihm, Lars Kaestner, Christian Wagner, Stephan Quint
---
最新提交年份：
2018
---
分类信息：

一级分类：Physics        物理学
二级分类：Biological Physics        生物物理学
分类描述：Molecular biophysics, cellular biophysics, neurological biophysics, membrane biophysics, single-molecule biophysics, ecological biophysics, quantum phenomena in biological systems (quantum biophysics), theoretical biophysics, molecular dynamics/modeling and simulation, game theory, biomechanics, bioinformatics, microorganisms, virology, evolution, biophysical methods.
分子生物物理、细胞生物物理、神经生物物理、膜生物物理、单分子生物物理、生态生物物理、生物系统中的量子现象（量子生物物理）、理论生物物理、分子动力学/建模与模拟、博弈论、生物力学、生物信息学、微生物、病毒学、进化论、生物物理方法。
--
一级分类：Physics        物理学
二级分类：Fluid Dynamics        流体动力学
分类描述：Turbulence, instabilities, incompressible/compressible flows, reacting flows. Aero/hydrodynamics, fluid-structure interactions, acoustics. Biological fluid dynamics, micro/nanofluidics, interfacial phenomena. Complex fluids, suspensions and granular flows, porous media flows. Geophysical flows, thermoconvective and stratified flows. Mathematical and computational methods for fluid dynamics, fluid flow models, experimental techniques.
湍流，不稳定性，不可压缩/可压缩流，反应流。气动/流体力学，流体-结构相互作用，声学。生物流体力学，微/纳米流体力学，界面现象。复杂流体，悬浮液和颗粒流，多孔介质流。地球物理流，热对流和层流。流体动力学的数学和计算方法，流体流动模型，实验技术。
--
一级分类：Quantitative Biology        数量生物学
二级分类：Other Quantitative Biology        其他定量生物学
分类描述：Work in quantitative biology that does not fit into the other q-bio classifications
不适合其他q-bio分类的定量生物学工作
--

---
英文摘要：
  The manual evaluation, classification and counting of biological objects demands for an enormous expenditure of time and subjective human input may be a source of error. Investigating the shape of red blood cells (RBCs) in microcapillary Poiseuille flow, we overcome this drawback by introducing a convolutional neural regression network for an automatic, outlier tolerant shape classification. From our experiments we expect two stable geometries: the so-called `slipper' and `croissant' shapes depending on the prevailing flow conditions and the cell-intrinsic parameters. Whereas croissants mostly occur at low shear rates, slippers evolve at higher flow velocities. With our method, we are able to find the transition point between both `phases' of stable shapes which is of high interest to ensuing theoretical studies and numerical simulations. Using statistically based thresholds, from our data, we obtain so-called phase diagrams which are compared to manual evaluations. Prospectively, our concept allows us to perform objective analyses of measurements for a variety of flow conditions and to receive comparable results. Moreover, the proposed procedure enables unbiased studies on the influence of drugs on flow properties of single RBCs and the resulting macroscopic change of the flow behavior of whole blood.
---
PDF链接：
https://arxiv.org/pdf/1806.08179