Search for: All records

Label-free cell classification is advantageous for supplying pristine cells for further use or examination, yet existing techniques frequently fall short in terms of specificity and speed. In this study, we address these limitations through the development of a novel machine learning framework, Multiplex Image Machine Learning (MIML). This architecture uniquely combines label-free cell images with biomechanical property data, harnessing the vast, often underutilized biophysical information intrinsic to each cell. By integrating both types of data, our model offers a holistic understanding of cellular properties, utilizing cell biomechanical information typically discarded in traditional machine learning models. This approach has led to a remarkable 98.3% accuracy in cell classification, a substantial improvement over models that rely solely on image data. MIML has been proven effective in classifying white blood cells and tumor cells, with potential for broader application due to its inherent flexibility and transfer learning capability. It is particularly effective for cells with similar morphology but distinct biomechanical properties. This innovative approach has significant implications across various fields, from advancing disease diagnostics to understanding cellular behavior. 

In recent years, extracellular vesicles have become promising carriers as next-generation drug delivery platforms. Effective loading of exogenous cargos without compromising the extracellular vesicle membrane is a major challenge. Rapid squeezing through nanofluidic channels is a widely used approach to load exogenous cargoes into the EV through the nanopores generated temporarily on the membrane. However, the exact mechanism and dynamics of nanopore opening, as well as cargo loading through nanopores during the squeezing process remains unknown and it is impossible to visualize or quantify it experimentally due to the small size of the EV and the fast transient process. This paper developed a systemic algorithm to simulate nanopore formation and predict drug loading during extracellular vesicle (EV) squeezing by leveraging the power of coarse-grain (CG) molecular dynamics simulations with fluid dynamics. The EV CG beads are coupled with implicit the fluctuating lattice Boltzmann solvent. The effects of EV properties and various squeezing test parameters, such as EV size, flow velocity, channel width, and length, on pore formation and drug loading efficiency are analyzed. Based on the simulation results, a phase diagram is provided as a design guide for nanochannel geometry and squeezing velocity to generate pores on the membrane without damaging the EV. This method can be utilized to optimize the nanofluidic device configuration and flow setup to obtain desired drug loading into EVs. 

Abstract Microfluidic devices have found extensive applications in mechanical, biomedical, chemical, and materials research. However, the high initial cost, low resolution, inferior feature fidelity, poor repeatability, rough surface finish, and long turn-around time of traditional prototyping methods limit their wider adoption. In this study, a strategic approach to a deterministic fabrication process based on in-situ image analysis and intermittent flow control called image-guided in-situ maskless lithography (IGIs-ML), has been proposed to overcome these challenges. By using dynamic image analysis and integrated flow control, IGIs-ML provides superior repeatability and fidelity of densely packed features across a large area and multiple devices. This general and robust approach enables the fabrication of a wide variety of microfluidic devices and resolves critical proximity effect and size limitations in rapid prototyping. The affordability and reliability of IGIs-ML make it a powerful tool for exploring the design space beyond the capabilities of traditional rapid prototyping.