MEMS Particle Sorting With Camera Confirmation and Deep Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fluorescence-activated cell sorting systems (FACS) are large, expensive, and require substantial training, leading to limited accessibility and inefficiencies in sorting sub-populations, while MEMS-based systems face challenges in real-time optimization and accuracy.
Innovation Solution
A microfabricated particle manipulation system with multiple laser interrogation regions and optical confirmation using a camera/classifier, employing deep learning algorithms for real-time optimization and enhanced accuracy in sorting or manipulating particles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fluorescence-activated cell sorting systems (FACS) are used for particle sorting, then sorting capability is achieved, but system size and cost increase substantially
Solution Approach 1:
The patent divides the particle sorting function into separate modular components: a microfabricated particle manipulation device with multiple discrete manipulation stages, each performing specific functions (deflection, sorting, manipulation). This segmentation allows the system to achieve complex sorting capabilities while maintaining a compact overall structure, avoiding the need for large integrated FACS systems.
Solution Approach 2:
The patent replaces the complex optical-mechanical FACS system with a microfabricated device that uses controlled fluid flow and electromagnetic fields for particle manipulation. The microfabricated device uses pressure-driven flow and electrostatic or magnetic actuation instead of large optical systems, lasers, and mechanical sorting mechanisms, thereby reducing system size while maintaining sorting functionality.
2Reliability
If fluorescence-activated cell sorting systems (FACS) are used for particle sorting, then sorting capability is achieved, but system cost and training requirements increase
Solution Approach 1:
The microfabricated particle manipulation device is designed with automated control systems that manage the complex sorting operations without requiring extensive user training. The device integrates control electronics and software that automatically regulate fluid flow, particle detection, and manipulation stage actuation, making the system easier to operate compared to traditional FACS systems that require specialized training.
3Device complexity
If MEMS-based particle manipulation systems are used, then system size is reduced, but real-time optimization capability is limited
Solution Approach 1:
The patent incorporates feedback mechanisms in the microfabricated particle manipulation device, where detectors monitor particle properties in real-time and the control system adjusts manipulation parameters accordingly. This feedback loop enables real-time optimization of sorting parameters, allowing the compact MEMS-based system to adapt to varying particle characteristics and optimize performance dynamically.
Solution Approach 2:
The microfabricated device employs dynamically adjustable parameters including variable fluid flow rates, adjustable electromagnetic field strengths, and movable manipulation stages that can be repositioned in real-time. This dynamic capability allows the system to adapt to different particle types and sorting requirements, providing versatility comparable to larger systems while maintaining compact dimensions.
4Manufacturing precision
If multiple manipulation stages are used in microfabricated devices, then manipulation precision is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple manipulation functions into a single integrated microfabricated device structure. The multiple manipulation stages are fabricated together on the same substrate using microfabrication techniques, sharing common fluid channels, support structures, and control systems. This merging approach maintains high manipulation precision through multi-stage processing while avoiding the complexity of assembling separate devices.
Solution Approach 2:
The microfabricated device is designed with universal components that perform multiple functions: the same substrate and fluid channels support all manipulation stages, the same control electronics regulate all actuation mechanisms, and the same detector system monitors particles throughout the manipulation process. This multi-functionality reduces overall device complexity while enabling precise multi-stage particle manipulation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables real-time adjustment of sorting parameters, improves accuracy and efficiency, and reduces the need for extensive training, making MEMS-based systems more accessible and effective for smaller entities.
Implementation Method 1
This signal may be a photon from a fluorescent tag which is affixed to the target particle and excited by laser illumination in an interrogation region upstream of the MEMS device.
Implementation Method 2
The actuation means for the moveable switch may be thermal, piezoelectric, electrostatic, or magnetic, for example.
Implementation Method 3
The actuation means for the moveable switch may be thermal, piezoelectric, electrostatic, or magnetic, for example.
Data Source
AI summary
A MEMS-based particle manipulation system which uses a particle manipulation stage and optical confirmation of the manipulation. The optical confirmation may be camera-based, and may be used to assess the effectiveness or accuracy of the particle manipulation stage. In one exemplary embodiment, the particle manipulation stage is a microfabricated, fluid valve, which sorts a target particle from non-target particles in a fluid stream. The optical confirmation stage is disposed in the microfabricated fluid channels at the input and output of the microfabricated sorting valve. Deep learning techniques are brought to bear on the camera output to increase speed, accuracy and reliability.