Neuromorphic-enabled video-activated cell sorting
Weihua He1, Junwen Zhu1, Yongxiang Feng1
1State Key Laboratory of Precision Measurement Technology and Instrument, Department of Precision Instrument, Tsinghua University, Beijing, China.
Nature Communications
|December 31, 2024
Summary
We developed a neuromorphic-enabled video-activated cell sorter (NEVACS) for high-throughput cell sorting. NEVACS improves accuracy in cell classification by using video data, overcoming limitations of current image-activated cell sorting methods.
Area of Science:
- Biotechnology
- Neuromorphic Engineering
- Cell Biology
Background:
- Existing image-activated cell sorting (IACS) methods struggle with 3D information loss and processing latency.
- Real-time cell sorting requires advanced spatiotemporal characterization capabilities.
Purpose of the Study:
- To introduce a neuromorphic-enabled video-activated cell sorter (NEVACS) framework.
- To achieve high-dimensional spatiotemporal characterization and high-throughput particle sorting.
Main Methods:
- NEVACS utilizes an event camera, CPU, and spiking neural networks on a neuromorphic chip.
- The framework employs simple microfluidic infrastructures for ease of use.
- It achieves a sorting throughput of 1000 cells/s with an economical hybrid hardware solution.
Main Results:
- NEVACS demonstrated high accuracy in classifying red blood cells and spherocytes.
- Utilizing video data significantly reduced classification error (0.99%) compared to single-frame analysis (19.93%).
- The system offers a wide field of view for comprehensive particle analysis.
Conclusions:
- NEVACS overcomes 3D information loss and latency issues in cell sorting.
- The framework shows significant potential for cell morphology screening and disease diagnosis.
- NEVACS provides an accurate and efficient solution for advanced cell analysis.
