Low-latency label-free image-activated cell sorting using fast deep learning and AI inferencing.

Journal: Biosensors & bioelectronics
Published Date: Nov 7, 2022

Abstract

Classification and sorting of cells using image-activated cell sorting (IACS) systems can bring significant insight to biomedical sciences. Incorporating deep learning algorithms into IACS enables cell classification and isolation based on complex and human-vision uninterpretable morphological features within a heterogeneous cell population. However, the limited capabilities and complicated implementation of deep learning-assisted IACS systems reported to date hinder the adoption of the systems for a wide range of biomedical research. Here, we present image-activated cell sorting by applying fast deep learning algorithms to conduct cell sorting without labeling. The overall sorting latency, including signal processing and AI inferencing, is less than 3 ms, and the training time for the deep learning model is less than 30 min with a training dataset of 20,000 images. Both values set the record for IACS with sorting by AI inference. . We demonstrated our system performance through a 2-part polystyrene beads sorting experiment with 96.6% sorting purity, and a 3-part human leukocytes sorting experiment with 89.05% sorting purity for monocytes, 92.00% sorting purity for lymphocytes, and 98.24% sorting purity for granulocytes. The above performance was achieved with simple hardware containing only 1 FPGA, 1 PC and GPU, as a result of an optimized custom CNN UNet and efficient use of computing power. The system provides a compact, sterile, low-cost, label-free, and low-latency cell sorting solution based on real-time AI inferencing and fast training of the deep learning model.

Authors

  • Rui Tang
    State Key Laboratory of Earth Surface Processes and Resource Ecology, College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, China.
  • Lin Xia
    Department of Pharmacy, Shanghai Changhai Hospital, Naval Medical University, Shanghai, People's Republic of China.
  • Bien Gutierrez
    NanoCellect Biomedical Inc., San Diego, CA, 92121, USA.
  • Ivan Gagne
    NanoCellect Biomedical Inc., San Diego, CA, 92121, USA.
  • Adonary Munoz
    NanoCellect Biomedical Inc., San Diego, CA, 92121, USA.
  • Korina Eribez
    NanoCellect Biomedical Inc., San Diego, CA, 92121, USA.
  • Nicole Jagnandan
    NanoCellect Biomedical Inc., San Diego, CA, 92121, USA.
  • Xinyu Chen
    State Key Laboratory of ASIC and System, School of Microelectronics, Fudan University, Shanghai 200433, China.
  • Zunming Zhang
    Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, 92093, USA.
  • Lauren Waller
    Department of Bioengineering, University of California, San Diego, La Jolla, CA, 92093, USA.
  • William Alaynick
    NanoCellect Biomedical Inc., San Diego, CA, 92121, USA.
  • Sung Hwan Cho
    Department of Anesthesiology and Pain Medicine, Soonchunhyang University Bucheon Hospital, Soonchunhyang University College of Medicine, Bucheon, Republic of Korea.
  • Cheolhong An
    Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA.
  • Yu-Hwa Lo
    Department of Electrical and Computer Engineering, University of California, San Diego, California.

Keywords

External Resources

Popular Topics
Recent Journals