Abstract

In this work we combine a high flow cytometry experimental setup and a 10Kframe/sec capable neuromorphic event-based camera, followed by lightweight machine learning schemes, thus allowing the simultaneous imaging and real-time classification of test particles, moving at a speed of 0.8m/sec with an accuracy of 97.6%. The key advantage of the utilized microscopy system, is the use of an event-based camera, generating spiking events, triggered by pixel’s contrast changes. This bio-inspired operation, contrary to conventional CMOS cameras [1], alleviates bandwidth constraints and can significantly boost frame-rate capabilities, thus capturing high speed events. Following this paradigm, medical imaging modalities, where the detection and analysis of fast-moving particles is a necessity, such as high-flow cytometry, can greatly proliferate from the proposed approach.

© 2023 IEEE