Ioannis Tsilikas | Searcharxiv

arXiv2025

Neuromorphic Imaging Flow Cytometry combined with Adaptive Recurrent Spiking Neural Networks

We present an experimental imaging flow cytometer using a 1 μs temporal resolution event-based CMOS camera, with data processed by adaptive feedforward and recurrent spiking neural networks. Our study classifies PMMA particles (12, 16, 20 μm) flowing at 0.7 m/s in a microfluidic channel. Processing of experimental data highlighted that spiking recurrent networks, including LSTM and GRU models, achieved 98.4% accuracy by leveraging temporal dependencies. Additionally, adaptation mechanisms in lightweight feedforward spiking networks improved accuracy by 4.3%. This work outlines a technological roadmap for neuromorphic-assisted biomedical applications, enhancing classification performance while maintaining low latency and sparsity.

physics.optics↗

arXiv2024

Photonic Neuromorphic Accelerators for Event-Based Imaging Flow Cytometry

In this work, we present experimental results of a high-speed label-free imaging cytometry system that seamlessly merges the high-capturing rate and data sparsity of an event-based CMOS camera with lightweight photonic neuromorphic processing. This combination offers high classification accuracy and a massive reduction in the number of trainable parameters of the digital machine-learning back-end. The photonic neuromorphic accelerator is based on a hardware-friendly passive optical spectrum slicing technique that is able to extract meaningful features from the generated spike-trains. The experimental scenario comprises the discrimination of artificial polymethyl methacrylate calibrated beads, having different diameters, flowing at a mean speed of 0.01m/sec. Classification accuracy, using only lightweight, digital machine-learning schemes has topped at 98.2%. On the other hand, by experimentally pre-processing the raw spike data through the proposed photonic neuromorphic spectrum slicer we achieved an accuracy of 98.6%. This performance was accompanied by a reduction in the number of trainable parameters at the classification back-end by a factor ranging from 8 to 22, depending on the configuration of the digital neural network.

physics.optics↗