Publication

FPGA implementation of sequence-to-sequence encoder-decoder deep learning model for real-time fluorescence parameter estimation through SwissSPAD2 camera

Claudio Bruschini
2025

Abstract

Fluorescence Lifetime Imaging (FLI) is widely used in biomedical research for its high sensitivity and detailed cellular insights. It is effective for multiplexed studies and provides information about metabolic states, protein interactions, and ligand-target engagements, independent of signal intensity and fluorophore concentration. Traditional FLI techniques are slow and computationally demanding. This study addresses these limitations by implementing a deep learning-based sequence-to-sequence model directly into the SwissSPAD2 (SS2), a photon-counting camera coupled to an FPGA. The integration, enhanced by efficient resource management and parallel computation, allows for near-real-time output of FLI parameters. We tested the performance using in-silico and in-vitro data, demonstrating that this approach advances the feasibility of real-time FLI analysis, with promising implications for both preclinical and clinical applications.

Official source

https://infoscience.epfl.ch/entities/publication/42b37280-c743-4e53-9d9a-a03108a53842

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Claudio Bruschini
2025

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/42b37280-c743-4e53-9d9a-a03108a53842

About this result

Related concepts (23)

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Transformer (machine learning model)

A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.

Autoencoder

An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction. Variants exist, aiming to force the learned representations to assume useful properties.

Related publications (32)

FPGA implementation of sequence-to-sequence encoder-decoder deep learning model for real-time fluorescence parameter estimation through SwissSPAD2 camera

Chat with Graph Search

A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation

Advection-Diffusion on Graphs: A Bakry-Émery Laplacian for Spectral Graph Neural Networks

Physically Grounded Generative Modeling of All-Atom Biomolecular Dynamics