Artificial neural network approaches for fluorescence lifetime imaging techniques

Gang Wu; Thomas Nowotny; Yongliang Zhang; Hongqi Yu; David Day-Uei Li

doi:10.1364/OL.41.002561

Artificial neural network approaches for fluorescence lifetime imaging techniques

Gang Wu, Thomas Nowotny, Yongliang Zhang, Hongqi Yu, David Day-Uei Li

Strathclyde Institute Of Pharmacy And Biomedical Sciences

Research output: Contribution to journal › Article › peer-review

49 Citations (Scopus)

114 Downloads (Pure)

Abstract

A novel high-speed fluorescence lifetime imaging (FLIM) analysis method based on artificial neural networks (ANN) has been proposed. The proposed ANN-FLIM method does not require iterative searching procedures or initial conditions, which are usually required for traditional FLIM methods. In terms of image generation, ANN-FLIM is free from iterative computations and able to generate lifetime images at least 180-fold faster than conventional least squares curve-fitting approaches. The advantages of ANN-FLIM were demonstrated on both synthesized and experimental data, showing that it has great potential to fuel current revolutions in rapid FLIM technologies.

Original language	English
Pages (from-to)	2561-2564
Number of pages	4
Journal	Optics Letters
Volume	41
Issue number	11
DOIs	https://doi.org/10.1364/OL.41.002561
Publication status	Published - 25 May 2016

Keywords

fluorescence lifetime imaging microscopy
FLIM
fluorophores

Access to Document

10.1364/OL.41.002561

Wu-etal-OL-2016-Artificial-neural-network-approaches-for-fluorescence-lifetimeFinal published version, 1.73 MB

David Li
- david.listrath.acuk
- Health and Wellbeing
- Biomedical Engineering - Reader
Person: Academic

Smart solid-state Raman spectrometers
Li, D. (Principal Investigator) & Lin, S.-D. (Academic)
Royal Society
16/03/15 → 15/09/17
Project: Research
GPU-enhanced Biomedical Image Analysis
Li, D. (Principal Investigator), Nowotny, T. (Co-investigator) & Wu, G. (Post Grad Student)
1/06/12 → 31/08/16
Project: Research

File

Cite this

@article{2b33e9d531aa49f99e18409d4f85b7b4,

title = "Artificial neural network approaches for fluorescence lifetime imaging techniques",

abstract = "A novel high-speed fluorescence lifetime imaging (FLIM) analysis method based on artificial neural networks (ANN) has been proposed. The proposed ANN-FLIM method does not require iterative searching procedures or initial conditions, which are usually required for traditional FLIM methods. In terms of image generation, ANN-FLIM is free from iterative computations and able to generate lifetime images at least 180-fold faster than conventional least squares curve-fitting approaches. The advantages of ANN-FLIM were demonstrated on both synthesized and experimental data, showing that it has great potential to fuel current revolutions in rapid FLIM technologies. ",

keywords = "fluorescence lifetime imaging microscopy, FLIM, fluorophores",

author = "Gang Wu and Thomas Nowotny and Yongliang Zhang and Hongqi Yu and Li, {David Day-Uei}",

note = "{\textcopyright} 2016 Optical Society of America. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modifications of the content of this paper are prohibited.",

year = "2016",

month = may,

day = "25",

doi = "10.1364/OL.41.002561",

language = "English",

volume = "41",

pages = "2561--2564",

journal = "Optics Letters",

issn = "0146-9592",

publisher = "Optical Society of America",

number = "11",

}

TY - JOUR

T1 - Artificial neural network approaches for fluorescence lifetime imaging techniques

AU - Wu, Gang

AU - Nowotny, Thomas

AU - Zhang, Yongliang

AU - Yu, Hongqi

AU - Li, David Day-Uei

N1 - © 2016 Optical Society of America. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modifications of the content of this paper are prohibited.

PY - 2016/5/25

Y1 - 2016/5/25

N2 - A novel high-speed fluorescence lifetime imaging (FLIM) analysis method based on artificial neural networks (ANN) has been proposed. The proposed ANN-FLIM method does not require iterative searching procedures or initial conditions, which are usually required for traditional FLIM methods. In terms of image generation, ANN-FLIM is free from iterative computations and able to generate lifetime images at least 180-fold faster than conventional least squares curve-fitting approaches. The advantages of ANN-FLIM were demonstrated on both synthesized and experimental data, showing that it has great potential to fuel current revolutions in rapid FLIM technologies.

AB - A novel high-speed fluorescence lifetime imaging (FLIM) analysis method based on artificial neural networks (ANN) has been proposed. The proposed ANN-FLIM method does not require iterative searching procedures or initial conditions, which are usually required for traditional FLIM methods. In terms of image generation, ANN-FLIM is free from iterative computations and able to generate lifetime images at least 180-fold faster than conventional least squares curve-fitting approaches. The advantages of ANN-FLIM were demonstrated on both synthesized and experimental data, showing that it has great potential to fuel current revolutions in rapid FLIM technologies.

KW - fluorescence lifetime imaging microscopy

KW - FLIM

KW - fluorophores

U2 - 10.1364/OL.41.002561

DO - 10.1364/OL.41.002561

M3 - Article

SN - 0146-9592

VL - 41

SP - 2561

EP - 2564

JO - Optics Letters

JF - Optics Letters

IS - 11

ER -

Artificial neural network approaches for fluorescence lifetime imaging techniques

Abstract

Keywords

Access to Document

Fingerprint

Profiles

David Li

Projects

Smart solid-state Raman spectrometers

GPU-enhanced Biomedical Image Analysis

Cite this