Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)

With the recent surge in the development of highly selective probes, fluorescence microscopy has become one of the most widely used approaches to studying cellular properties and signaling in living cells and tissues. Traditionally, microscopy image analysis heavily relies on manufacturer-supplied s...

Full description

Saved in:
Bibliographic Details
Main Authors: Alok Bhattarai, Jan Meyer, Laura Petersilie, Syed I. Shah, Louis A. Neu, Christine R. Rose, Ghanim Ullah
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Biomolecules
Subjects:
Online Access:https://www.mdpi.com/2218-273X/14/11/1348
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154152930967552
author Alok Bhattarai
Jan Meyer
Laura Petersilie
Syed I. Shah
Louis A. Neu
Christine R. Rose
Ghanim Ullah
author_facet Alok Bhattarai
Jan Meyer
Laura Petersilie
Syed I. Shah
Louis A. Neu
Christine R. Rose
Ghanim Ullah
author_sort Alok Bhattarai
collection DOAJ
description With the recent surge in the development of highly selective probes, fluorescence microscopy has become one of the most widely used approaches to studying cellular properties and signaling in living cells and tissues. Traditionally, microscopy image analysis heavily relies on manufacturer-supplied software, which often demands extensive training and lacks automation capabilities for handling diverse datasets. A critical challenge arises if the fluorophores employed exhibit low brightness and a low signal-to-noise ratio (SNR). Consequently, manual intervention may become a necessity, introducing variability in the analysis outcomes even for identical samples when analyzed by different users. This leads to the incorporation of blinded analysis, which ensures that the outcome is free from user bias to a certain extent but is extremely time-consuming. To overcome these issues, we developed a tool called DL-SCAN that automatically segments and analyzes fluorophore-stained regions of interest such as cell bodies in fluorescence microscopy images using deep learning. We demonstrate the program’s ability to automate cell identification and study cellular ion dynamics using synthetic image stacks with varying SNR. This is followed by its application to experimental Na<sup>+</sup> and Ca<sup>2+</sup> imaging data from neurons and astrocytes in mouse brain tissue slices exposed to transient chemical ischemia. The results from DL-SCAN are consistent, reproducible, and free from user bias, allowing efficient and rapid analysis of experimental data in an objective manner. The open-source nature of the tool also provides room for modification and extension to analyze other forms of microscopy images specific to the dynamics of different ions in other cell types.
format Article
id doaj-art-20481e4f24a44d3fbc7f586ad5074659
institution Kabale University
issn 2218-273X
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Biomolecules
spelling doaj-art-20481e4f24a44d3fbc7f586ad50746592024-11-26T17:53:54ZengMDPI AGBiomolecules2218-273X2024-10-011411134810.3390/biom14111348Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)Alok Bhattarai0Jan Meyer1Laura Petersilie2Syed I. Shah3Louis A. Neu4Christine R. Rose5Ghanim Ullah6Department of Physics, University of South Florida, Tampa, FL 33647, USAInstitute of Neurobiology, Faculty of Mathematics and Natural Sciences, Heinrich-Heine-University, 40225 Düsseldorf, GermanyInstitute of Neurobiology, Faculty of Mathematics and Natural Sciences, Heinrich-Heine-University, 40225 Düsseldorf, GermanyDepartment of Physics, University of South Florida, Tampa, FL 33647, USAInstitute of Neurobiology, Faculty of Mathematics and Natural Sciences, Heinrich-Heine-University, 40225 Düsseldorf, GermanyInstitute of Neurobiology, Faculty of Mathematics and Natural Sciences, Heinrich-Heine-University, 40225 Düsseldorf, GermanyDepartment of Physics, University of South Florida, Tampa, FL 33647, USAWith the recent surge in the development of highly selective probes, fluorescence microscopy has become one of the most widely used approaches to studying cellular properties and signaling in living cells and tissues. Traditionally, microscopy image analysis heavily relies on manufacturer-supplied software, which often demands extensive training and lacks automation capabilities for handling diverse datasets. A critical challenge arises if the fluorophores employed exhibit low brightness and a low signal-to-noise ratio (SNR). Consequently, manual intervention may become a necessity, introducing variability in the analysis outcomes even for identical samples when analyzed by different users. This leads to the incorporation of blinded analysis, which ensures that the outcome is free from user bias to a certain extent but is extremely time-consuming. To overcome these issues, we developed a tool called DL-SCAN that automatically segments and analyzes fluorophore-stained regions of interest such as cell bodies in fluorescence microscopy images using deep learning. We demonstrate the program’s ability to automate cell identification and study cellular ion dynamics using synthetic image stacks with varying SNR. This is followed by its application to experimental Na<sup>+</sup> and Ca<sup>2+</sup> imaging data from neurons and astrocytes in mouse brain tissue slices exposed to transient chemical ischemia. The results from DL-SCAN are consistent, reproducible, and free from user bias, allowing efficient and rapid analysis of experimental data in an objective manner. The open-source nature of the tool also provides room for modification and extension to analyze other forms of microscopy images specific to the dynamics of different ions in other cell types.https://www.mdpi.com/2218-273X/14/11/1348live cell imagingcell segmentationtracking ion dynamicsstreamlittracking morphological changes
spellingShingle Alok Bhattarai
Jan Meyer
Laura Petersilie
Syed I. Shah
Louis A. Neu
Christine R. Rose
Ghanim Ullah
Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)
Biomolecules
live cell imaging
cell segmentation
tracking ion dynamics
streamlit
tracking morphological changes
title Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)
title_full Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)
title_fullStr Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)
title_full_unstemmed Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)
title_short Deep-Learning-Based Segmentation of Cells and Analysis (DL-SCAN)
title_sort deep learning based segmentation of cells and analysis dl scan
topic live cell imaging
cell segmentation
tracking ion dynamics
streamlit
tracking morphological changes
url https://www.mdpi.com/2218-273X/14/11/1348
work_keys_str_mv AT alokbhattarai deeplearningbasedsegmentationofcellsandanalysisdlscan
AT janmeyer deeplearningbasedsegmentationofcellsandanalysisdlscan
AT laurapetersilie deeplearningbasedsegmentationofcellsandanalysisdlscan
AT syedishah deeplearningbasedsegmentationofcellsandanalysisdlscan
AT louisaneu deeplearningbasedsegmentationofcellsandanalysisdlscan
AT christinerrose deeplearningbasedsegmentationofcellsandanalysisdlscan
AT ghanimullah deeplearningbasedsegmentationofcellsandanalysisdlscan