Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB
Abstract Background Endothelial healing after deployment of cardiovascular devices is particularly important in the context of clinical outcome. It is therefore of great interest to develop tools for a precise prediction of endothelial growth after injury in the process of implant deployment. For ex...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-06-01
|
Series: | BMC Molecular and Cell Biology |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12860-021-00369-3 |
id |
doaj-475e1edd0f744205a180b1fb1c80034a |
---|---|
record_format |
Article |
spelling |
doaj-475e1edd0f744205a180b1fb1c80034a2021-06-06T11:45:07ZengBMCBMC Molecular and Cell Biology2661-88502021-06-0122111510.1186/s12860-021-00369-3Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLABJan Oldenburg0Lisa Maletzki1Anne Strohbach2Paul Bellé3Stefan Siewert4Raila Busch5Stephan B. Felix6Klaus-Peter Schmitz7Michael Stiehm8Institute for ImplantTechnology and Biomaterials e.VDepartment of Internal Medicine, Cardiology, University Medicine GreifswaldDepartment of Internal Medicine, Cardiology, University Medicine GreifswaldInstitute for ImplantTechnology and Biomaterials e.VInstitute for ImplantTechnology and Biomaterials e.VDepartment of Internal Medicine, Cardiology, University Medicine GreifswaldDepartment of Internal Medicine, Cardiology, University Medicine GreifswaldInstitute for ImplantTechnology and Biomaterials e.VInstitute for ImplantTechnology and Biomaterials e.VAbstract Background Endothelial healing after deployment of cardiovascular devices is particularly important in the context of clinical outcome. It is therefore of great interest to develop tools for a precise prediction of endothelial growth after injury in the process of implant deployment. For experimental investigation of re-endothelialization in vitro cell migration assays are routinely used. However, semi-automatic analyses of live cell images are often based on gray value distributions and are as such limited by image quality and user dependence. The rise of deep learning algorithms offers promising opportunities for application in medical image analysis. Here, we present an intelligent cell detection (iCD) approach for comprehensive assay analysis to obtain essential characteristics on cell and population scale. Results In an in vitro wound healing assay, we compared conventional analysis methods with our iCD approach. Therefore we determined cell density and cell velocity on cell scale and the movement of the cell layer as well as the gap closure between two cell monolayers on population scale. Our data demonstrate that cell density analysis based on deep learning algorithms is superior to an adaptive threshold method regarding robustness against image distortion. In addition, results on cell scale obtained with iCD are in agreement with manually velocity detection, while conventional methods, such as Cell Image Velocimetry (CIV), underestimate cell velocity by a factor of 0.5. Further, we found that iCD analysis of the monolayer movement gave results just as well as manual freehand detection, while conventional methods again shows more frayed leading edge detection compared to manual detection. Analysis of monolayer edge protrusion by ICD also produced results, which are close to manual estimation with an relative error of 11.7%. In comparison, the conventional Canny method gave a relative error of 76.4%. Conclusion The results of our experiments indicate that deep learning algorithms such as our iCD have the ability to outperform conventional methods in the field of wound healing analysis. The combined analysis on cell and population scale using iCD is very well suited for timesaving and high quality wound healing analysis enabling the research community to gain detailed understanding of endothelial movement.https://doi.org/10.1186/s12860-021-00369-3Endothelial cellsUnetCNNNeural networkWound healingCell scale |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jan Oldenburg Lisa Maletzki Anne Strohbach Paul Bellé Stefan Siewert Raila Busch Stephan B. Felix Klaus-Peter Schmitz Michael Stiehm |
spellingShingle |
Jan Oldenburg Lisa Maletzki Anne Strohbach Paul Bellé Stefan Siewert Raila Busch Stephan B. Felix Klaus-Peter Schmitz Michael Stiehm Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB BMC Molecular and Cell Biology Endothelial cells Unet CNN Neural network Wound healing Cell scale |
author_facet |
Jan Oldenburg Lisa Maletzki Anne Strohbach Paul Bellé Stefan Siewert Raila Busch Stephan B. Felix Klaus-Peter Schmitz Michael Stiehm |
author_sort |
Jan Oldenburg |
title |
Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB |
title_short |
Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB |
title_full |
Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB |
title_fullStr |
Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB |
title_full_unstemmed |
Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB |
title_sort |
methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in matlab |
publisher |
BMC |
series |
BMC Molecular and Cell Biology |
issn |
2661-8850 |
publishDate |
2021-06-01 |
description |
Abstract Background Endothelial healing after deployment of cardiovascular devices is particularly important in the context of clinical outcome. It is therefore of great interest to develop tools for a precise prediction of endothelial growth after injury in the process of implant deployment. For experimental investigation of re-endothelialization in vitro cell migration assays are routinely used. However, semi-automatic analyses of live cell images are often based on gray value distributions and are as such limited by image quality and user dependence. The rise of deep learning algorithms offers promising opportunities for application in medical image analysis. Here, we present an intelligent cell detection (iCD) approach for comprehensive assay analysis to obtain essential characteristics on cell and population scale. Results In an in vitro wound healing assay, we compared conventional analysis methods with our iCD approach. Therefore we determined cell density and cell velocity on cell scale and the movement of the cell layer as well as the gap closure between two cell monolayers on population scale. Our data demonstrate that cell density analysis based on deep learning algorithms is superior to an adaptive threshold method regarding robustness against image distortion. In addition, results on cell scale obtained with iCD are in agreement with manually velocity detection, while conventional methods, such as Cell Image Velocimetry (CIV), underestimate cell velocity by a factor of 0.5. Further, we found that iCD analysis of the monolayer movement gave results just as well as manual freehand detection, while conventional methods again shows more frayed leading edge detection compared to manual detection. Analysis of monolayer edge protrusion by ICD also produced results, which are close to manual estimation with an relative error of 11.7%. In comparison, the conventional Canny method gave a relative error of 76.4%. Conclusion The results of our experiments indicate that deep learning algorithms such as our iCD have the ability to outperform conventional methods in the field of wound healing analysis. The combined analysis on cell and population scale using iCD is very well suited for timesaving and high quality wound healing analysis enabling the research community to gain detailed understanding of endothelial movement. |
topic |
Endothelial cells Unet CNN Neural network Wound healing Cell scale |
url |
https://doi.org/10.1186/s12860-021-00369-3 |
work_keys_str_mv |
AT janoldenburg methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT lisamaletzki methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT annestrohbach methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT paulbelle methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT stefansiewert methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT railabusch methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT stephanbfelix methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT klauspeterschmitz methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab AT michaelstiehm methodologyforcomprehensivecelllevelanalysisofwoundhealingexperimentsusingdeeplearninginmatlab |
_version_ |
1721393579629215744 |