Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB

Oldenburg, Jan; Maletzki, Lisa; Strohbach, Anne; Belle, Paul; Siewert, Stefan; Busch, Rainer; Felix, Stephan B.; Schmitz, Klaus‐Peter; Stiehm, Michael

doi:10.1186/s12860-021-00369-3

Cited by 6 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the DL side, Oldenburg et al developed a platform for living cell research that can conduct cell- and population-scale analyses using MATLAB-based DL techniques [ 25 ]. They introduced a system that can analyze cell mobility at both the cell and population scales by training a 3-layer U-net structure using a semi-automatic labeling method.…”

Section: Discussionmentioning

confidence: 99%

“…Note that the notation is not fixed and may vary based on the input size and the specific details of the implementation [ 71 ]. The representation given here is intended to serve as a general guide to understanding the complexity of the model Study Cell line Data type Sample size Architecture DSC ACC IoU PRE REC SPE Network complexity Zaritsky et al [ 67 ] DA3, MDCK Wound healing assay 126 SVMs N/A 0.945 N/A N/A N/A N/A Glass et al [ 68 ] U2OS, 8505C Wound healing assay 107, 60 SVMs N/A N/A N/A 0.900 0.840 N/A Oldenburg et al [ 25 ] HCAEC Wound healing assay 280 U-net 0.918 N/A 0.821 N/A N/A N/A Ayanzadeh et al [ 30 ] MDA-MB-231,DSB2018 Individual cell segmentation 600, 670 U-net, ResN...…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

An automated in vitro wound healing microscopy image analysis approach utilizing U-net-based deep learning methodology

Doğru,

Özdemir,

Özdemir

et al. 2024

BMC Med Imaging

View full text Add to dashboard Cite

Background The assessment of in vitro wound healing images is critical for determining the efficacy of the therapy-of-interest that may influence the wound healing process. Existing methods suffer significant limitations, such as user dependency, time-consuming nature, and lack of sensitivity, thus paving the way for automated analysis approaches. Methods Hereby, three structurally different variations of U-net architectures based on convolutional neural networks (CNN) were implemented for the segmentation of in vitro wound healing microscopy images. The developed models were fed using two independent datasets after applying a novel augmentation method aimed at the more sensitive analysis of edges after the preprocessing. Then, predicted masks were utilized for the accurate calculation of wound areas. Eventually, the therapy efficacy-indicator wound areas were thoroughly compared with current well-known tools such as ImageJ and TScratch. Results The average dice similarity coefficient (DSC) scores were obtained as 0.958$$\sim$$ ∼ 0.968 for U-net-based deep learning models. The averaged absolute percentage errors (PE) of predicted wound areas to ground truth were 6.41%, 3.70%, and 3.73%, respectively for U-net, U-net++, and Attention U-net, while ImageJ and TScratch had considerable averaged error rates of 22.59% and 33.88%, respectively. Conclusions Comparative analyses revealed that the developed models outperformed the conventional approaches in terms of analysis time and segmentation sensitivity. The developed models also hold great promise for the prediction of the in vitro wound area, regardless of the therapy-of-interest, cell line, magnification of the microscope, or other application-dependent parameters.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

An automated in vitro wound healing microscopy image analysis approach utilizing U-net-based deep learning methodology

Doğru,

Özdemir,

Özdemir

et al. 2024

BMC Med Imaging

View full text Add to dashboard Cite

show abstract

“…There are many alternative machine and deep learning alternatives for segmentation 14 . However, the U-Net architecture has been used widely for a variety of applications 16 , 40 – 45 , as a de facto standard because it is well suited for analysis of grayscale biomedical images with features such as cells and nuclei. U-Net has well-documented instructions, can be implemented in ImageJ, and is easily trainable.…”

Section: Discussionmentioning

confidence: 99%

High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury

McElliott¹,

Al-Suraimi²,

Telang³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Recovery from acute kidney injury can vary widely in patients and in animal models. Immunofluorescence staining can provide spatial information about heterogeneous injury responses, but often only a fraction of stained tissue is analyzed. Deep learning can expand analysis to larger areas and sample numbers by substituting for time-intensive manual or semi-automated quantification techniques. Here we report one approach to leverage deep learning tools to quantify heterogenous responses to kidney injury that can be deployed without specialized equipment or programming expertise. We first demonstrated that deep learning models generated from small training sets accurately identified a range of stains and structures with performance similar to that of trained human observers. We then showed this approach accurately tracks the evolution of folic acid induced kidney injury in mice and highlights spatially clustered tubules that fail to repair. We then demonstrated that this approach captures the variation in recovery across a robust sample of kidneys after ischemic injury. Finally, we showed markers of failed repair after ischemic injury were correlated both spatially within and between animals and that failed repair was inversely correlated with peritubular capillary density. Combined, we demonstrate the utility and versatility of our approach to capture spatially heterogenous responses to kidney injury.

show abstract

“…On the DL side, Oldenburg et al developed a platform for living cell research that can conduct cell-and population-scale analyses using MATLAB-based DL techniques [45]. They introduced a system that can analyze cell mobility at both the cell and population scales by training a 3-layer U-net structure using a semi-automatic labeling method.…”

Section: Evaluating Implicationsmentioning

confidence: 99%

An automated in vitro wound healing microscopy image analysis approach utilizing U-net-based deep learning methodology

Dogru,

Ozdemir,

Ozdemir

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: The assessment of in vitro wound healing images is critical for determining the efficacy of the therapy-of-interest that may influence the wound healing process. Existing methods suffer significant limitations, such as their user dependency and time-consuming nature, and lack of sensitivity, and thus pave the way for automated analysis approaches. Methods: Hereby, three structurally different variations of U-net architectures based on convolutional neural networks (CNN) were implemented for the segmentation of in vitro wound healing microscopy images. Developed models were fed using two independent datasets after applying a novel augmentation method based aim at the more sensitive analysis of edges after the preprocessing. Then, predicted masks were utilized for the accurate calculation of wound areas. Eventually, the therapy efficacy-indicator wound areas were thoroughly compared with current well-known tools such as ImageJ and TScratch. Results: The average dice similarity coefficient (DSC) scores were obtained as 0.958∼0.968 for U-net-based deep learning models. The averaged absolute percentage errors of predicted wound areas to ground truth were 6.41%, 3.70%, and 3.73%, respectively for U-net, U-net++, and Attention U-net, while ImageJ and TScratch had huge averaged error rates of 22.59% and 33.88%, respectively. Conclusions: Comparative analyses revealed that the developed models outperformed the conventional approaches in terms of analysis time and segmentation sensitivity. The developed models hold also great promise for the prediction of the in vitro wound area regardless of the therapy-of-interest, cell line, magnification of the microscope, or other application-dependent parameters.

show abstract

Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB

Cited by 6 publications

References 36 publications

An automated in vitro wound healing microscopy image analysis approach utilizing U-net-based deep learning methodology

An automated in vitro wound healing microscopy image analysis approach utilizing U-net-based deep learning methodology

High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury

An automated in vitro wound healing microscopy image analysis approach utilizing U-net-based deep learning methodology

Contact Info

Product

Resources

About