Computational approaches for evaluating morphological changes in the corneal stroma associated with decellularization

doi:10.3389/fbioe.2023.1105377

. 2023 May 26:11:1105377.

doi: 10.3389/fbioe.2023.1105377. eCollection 2023.

Computational approaches for evaluating morphological changes in the corneal stroma associated with decellularization

Igor V Pantic^{1

2

3

4}, Jelena Cumic⁵, Svetlana Valjarevic⁶, Adeeba Shakeel⁷, Xinyu Wang^{7

8}, Hema Vurivi⁹, Sayel Daoud¹⁰, Vincent Chan⁸, Georg A Petroianu⁴, Meklit G Shibru⁷, Zehara M Ali⁷, Dejan Nesic¹, Ahmed E Salih¹¹, Haider Butt¹¹, Peter R Corridon^{7

8

9}

Affiliations

¹ Department of Medical Physiology, Faculty of Medicine, Visegradska 26/II, University of Belgrade, Belgrade, Serbia.
² University of Haifa, Haifa, Israel.
³ Department of Physiology and Cell Biology, Faculty of Health Sciences, Ben-Gurion University of the Negev, Be'er Sheva, Israel.
⁴ Department of Pharmacology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
⁵ Faculty of Medicine, University of Belgrade, University Clinical Center of Serbia, Belgrade, Serbia.
⁶ Faculty of Medicine, Clinical Hospital Center Zemun, University of Belgrade, Belgrade, Serbia.
⁷ Department of Immunology and Physiology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
⁸ Biomedical Engineering, Healthcare Engineering Innovation Center, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
⁹ Center for Biotechnology, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
¹⁰ Anatomical Pathology Laboratory, Cleveland Clinic Abu Dhabi, Abu Dhabi, United Arab Emirates.
¹¹ Department of Mechanical Engineering, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.

PMID: 37304146
PMCID: PMC10250676
DOI: 10.3389/fbioe.2023.1105377

Computational approaches for evaluating morphological changes in the corneal stroma associated with decellularization

Igor V Pantic et al. Front Bioeng Biotechnol. 2023.

. 2023 May 26:11:1105377.

doi: 10.3389/fbioe.2023.1105377. eCollection 2023.

Authors

Affiliations

¹ Department of Medical Physiology, Faculty of Medicine, Visegradska 26/II, University of Belgrade, Belgrade, Serbia.
² University of Haifa, Haifa, Israel.
³ Department of Physiology and Cell Biology, Faculty of Health Sciences, Ben-Gurion University of the Negev, Be'er Sheva, Israel.
⁴ Department of Pharmacology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
⁵ Faculty of Medicine, University of Belgrade, University Clinical Center of Serbia, Belgrade, Serbia.
⁶ Faculty of Medicine, Clinical Hospital Center Zemun, University of Belgrade, Belgrade, Serbia.
⁷ Department of Immunology and Physiology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
⁸ Biomedical Engineering, Healthcare Engineering Innovation Center, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
⁹ Center for Biotechnology, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
¹⁰ Anatomical Pathology Laboratory, Cleveland Clinic Abu Dhabi, Abu Dhabi, United Arab Emirates.
¹¹ Department of Mechanical Engineering, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.

PMID: 37304146
PMCID: PMC10250676
DOI: 10.3389/fbioe.2023.1105377

Abstract

Decellularized corneas offer a promising and sustainable source of replacement grafts, mimicking native tissue and reducing the risk of immune rejection post-transplantation. Despite great success in achieving acellular scaffolds, little consensus exists regarding the quality of the decellularized extracellular matrix. Metrics used to evaluate extracellular matrix performance are study-specific, subjective, and semi-quantitative. Thus, this work focused on developing a computational method to examine the effectiveness of corneal decellularization. We combined conventional semi-quantitative histological assessments and automated scaffold evaluations based on textual image analyses to assess decellularization efficiency. Our study highlights that it is possible to develop contemporary machine learning (ML) models based on random forests and support vector machine algorithms, which can identify regions of interest in acellularized corneal stromal tissue with relatively high accuracy. These results provide a platform for developing machine learning biosensing systems for evaluating subtle morphological changes in decellularized scaffolds, which are crucial for assessing their functionality.

Keywords: GLCM (gray level co-event matrix); cornea; corneal stroma; decellualrization; keratocytes.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

**FIGURE 1**
Example of Mazda user interface with a digital micrograph of native cornea. The micrographs were converted to grayscale BMP format for ROI creation and subsequent GLCM and DWT analyses.

**FIGURE 2**
Light transmittance through native and decellularized corneas. Comparison of DNA contents in native and acellular corneas. Residual DNA contents estimated in scaffolds produced from each decellularization condition significantly differed from the DNA contents in the native corneas. The p values are based on the Kruskal–Wallis test that identified the difference among the groups (p < 0.002), and pairwise group comparisons generated using the Dunn’s *post hoc* test highlight the significant difference between the native DNA concentration and DNA concentration retained after each decellularization approach (**), before and after the Bonferroni correction.

**FIGURE 3**
Digital images and brightfield 10X micrographs of native and decellularized ovine corneas. Digital images of an extracted **(A)** native cornea (group 1), **(B)** cornea decellularized using 1% biosurfactant for 2 days (group 1), **(C)** cornea decellularized using 1% biosurfactant for 4 days (group 1), **(D)** cornea decellularized using 1% biosurfactant for 2 days (group 1). Brightfield 10X micrographs obtained from an extracted **(A)** native cornea (group 1), **(B)** cornea decellularized using 1% biosurfactant for 2 days (group 1), **(C)** cornea decellularized using 1% biosurfactant for 4 days (group 1), **(D)** cornea decellularized using 1% biosurfactant for 2 days (group 1). The epithelium, Bowman’s membrane, and stroma (specifically with the presence of keratocytes identified by the arrows) are clearly defined in native tissues compared to the decellularized scaffolds. Scale bars = 20 μm. Digital images and brightfield 10X micrographs using 1% biosurfactant for 2 days (group 2), **(C)** cornea and **(E)** cornea decellularized using 4% biosurfactant using 1% biosurfactant for 2 days (group 2), **(H)** cornea and **(J)** cornea decellularized using 4% biosurfactant the arrows) are clearly defined in native tissues compared.

**FIGURE 4**
Histological assessments identifying morphological fiber misalignment and damage that resulted from decellularization.

**FIGURE 5**
GLCM indicators for native corneas and scaffolds created using various decellularization conditions. **p < 0.01 compared to controls.

**FIGURE 6**
Mean values of discrete wavelet transform coefficient energies. **p < 0.01.

**FIGURE 7**
Receiver operating characteristics curves for SVM and RF ML models.

See this image and copyright information in PMC

Cited by

A proposed model of xeno-keratoplasty using 3D printing and decellularization.
Wang X, Elbahrawi RT, Abdukadir AM, Ali ZM, Chan V, Corridon PR. Wang X, et al. Front Pharmacol. 2023 Sep 20;14:1193606. doi: 10.3389/fphar.2023.1193606. eCollection 2023. Front Pharmacol. 2023. PMID: 37799970 Free PMC article.
Integrated environmental and health economic assessments of novel xeno-keratografts addressing a growing public health crisis.
Ali M, Corridon PR. Ali M, et al. Sci Rep. 2024 Oct 27;14(1):25600. doi: 10.1038/s41598-024-77783-y. Sci Rep. 2024. PMID: 39465317 Free PMC article.
Enhancing the expression of a key mitochondrial enzyme at the inception of ischemia-reperfusion injury can boost recovery and halt the progression of acute kidney injury.
Corridon PR. Corridon PR. Front Physiol. 2023 Feb 8;14:1024238. doi: 10.3389/fphys.2023.1024238. eCollection 2023. Front Physiol. 2023. PMID: 36846323 Free PMC article.
Capturing effects of blood flow on the transplanted decellularized nephron with intravital microscopy.
Corridon PR. Corridon PR. Sci Rep. 2023 Mar 31;13(1):5289. doi: 10.1038/s41598-023-31747-w. Sci Rep. 2023. PMID: 37002341 Free PMC article.
Machine learning approaches to detect hepatocyte chromatin alterations from iron oxide nanoparticle exposure.
Paunovic Pantic J, Vucevic D, Radosavljevic T, Corridon PR, Valjarevic S, Cumic J, Bojic L, Pantic I. Paunovic Pantic J, et al. Sci Rep. 2024 Aug 23;14(1):19595. doi: 10.1038/s41598-024-70559-4. Sci Rep. 2024. PMID: 39179629 Free PMC article.

See all "Cited by" articles

References

1. Abassi Z., Shalabi A., Sohotnik R., Nativ O., Awad H., Bishara B., et al. (2013). Urinary NGAL and KIM-1: Biomarkers for assessment of acute ischemic kidney injury following nephron sparing surgery. J. Urol. 189, 1559–1566. 10.1016/j.juro.2012.10.029 - DOI - PubMed
1. Adankon M.M., Cheriet M. (2015). Support Vector Machine. In: Li, S.Z., Jain, A.K. (eds) Encyclopedia of Biometrics. Springer, Boston, MA. 10.1007/978-1-4899-7488-4_29 - DOI
1. Ahearne M. (2020). Corneal extracellular matrix decellularization. Methods Cell Biol. 157, 81–95. 10.1016/bs.mcb.2019.10.013 - DOI - PubMed
1. Aldrovani M., Guaraldo A. M. A., Vidal B. C. (2007). Optical anisotropies in corneal stroma collagen fibers from diabetic spontaneous mice. Vis. Res. 47, 3229–3237. 10.1016/j.visres.2007.02.011 - DOI - PubMed
1. Bochert R., Zhivov A., Kraak R., Stave J., Guthoff R. (2005). Contribution to comprehension of image formation in confocal microscopy of cornea with Rostock cornea module. Br. J. Ophthalmol. 89, 1351–1355. 10.1136/bjo.2004.063743 - DOI - PMC - PubMed

LinkOut - more resources

Full Text Sources

[1] Abassi Z., Shalabi A., Sohotnik R., Nativ O., Awad H., Bishara B., et al. (2013). Urinary NGAL and KIM-1: Biomarkers for assessment of acute ischemic kidney injury following nephron sparing surgery. J. Urol. 189, 1559–1566. 10.1016/j.juro.2012.10.029 - DOI - PubMed

[2] Abassi Z., Shalabi A., Sohotnik R., Nativ O., Awad H., Bishara B., et al. (2013). Urinary NGAL and KIM-1: Biomarkers for assessment of acute ischemic kidney injury following nephron sparing surgery. J. Urol. 189, 1559–1566. 10.1016/j.juro.2012.10.029 - DOI - PubMed

[3] Adankon M.M., Cheriet M. (2015). Support Vector Machine. In: Li, S.Z., Jain, A.K. (eds) Encyclopedia of Biometrics. Springer, Boston, MA. 10.1007/978-1-4899-7488-4_29 - DOI

[4] Adankon M.M., Cheriet M. (2015). Support Vector Machine. In: Li, S.Z., Jain, A.K. (eds) Encyclopedia of Biometrics. Springer, Boston, MA. 10.1007/978-1-4899-7488-4_29 - DOI

[5] Ahearne M. (2020). Corneal extracellular matrix decellularization. Methods Cell Biol. 157, 81–95. 10.1016/bs.mcb.2019.10.013 - DOI - PubMed

[6] Ahearne M. (2020). Corneal extracellular matrix decellularization. Methods Cell Biol. 157, 81–95. 10.1016/bs.mcb.2019.10.013 - DOI - PubMed

[7] Aldrovani M., Guaraldo A. M. A., Vidal B. C. (2007). Optical anisotropies in corneal stroma collagen fibers from diabetic spontaneous mice. Vis. Res. 47, 3229–3237. 10.1016/j.visres.2007.02.011 - DOI - PubMed

[8] Aldrovani M., Guaraldo A. M. A., Vidal B. C. (2007). Optical anisotropies in corneal stroma collagen fibers from diabetic spontaneous mice. Vis. Res. 47, 3229–3237. 10.1016/j.visres.2007.02.011 - DOI - PubMed

[9] Bochert R., Zhivov A., Kraak R., Stave J., Guthoff R. (2005). Contribution to comprehension of image formation in confocal microscopy of cornea with Rostock cornea module. Br. J. Ophthalmol. 89, 1351–1355. 10.1136/bjo.2004.063743 - DOI - PMC - PubMed

[10] Bochert R., Zhivov A., Kraak R., Stave J., Guthoff R. (2005). Contribution to comprehension of image formation in confocal microscopy of cornea with Rostock cornea module. Br. J. Ophthalmol. 89, 1351–1355. 10.1136/bjo.2004.063743 - DOI - PMC - PubMed

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Computational approaches for evaluating morphological changes in the corneal stroma associated with decellularization

Affiliations

Computational approaches for evaluating morphological changes in the corneal stroma associated with decellularization

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

Similar articles

Cited by

References

LinkOut - more resources

Full Text Sources