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

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.

A proposed model of xeno-keratoplasty using 3D printing and decellularization

“…Hence, several methods are used in the corneal decellularization process ( Table 1 ; Figure 1 ) to adequately balance the removal the cellular and nuclear components of the tissue, and the retention of essential structural and bioactive ECM components that support graft develpoment ( Crapo et al, 2011 ; Wilson et al, 2013 ). Most of these techniques have been examined in bovine, ovine, and porcine corneas ( Gusnard and Kirschner, 1977 ; Amano et al, 2008 ; Wilson et al, 2013 ; Pantic I. V. et al, 2023 ; Khan et al, 2023 ; Wang et al, 2023 ). An overview of some commonly used approaches, which can be primarily classified as biological, chemical, and physical, for corneal decellularization and their effects on cellular and extracellular tissue constituents is presented below.…”

“…In comparison, bioartificial corneal scaffolds have been considered effective substitutes for reducing immunogenicity and enhancing compatibility and integration into the recipient ( Wilson et al, 2013 ; Pantic I. V. et al, 2023 ). As previously stated, the supply of human donor corneas is incapable of meeting existing and projected transplantation needs.…”

“…This characteristic supports its use for xenografting ( Cooper et al, 2007 ). Moreover, recent studies have revealed the potential to repurpose ( Dey et al, 2023 ) and generate a limitless supply of corneal xenografts using slaughterhouse waste ( Yoeruek et al, 2012a ; Yoeruek et al, 2012b ; Pantic I. V. et al, 2023 ; Khan et al, 2023 ; Wang et al, 2023 ). Based on this potential, we assessed current applications and performance in preclinical and clinical practices of various decellularization protocols used to create Kpros and their ability to maintain pertinent structural and physiological capacities.…”

Artificial intelligence strategies based on run length matrix and wavelet analyses for detection of subtle alterations in hepatocyte chromatin organization following exposure to iron oxide nanoparticles

“…Textural analysis of digital micrographs and the use of textural features for ML model training can be conducted in multiple ways. The conventional Gray-level Co-occurrence Matrix (GLCM) technique [7][8][9] is widely used to quantify cell and tissue parameters such as textural homogeneity based on inverse difference moment or textural uniformity based on angular second moment. Alternatively, and yet relatively uninvestigated, approaches to textural analysis of cell structure include Run Length Matrix analysis (RLM), which can be particularly useful for providing information on intensity and spatial relationships of micrograph components.…”

Oxidopamine-Induced Nuclear Alterations Quantified Using Advanced Fractal Analysis: Random Forest Machine Learning Approach

“…Random forest (RF) algorithms are particularly intriguing supervised learning ensemble methods that are today commonly used in medical data analysis due to their versatility and accuracy [8][9][10][11]. They combine information from a multitude of individual decision trees that are created to include a randomly chosen subset of a training data sample.…”