Analysis of Collagen Spatial Structure Using Multiphoton Microscopy and Machine Learning Methods

Machine Learning in Tissue Engineering

Machine learning (ML) and artificial intelligence have accelerated scientific discovery, augmented clinical practice, and deepened fundamental understanding of many biological phenomena. ML technologies have now been applied to diverse areas of tissue engineering research, including biomaterial design, scaffold fabrication, and cell/tissue modeling. Emerging ML-empowered strategies include machine-optimized polymer synthesis, predictive modeling of scaffold fabrication processes, complex analyses of structure-function relationships, and deep learning of spatialized cell phenotypes and tissue composition. The emergence of ML in tissue engineering, while relatively recent, has already enabled increasingly complex and multivariate analyses of the relationships between biological, chemical, and physical factors in driving tissue regenerative outcomes. This review highlights the novel methodologies, emerging strategies, and areas of potential growth within this rapidly evolving area of research. Impact statement Machine learning (ML) has accelerated scientific discovery and augmented clinical practice across multiple fields. Now, ML has driven exciting new paradigms in tissue engineering research, including machine-optimized biomaterial design, predictive modeling of scaffold fabrication, and spatiotemporal analysis of cell and tissue systems. The emergence of ML in tissue engineering, while relatively recent, has already enabled increasingly complex analyses of the relationships between biological, chemical, and physical factors in driving tissue regenerative outcomes. This review highlights the novel methodologies, emerging strategies, and areas of potential growth within this rapidly evolving area of research.

Extracellular matrix mechanobiology in cancer cell migration

The extracellular matrix (ECM) is pivotal in modulating tumor progression. Besides chemically stimulating tumor cells, it also offers physical support that orchestrates the sequence of events in the metastatic cascade upon dynamically modulating cell mechanosensation. Understanding this translation between matrix biophysical cues and intracellular signaling has led to rapid growth in the interdisciplinary field of cancer mechanobiology in the last decade. Substantial efforts have been made to develop novel in vitro tumor mimicking platforms to visualize and quantify the mechanical forces within the tissue that dictate tumor cell invasion and metastatic growth. This review highlights recent findings on tumor matrix biophysical cues such as fibrillar arrangement, crosslinking density, confinement, rigidity, topography, and non-linear mechanics and their implications on tumor cell behavior. We also emphasize how perturbations in these cues alter cellular mechanisms of mechanotransduction, consequently enhancing malignancy. Finally, we elucidate engineering techniques to individually emulate the mechanical properties of tumors that could help serve as toolkits for developing and testing ECM-targeted therapeutics on novel bioengineered tumor platforms. STATEMENT OF SIGNIFICANCE: Disrupted ECM mechanics is a driving force for transitioning incipient cells to life-threatening malignant variants. Understanding these ECM changes can be crucial as they may aid in developing several efficacious drugs that not only focus on inducing cytotoxic effects but also target specific matrix mechanical cues that support and enhance tumor invasiveness. Designing and implementing an optimal tumor mimic can allow us to predictively map biophysical cue-modulated cell behaviors and facilitate the design of improved lab-grown tumor models with accurately controlled structural features. This review focuses on the abnormal changes within the ECM during tumorigenesis and its implications on tumor cell-matrix mechanoreciprocity. Additionally, it accentuates engineering approaches to produce ECM features of varying levels of complexity which is critical for improving the efficiency of current engineered tumor tissue models.

Machine learning approaches for biomolecular, biophysical, and biomaterials research

A fluent conversation with a virtual assistant, person-tailored news feeds, and deep-fake images created within seconds-all those things that have been unthinkable for a long time are now a part of our everyday lives. What these examples have in common is that they are realized by different means of machine learning (ML), a technology that has fundamentally changed many aspects of the modern world. The possibility to process enormous amount of data in multi-hierarchical, digital constructs has paved the way not only for creating intelligent systems but also for obtaining surprising new insight into many scientific problems. However, in the different areas of biosciences, which typically rely heavily on the collection of time-consuming experimental data, applying ML methods is a bit more challenging: Here, difficulties can arise from small datasets and the inherent, broad variability, and complexity associated with studying biological objects and phenomena. In this Review, we give an overview of commonly used ML algorithms (which are often referred to as "machines") and learning strategies as well as their applications in different bio-disciplines such as molecular biology, drug development, biophysics, and biomaterials science. We highlight how selected research questions from those fields were successfully translated into machine readable formats, discuss typical problems that can arise in this context, and provide an overview of how to resolve those encountered difficulties.

Multi-photon microscopy for the evaluation of interstitial fibrosis in extended criteria donor kidneys: A Proof-of-Concept Study

INTRODUCTION

To evaluate the initial use of label-free second harmonic generation (SHG) imaging with two-photon excitation (2PE) auto-fluorescence in multi-photon microscopy (MPM) for the quantification of collagen/fibrosis on pre-implantation biopsies of extended criteria donors (ECD).

MATERIALS AND METHODS

20 pre-implantation core biopsies were extracted from 10 donor kidney samples, of which originated from 7 donors. Kidney Donor Profile Index (KDPI) and Remuzzi scores of biopsies were calculated. Collagen parameters measured included quantification by the Collagen Area Ratio in Total Tissue (CART) and qualitative measurements by Collagen Reticulation Index (CRI).

RESULTS

Biopsies classified with > 85% KDPI scores had significantly higher CART (p = 0.011) and lower CRI values (p = 0.025) than biopsies with ≤ 85% KDPI scores. Increase in CRI values correlated significantly with rise in recipient creatinine levels 1-year post-transplant (p = 0.027; 95% CI: 4.635-66.797).

CONCLUSION

MPM is an evolving technology that enables the quantification of the amount (CART) and quality (CRI) of collagen deposition in unstained pre-implantation biopsies of donor kidneys stratified by KDPI scores. This initial evaluation found significant differences in both parameters between donor kidneys with more or less than 85% KDPI. This article is protected by copyright. All rights reserved.

Multiphoton microscopy providing pathological-level quantification of myocardial fibrosis in transplanted human heart

Multiphoton microscopy (MPM), a high-resolution laser scanning technique, has been shown to provide detailed real-time information on fibrosis assessment in animal models. But the value of MPM in human histology, especially in heart tissue, has not been fully explored. We aimed to evaluate the association between myocardial fibrosis measured by MPM and that measured by histological staining in the transplanted human heart. One hundred and twenty samples of heart tissue were obtained from 20 patients consisting of 10 dilated cardiomyopathies (DCM) and 10 ischemic cardiomyopathies (ICM). MPM and picrosirius red staining were performed to quantify collagen volume fraction (CVF) in explanted hearts postoperatively. Cardiomyocyte and myocardial fibrosis could be clearly visualized by MPM. Although patients with ICM had significantly greater MPM-derived CVF than patients with DCM (25.33  ± 12.65 % vs. 19.82  ± 8.62 %, p = 0.006), there was a substantial overlap of CVF values between them. MPM-derived CVF was comparable to that derived from picrosirius red staining based on all samples (22.58 ± 11.13% vs. 21.19 ± 11.79%, p = 0.348), as well as in DCM samples and ICM samples. MPM-derived CVF was correlated strongly with the magnitude of staining-derived CVF in both all samples and DCM samples and ICM samples (r = 0.972, r = 0.963, r = 0.973, respectively; all p < 0.001). Intra- and inter-observer reproducibility for MPM-derived CVF and staining-derived CVF were 0.995, 0.989, 0.995, and 0.985, respectively. Our data demonstrated that MPM can provide a pathological-level assessment of myocardial microstructure in transplanted human heart.

Xenoimplant of Collagen Matrix Scaffold in Liver Tissue as a Niche for Liver Cells

Hepatitis C virus-induced liver damage, chronic liver damage due to alcohol, and non-alcoholic liver disease-induced cellular alterations promote fibrosis, cirrhosis, and/or hepatocellular carcinoma. The recommended therapeutic option for advanced liver damage is liver transplantation. Extracellular matrix scaffolds have been evaluated as an alternative for tissue restoration. Studies on the biocompatibility and rejection of synthetic and natural scaffolds as an alternative to organ transplantation have been evaluated. Our group has recently described the xenoimplant of collagen matrix scaffold (CMS) in a rat model. However, no complete macroscopic and histological description of the liver parenchyma at the initial (day 3), intermediate (day 14), and advanced (day 21) stages has been obtained. In this study, we described and compared liver tissue from the CMS zone (CZ, CMS, and liver parenchyma), liver tissue from the normal zone (liver parenchyma close to the CMS), and basal tissue (resected tissue from the CMS implantation site). Our data strongly suggest that the collagen matrix xenoimplant is a good niche for hepatocytes, with no rejection, and does not affect liver function tests. The liver can regenerate after damage, but this capacity is inhibited in a chronic injury. At present, the use of CMS after liver damage has not been reported. This biomaterial could be a novel alternative in the field of regenerative medicine for liver diseases.

In Vivo Quantification of the Effectiveness of Topical Low-Dose Photodynamic Therapy in Wound Healing Using Two-Photon Microscopy

The effect of low-dose photodynamic therapy on in vivo wound healing with topical application of 5-aminolevulinic acid and methylene blue was investigated using an animal model for two laser radiation doses (1 and 4 J/cm2). A second-harmonic-generation-to-auto-fluorescence aging index of the dermis (SAAID) was analyzed by two-photon microscopy. SAAID measured at 60-80 μm depths was shown to be a suitable quantitative parameter to monitor wound healing. A comparison of SAAID in healthy and wound tissues during phototherapy showed that both light doses were effective for wound healing; however, healing was better at a dose of 4 J/cm2.

Method for measurement of collagen monomer orientation in fluorescence microscopy

SIGNIFICANCE

Collagen is the most abundant protein in vertebrates and is found in tissues that regularly experience tension, compression, and shear forces. However, the underlying mechanism of collagen fibril formation and remodeling is poorly understood.

AIM

We explore how a collagen monomer is visualized using fluorescence microscopy and how its spatial orientation is determined. Defining the orientation of collagen monomers is not a trivial problem, as the monomer has a weak contrast and is relatively small. It is possible to attach fluorescence tags for contrast, but the size is still a problem for detecting orientation using fluorescence microscopy.

APPROACH

We present two methods for detecting a monomer and classifying its orientation. A modified Gabor filter set and an automatic classifier trained by convolutional neural network based on a synthetic dataset were used.

RESULTS

By evaluating the performance of these two approaches with synthetic and experimental data, our results show that it is possible to determine the location and orientation with an error of ∼37  deg of a single monomer with fluorescence microscopy.

CONCLUSIONS

These findings can contribute to our understanding of collagen monomers interaction with collagen fibrils surface during fibril formation and remodeling.

Dual-LC PSHG microscopy for imaging collagen type I and type II gels with pixel-resolution analysis

Collagen of type I (Col I) and type II (Col II) are critical for cartilage and connective tissues in the human body, and several diseases may alter their properties. Assessing the identification and quantification of fibrillar collagen without biomarkers is a challenge. Advancements in non-invasive polarization-resolved second-harmonic generation (PSHG) microscopy have provided a method for the non-destructive investigation of collagen molecular level properties. Here we explored an alternative polarization modulated approach, dual-LC PSHG, that is based on two liquid crystal devices (Liquid crystal polarization rotators, LPRs) operating simultaneously with a laser scanning SHG microscope. We demonstrated that this more accessible technology allows the quick and accurate generation of any desired linear and circular polarization state without any mechanical parts. This study demonstrates that this method can aid in improving the ability to quantify the characteristics of both types of collagen, including pitch angle, anisotropy, and circular dichroism analysis. Using this approach, we estimated the effective pitch angle for Col I and Col II to be 49.7° and 51.6°, respectively. The effective peptide pitch angle for Col II gel was first estimated and is similar to the value obtained for Col I gel in the previous studies. Additionally, the difference of the anisotropy parameter of both collagen type gels was assessed to be 0.293, which reflects the different type molecular fibril assembly. Further, our work suggests a potential method for monitoring and differentiating different collagen types in biological tissues, especially cartilage or connective tissue.

Decoding Optical Data with Machine Learning

Optical spectroscopy and imaging techniques play important roles in many fields such as disease diagnosis, biological study, information technology, optical science, and materials science. Over the past decade, machine learning (ML) has proved promising in decoding complex data, enabling rapid and accurate analysis of optical spectra and images. This review aims to shed light on various ML algorithms for optical data analysis with a focus on their applications in a wide range of fields. The goal of this work is to sketch the validity of ML-based optical data decoding. The review concludes with an outlook on unaddressed problems and opportunities in this emerging subject that interfaces optics, data science and ML.

Engineering Tissue Fabrication With Machine Intelligence: Generating a Blueprint for Regeneration

Regenerating lost or damaged tissue is the primary goal of Tissue Engineering. 3D bioprinting technologies have been widely applied in many research areas of tissue regeneration and disease modeling with unprecedented spatial resolution and tissue-like complexity. However, the extraction of tissue architecture and the generation of high-resolution blueprints are challenging tasks for tissue regeneration. Traditionally, such spatial information is obtained from a collection of microscopic images and then combined together to visualize regions of interest. To fabricate such engineered tissues, rendered microscopic images are transformed to code to inform a 3D bioprinting process. If this process is augmented with data-driven approaches and streamlined with machine intelligence, identification of an optimal blueprint can become an achievable task for functional tissue regeneration. In this review, our perspective is guided by an emerging paradigm to generate a blueprint for regeneration with machine intelligence. First, we reviewed recent articles with respect to our perspective for machine intelligence-driven information retrieval and fabrication. After briefly introducing recent trends in information retrieval methods from publicly available data, our discussion is focused on recent works that use machine intelligence to discover tissue architectures from imaging and spectral data. Then, our focus is on utilizing optimization approaches to increase print fidelity and enhance biomimicry with machine learning (ML) strategies to acquire a blueprint ready for 3D bioprinting.

Application of multiphoton imaging and machine learning to lymphedema tissue analysis

The results of in-vivo two-photon imaging of lymphedema tissue are presented. The study involved 36 image samples from II stage lymphedema patients and 42 image samples from healthy volunteers. The papillary layer of the skin with a penetration depth of about 100 μm was examined. Both the collagen network disorganization and increase of the collagen/elastin ratio in lymphedema tissue, characterizing the severity of fibrosis, was observed. Various methods of image characterization, including edge detectors, a histogram of oriented gradients method, and a predictive model for diagnosis using machine learning, were used. The classification by "ensemble learning" provided 96% accuracy in validating the data from the testing set.