Label-free quality control and identification of human keratinocyte stem cells by deep learning-based automated cell tracking

The Recovery of Epidermal Proliferation Pattern in Human Skin Xenograft

Abnormalities in epidermal keratinocyte proliferation are a characteristic feature of a range of dermatological conditions. These include hyperproliferative states in psoriasis and dermatitis as well as hypoproliferative states in chronic wounds. This emphasises the importance of investigating the proliferation kinetics under conditions of healthy skin and identifying the key regulators of epidermal homeostasis, maintenance, and recovery following wound healing. Animal models contribute to our understanding of human epidermal self-renewal. Human skin xenografting overcomes the ethical limitations of studying human skin during regeneration. The application of this approach has allowed for the identification of a single population of stem cells and both slowly and rapidly cycling progenitors within the epidermal basal layer and the mapping of their location in relation to rete ridges and hair follicles. Furthermore, we have traced the dynamics of the proliferation pattern reorganization that occurs during epidermal regeneration, underlining the role of YAP activity in epidermal relief formation.

Current status, challenges, and prospects of artificial intelligence applications in wound repair theranostics

Skin injuries caused by physical, pathological, and chemical factors not only compromise appearance and barrier function but can also lead to life-threatening microbial infections, posing significant challenges for patients and healthcare systems. Artificial intelligence (AI) technology has demonstrated substantial advantages in processing and analyzing image information. Recently, AI-based methods and algorithms, including machine learning, deep learning, and neural networks, have been extensively explored in wound care and research, providing effective clinical decision support for wound diagnosis, treatment, prognosis, and rehabilitation. However, challenges remain in achieving a closed-loop care system for the comprehensive application of AI in wound management, encompassing wound diagnosis, monitoring, and treatment. This review comprehensively summarizes recent advancements in AI applications in wound repair. Specifically, it discusses AI's role in injury type classification, wound measurement (including area and depth), wound tissue type classification, wound monitoring and prediction, and personalized treatment. Additionally, the review addresses the challenges and limitations AI faces in wound management. Finally, recommendations for the application of AI in wound repair are proposed, along with an outlook on future research directions, aiming to provide scientific evidence and technological support for further advancements in AI-driven wound repair theranostics.

Regenerative rehabilitation: a novel multidisciplinary field to maximize patient outcomes

Regenerative rehabilitation is a novel and rapidly developing multidisciplinary field that converges regenerative medicine and rehabilitation science, aiming to maximize the functions of disabled patients and their independence. While regenerative medicine provides state-of-the-art technologies that shed light on difficult-to-treated diseases, regenerative rehabilitation offers rehabilitation interventions to improve the positive effects of regenerative medicine. However, regenerative scientists and rehabilitation professionals focus on their aspects without enough exposure to advances in each other's field. This disconnect has impeded the development of this field. Therefore, this review first introduces cutting-edge technologies such as stem cell technology, tissue engineering, biomaterial science, gene editing, and computer sciences that promote the progress pace of regenerative medicine, followed by a summary of preclinical studies and examples of clinical investigations that integrate rehabilitative methodologies into regenerative medicine. Then, challenges in this field are discussed, and possible solutions are provided for future directions. We aim to provide a platform for regenerative and rehabilitative professionals and clinicians in other areas to better understand the progress of regenerative rehabilitation, thus contributing to the clinical translation and management of innovative and reliable therapies.

Epidermal stem cells: skin surveillance and clinical perspective

The skin epidermis is continually influenced by a myriad of internal and external elements. At its basal layer reside epidermal stem cells, which fuels epidermal renovation and hair regeneration with powerful self-renewal ability, as well as keeping diverse signals that direct their activity under surveillance with quick response. The importance of epidermal stem cells in wound healing and immune-related skin conditions has been increasingly recognized, and their potential for clinical applications is attracting attention. In this review, we delve into recent advancements and the various physiological and psychological factors that govern distinct epidermal stem cell populations, including psychological stress, mechanical forces, chronic aging, and circadian rhythm, as well as providing an overview of current methodological approaches. Furthermore, we discuss the pathogenic role of epidermal stem cells in immune-related skin disorders and their potential clinical applications.

Artificial Intelligence Supports Automated Characterization of Differentiated Human Pluripotent Stem Cells

Revolutionary advances in AI and deep learning in recent years have resulted in an upsurge of papers exploring applications within the biomedical field. Within stem cell research, promising results have been reported from analyses of microscopy images to, that is, distinguish between pluripotent stem cells and differentiated cell types derived from stem cells. In this work, we investigated the possibility of using a deep learning model to predict the differentiation stage of pluripotent stem cells undergoing differentiation toward hepatocytes, based on morphological features of cell cultures. We were able to achieve close to perfect classification of images from early and late time points during differentiation, and this aligned very well with the experimental validation of cell identity and function. Our results suggest that deep learning models can distinguish between different cell morphologies, and provide alternative means of semi-automated functional characterization of stem cell cultures.

Differentiable optimization layers enhance GNN-based mitosis detection

Automatic mitosis detection from video is an essential step in analyzing proliferative behaviour of cells. In existing studies, a conventional object detector such as Unet is combined with a link prediction algorithm to find correspondences between parent and daughter cells. However, they do not take into account the biological constraint that a cell in a frame can correspond to up to two cells in the next frame. Our model called GNN-DOL enables mitosis detection by complementing a graph neural network (GNN) with a differentiable optimization layer (DOL) that implements the constraint. In time-lapse microscopy sequences cultured under four different conditions, we observed that the layer substantially improved detection performance in comparison with GNN-based link prediction. Our results illustrate the importance of incorporating biological knowledge explicitly into deep learning models.

Blank Spots in the Map of Human Skin: The Challenge for Xenotransplantation

Most of the knowledge about human skin homeostasis, development, wound healing, and diseases has been accumulated from human skin biopsy analysis by transferring from animal models and using different culture systems. Human-to-mouse xenografting is one of the fundamental approaches that allows the skin to be studied in vivo and evaluate the ongoing physiological processes in real time. Humanized animals permit the actual techniques for tracing cell fate, clonal analysis, genetic modifications, and drug discovery that could never be employed in humans. This review recapitulates the novel facts about mouse skin self-renewing, regeneration, and pathology, raises issues regarding the gaps in our understanding of the same options in human skin, and postulates the challenges for human skin xenografting.

Implementation of transfer learning for the segmentation of human mesenchymal stem cells-A validation study

INTRODUCTION

Stem cell therapy has been gaining interest in the regeneration rather than repair of lost human tissues. However, the manual analysis of stem cells prior to implantation is a cumbersome task that can be automated to improve the efficiency and accuracy of this process.

OBJECTIVE

To develop a Deep Learning (DL) algorithm for segmentation of human mesenchymal stem cells (MSCs) on micrographic images and to validate its performance relative to the ground truth laid down via annotation.

METHODOLOGY

Pre-trained DeepLab algorithms were trained on annotated images of human MSCs obtained from the open-source EVICAN dataset. This dataset comprises of partially annotated images; a limitation that is overcome by blurring backgrounds of these images which consequently blurs the unannotated cells. Two algorithms were trained on the two different kinds of images from this dataset; with blurred and normal backgrounds, respectively. Algorithm 1 was trained on 139 images with blurred backgrounds and algorithm 2 was trained on 37 images from the same dataset with normal backgrounds to replicate real-life scenarios.

RESULTS

The performance metrics of algorithm 1 included accuracy of 99.22%, dice co-efficient of 99.66% and Intersection over Union (IoU) score of 0.84. Algorithm 2 was 96.34% accurate with dice co-efficient and IoU scores of 98.39% and 0.48, respectively.

CONCLUSION

Both algorithms showed adequate performance in the segmentation of human MSCs with performance metrics close to the ground truth. However, algorithm 2 has better clinical applicability, even with smaller dataset and relatively lower performance metrics.

Engineered biomaterials in stem cell-based regenerative medicine

Stem cell-based regenerative therapies, which harness the self-renewal and differentiation properties of stem cells, have been in the spotlight due to their widespread applications in treating degenerative, aging, and other, generally intractable diseases. Therapeutically effective hematopoietic stem cells, mesenchymal stem cells, embryonic stem cells, and induced pluripotent stem cells have been used in numerous basic and translational studies with exciting results. However, pre-/post-transplantation issues of poor cell survival and retention, uncontrolled differentiation, and insufficient numbers of cells engrafted into host tissues are the major challenges in stem cell-based regenerative therapies. Engineered biomaterials have adjustable biochemical and biophysical properties that significantly affect cell behaviors, such as cell engraftment, survival, migration, and differentiation outcomes, thereby enhancing the engraftment of implanted stem cells and guiding tissue regeneration. Therefore, the combination of stem cell biology with bioengineered materials is a promising strategy to improve the therapeutic outcomes of stem cell-based regenerative therapy. In this review, we summarize the advances in the modulation of behaviors of stem cells via engineered biomaterials. We then present different approaches to harnessing bioengineered materials to enhance the transplantation of stem cells. Finally, we will provide future directions in regenerative therapy using stem cells.

Deep Learning of Phase-Contrast Images of Cancer Stem Cells Using a Selected Dataset of High Accuracy Value Using Conditional Generative Adversarial Networks

Artificial intelligence (AI) technology for image recognition has the potential to identify cancer stem cells (CSCs) in cultures and tissues. CSCs play an important role in the development and relapse of tumors. Although the characteristics of CSCs have been extensively studied, their morphological features remain elusive. The attempt to obtain an AI model identifying CSCs in culture showed the importance of images from spatially and temporally grown cultures of CSCs for deep learning to improve accuracy, but was insufficient. This study aimed to identify a process that is significantly efficient in increasing the accuracy values of the AI model output for predicting CSCs from phase-contrast images. An AI model of conditional generative adversarial network (CGAN) image translation for CSC identification predicted CSCs with various accuracy levels, and convolutional neural network classification of CSC phase-contrast images showed variation in the images. The accuracy of the AI model of CGAN image translation was increased by the AI model built by deep learning of selected CSC images with high accuracy previously calculated by another AI model. The workflow of building an AI model based on CGAN image translation could be useful for the AI prediction of CSCs.

Label-free biological sample detection and non-contact separation system based on microfluidic chip

The detection and separation of biological samples are of great significance for achieving accurate diagnoses and state assessments. Currently, the detection and separation of cells mostly adopt labeling methods, which will undoubtedly affect the original physiological state and functions of cells. Therefore, in this study, a label-free cell detection method based on microfluidic chips is proposed. By measuring the scattering of cells to identify cells and then using optical tweezers to separate the target cells, the whole process without any labeling and physical contact could realize automatic cell identification and separation. Different concentrations of 15 µm polystyrene microspheres and yeast mixed solution are used as samples for detection and separation. The detection accuracy is over 90%, and the separation accuracy is over 73%.

EGFR-mediated epidermal stem cell motility drives skin regeneration through COL17A1 proteolysis

Skin regenerative capacity declines with age, but the underlying mechanisms are largely unknown. Here we demonstrate a functional link between epidermal growth factor receptor (EGFR) signaling and type XVII collagen (COL17A1) proteolysis on age-associated alteration of keratinocyte stem cell dynamics in skin regeneration. Live-imaging and computer simulation experiments predicted that human keratinocyte stem cell motility is coupled with self-renewal and epidermal regeneration. Receptor tyrosine kinase array identified the age-associated decline of EGFR signaling in mouse skin wound healing. Culture experiments proved that EGFR activation drives human keratinocyte stem cell motility with increase of COL17A1 by inhibiting its proteolysis through the secretion of tissue inhibitor of metalloproteinases 1 (TIMP1). Intriguingly, COL17A1 directly regulated keratinocyte stem cell motility and collective cell migration by coordinating actin and keratin filament networks. We conclude that EGFR-COL17A1 axis-mediated keratinocyte stem cell motility drives epidermal regeneration, which provides a novel therapeutic approach for age-associated impaired skin regeneration.

Cells/colony motion of oral keratinocytes determined by non-invasive and quantitative measurement using optical flow predicts epithelial regenerative capacity

Cells/colony motion determined by non-invasive, quantitative measurements using the optical flow (OF) algorithm can indicate the oral keratinocyte proliferative capacity in early-phase primary cultures. This study aimed to determine a threshold for the cells/colony motion index to detect substandard cell populations in a subsequent subculture before manufacturing a tissue-engineered oral mucosa graft and to investigate the correlation with the epithelial regenerative capacity. The distinctive proliferating pattern of first-passage [passage 1 (p1)] cells reveals the motion of p1 cells/colonies, which can be measured in a non-invasive, quantitative manner using OF with fewer full-screen imaging analyses and cell segmentations. Our results demonstrate that the motion index lower than 40 μm/h reflects cellular damages by experimental metabolic challenges although this value shall only apply in case of our culture system. Nonetheless, the motion index can be used as the threshold to determine the quality of cultured cells while it may be affected by any different culture conditions. Because the p1 cells/colony motion index is correlated with epithelial regenerative capacity, it is a reliable index for quality control of oral keratinocytes.

Label-free quality control and identification of human keratinocyte stem cells by deep learning-based automated cell tracking

Stem cell-based products have clinical and industrial applications. Thus, there is a need to develop quality control methods to standardize stem cell manufacturing. Here, we report a deep learning-based automated cell tracking (DeepACT) technology for noninvasive quality control and identification of cultured human stem cells. The combination of deep learning-based cascading cell detection and Kalman filter algorithm-based tracking successfully tracked the individual cells within the densely packed human epidermal keratinocyte colonies in the phase-contrast images of the culture. DeepACT rapidly analyzed the motion of individual keratinocytes, which enabled the quantitative evaluation of keratinocyte dynamics in response to changes in culture conditions. Furthermore, DeepACT can distinguish keratinocyte stem cell colonies from non-stem cell-derived colonies by analyzing the spatial and velocity information of cells. This system can be widely applied to stem cell cultures used in regenerative medicine and provides a platform for developing reliable and noninvasive quality control technology.