Deep-LUMEN assay - human lung epithelial spheroid classification from brightfield images using deep learning

From Organ-on-a-Chip to Human-on-a-Chip: A Review of Research Progress and Latest Applications

Organ-on-a-Chip (OOC) technology, which emulates the physiological environment and functionality of human organs on a microfluidic chip, is undergoing significant technological advancements. Despite its rapid evolution, this technology is also facing notable challenges, such as the lack of vascularization, the development of multiorgan-on-a-chip systems, and the replication of the human body on a single chip. The progress of microfluidic technology has played a crucial role in steering OOC toward mimicking the human microenvironment, including vascularization, microenvironment replication, and the development of multiorgan microphysiological systems. Additionally, advancements in detection, analysis, and organoid imaging technologies have enhanced the functionality and efficiency of Organs-on-Chips (OOCs). In particular, the integration of artificial intelligence has revolutionized organoid imaging, significantly enhancing high-throughput drug screening. Consequently, this review covers the research progress of OOC toward Human-on-a-chip, the integration of sensors in OOCs, and the latest applications of organoid imaging technologies in the biomedical field.

Image-based profiling and deep learning reveal morphological heterogeneity of colorectal cancer organoids

Patient-derived organoids have proven to be a highly relevant model for evaluating of disease mechanisms and drug efficacies, as they closely recapitulate in vivo physiology. Colorectal cancer organoids, specifically, exhibit a diverse range of morphologies, which have been analyzed with image-based profiling. However, the relationship between morphological subtypes and functional parameters of the organoids remains underexplored. Here, we identified two distinct morphological subtypes ("cystic" and "solid") across 31360 bright field images using image-based profiling, which correlated differently with viability and apoptosis level of colorectal cancer organoids. Leveraging object detection neural networks, we were able to categorize single organoids achieving higher viability scores as "cystic" than "solid" subtype. Furthermore, a deep generative model was proposed to predict apoptosis intensity based on a apoptosis-featured dataset encompassing over 17000 bright field and matched fluorescent images. Notably, a significant correlation of 0.91 between the predicted value and ground truth was achived, underscoring the feasibility of this generative model as a potential means for assessing organoid functional parameters. The underlying cellular heterogeneity of the organoids, i.e., conserved colonic cell types and rare immune components, was also verified with scRNA sequencing, implying a compromised tumor microenvironment. Additionally, the "cystic" subtype was identified as a relapse phenotype featuring intestinal stem cell signatures, suggesting that this visually discernible relapse phenotype shows potential as a novel biomarker for colorectal cancer diagnosis and prognosis. In summary, our findings demonstrate that the morphological heterogeneity of colorectal cancer organoids explicitly recapitulate the association of phenotypic features and exogenous perturbations through the image-based profiling, providing new insights into disease mechanisms.

Patient-Derived Microphysiological Systems for Precision Medicine

Patient-derived microphysiological systems (P-MPS) have emerged as powerful tools in precision medicine that provide valuable insight into individual patient characteristics. This review discusses the development of P-MPS as an integration of patient-derived samples, including patient-derived cells, organoids, and induced pluripotent stem cells, into well-defined MPSs. Emphasizing the necessity of P-MPS development, its significance as a nonclinical assessment approach that bridges the gap between traditional in vitro models and clinical outcomes is highlighted. Additionally, guidance is provided for engineering approaches to develop microfluidic devices and high-content analysis for P-MPSs, enabling high biological relevance and high-throughput experimentation. The practical implications of the P-MPS are further examined by exploring the clinically relevant outcomes obtained from various types of patient-derived samples. The construction and analysis of these diverse samples within the P-MPS have resulted in physiologically relevant data, paving the way for the development of personalized treatment strategies. This study describes the significance of the P-MPS in precision medicine, as well as its unique capacity to offer valuable insights into individual patient characteristics.

Deep-Orga: An improved deep learning-based lightweight model for intestinal organoid detection

PROBLEM

Organoids are 3D cultures that are commonly used for biological and medical research in vitro due to their functional and structural similarity to source organs. The development of organoids can be assessed by morphological tests. However, manual analysis of organoid morphology requires intensive labor from professionals and is prone to observer discrepancies.

AIM

Computer-assisted methods alleviate the pressure of manual labor, especially with the development of deep learning, the performance of morphological detection has been further improved. The aim of this paper is to automate the assessment of organoid morphology using deep learning techniques to reduce the labor pressure of professionals.

METHODS

Based on the lightweight model YOLOX, a lightweight intestinal organoid detection model named Deep-Orga is proposed. First, the performance of the Deep-Orga model is compared with other classical models on the intestinal organoids dataset. Then, ablation experiments are used to validate the improvement of the model detection performance by the improved module. Finally, Deep-Orga is compared with other methods.

RESULTS

Deep-Orga achieves optimal organoid detection with a partial increase in computational effort. Using Deep-Orga to replace the manual analysis process provides a new automated method for organoid morphology evaluation.

CONCLUSION

Deep-Orga proposed in this paper is able to accurately assess organoid development, effectively relieving the labor pressure of professionals and avoiding the subjectivity of assessment. This paper demonstrates the potential application of deep learning in the field of organoid morphology analysis.

Deep Learning Model for Predicting Airway Organoid Differentiation

BACKGROUND

Organoids are self-organized three-dimensional culture systems and have the advantages of both in vitro and in vivo experiments. However, each organoid has a different degree of self-organization, and methods such as immunofluorescence staining are required for confirmation. Therefore, we established a system to select organoids with high tissue-specific similarity using deep learning without relying on staining by acquiring bright-field images in a non-destructive manner.

METHODS

We identified four biomarkers in RNA extracted from airway organoids. We also predicted biomarker expression by image-based analysis of organoids by convolution neural network, a deep learning method.

RESULTS

We predicted airway organoid-specific marker expression from bright-field images of organoids. Organoid differentiation was verified by immunofluorescence staining of the same organoid after predicting biomarker expression in bright-field images.

CONCLUSION

Our study demonstrates the potential of imaging and deep learning to distinguish organoids with high human tissue similarity in disease research and drug screening.

Lung cancer organoids: models for preclinical research and precision medicine

Lung cancer is a malignancy with high incidence and mortality rates globally, and it has a 5-year survival rate of only 10%-20%. The significant heterogeneity in clinical presentation, histological features, multi-omics findings, and drug sensitivity among different lung cancer patients necessitate the development of personalized treatment strategies. The current precision medicine for lung cancer, primarily based on pathological and genomic multi-omics testing, fails to meet the needs of patients with clinically refractory lung cancer. Lung cancer organoids (LCOs) are derived from tumor cells within tumor tissues and are generated through three-dimensional tissue culture, enabling them to faithfully recapitulate in vivo tumor characteristics and heterogeneity. The establishment of a series of LCOs biobanks offers promising platforms for efficient screening and identification of novel targets for anti-tumor drug discovery. Moreover, LCOs provide supplementary decision-making factors to enhance the current precision medicine for lung cancer, thereby addressing the limitations associated with pathology-guided approaches in managing refractory lung cancer. This article presents a comprehensive review on the construction methods and potential applications of LCOs in both preclinical and clinical research. It highlights the significance of LCOs in biomarker exploration, drug resistance investigation, target identification, clinical precision drug screening, as well as microfluidic technology-based high-throughput drug screening strategies. Additionally, it discusses the current limitations and future prospects of this field.

Application of colloidal photonic crystals in study of organoids

As alternative disease models, other than 2D cell lines and patient-derived xenografts, organoids have preferable in vivo physiological relevance. However, both endogenous and exogenous limitations impede the development and clinical translation of these organoids. Fortunately, colloidal photonic crystals (PCs), which benefit from favorable biocompatibility, brilliant optical manipulation, and facile chemical decoration, have been applied to the engineering of organoids and have achieved the desirable recapitulation of the ECM niche, well-defined geometrical onsets for initial culture, in situ multiphysiological parameter monitoring, single-cell biomechanical sensing, and high-throughput drug screening with versatile functional readouts. Herein, we review the latest progress in engineering organoids fabricated from colloidal PCs and provide inputs for future research.

The interplay of cells, polymers, and vascularization in three-dimensional lung models and their applications in COVID-19 research and therapy

Millions of people have been affected ever since the emergence of the corona virus disease of 2019 (COVID-19) outbreak, leading to an urgent need for antiviral drug and vaccine development. Current experimentation on traditional two-dimensional culture (2D) fails to accurately mimic the in vivo microenvironment for the disease, while in vivo animal model testing does not faithfully replicate human COVID-19 infection. Human-based three-dimensional (3D) cell culture models such as spheroids, organoids, and organ-on-a-chip present a promising solution to these challenges. In this report, we review the recent 3D in vitro lung models used in COVID-19 infection and drug screening studies and highlight the most common types of natural and synthetic polymers used to generate 3D lung models.

Patient-derived organoids in translational oncology and drug screening

Patient-derived organoids (PDO) are a new biomedical research model that can reconstruct phenotypic and genetic characteristics of the original tissue and are useful for research on pathogenesis and drug screening. To introduce the progression in this field, we review the key factors of constructing organoids derived from epithelial tissues and cancers, covering culture medium and matrix, morphological characteristics, genetic profiles, high-throughput drug screening, and application potential. We also discuss the co-culture system of cancer organoids with tumor microenvironment (TME) associated cells. The co-culture system is widely used in evaluating crosstalk of cancer cells with TME components, such as fibroblasts, endothelial cells, immune cells, and microorganisms. The article provides a prospective for standardized cultivation mode, automatic morphological evaluation, and drug sensitivity screening using high-throughput methods.

Organoids revealed: morphological analysis of the profound next generation in-vitro model with artificial intelligence

In modern terminology, "organoids" refer to cells that grow in a specific three-dimensional (3D) environment in vitro, sharing similar structures with their source organs or tissues. Observing the morphology or growth characteristics of organoids through a microscope is a commonly used method of organoid analysis. However, it is difficult, time-consuming, and inaccurate to screen and analyze organoids only manually, a problem which cannot be easily solved with traditional technology. Artificial intelligence (AI) technology has proven to be effective in many biological and medical research fields, especially in the analysis of single-cell or hematoxylin/eosin stained tissue slices. When used to analyze organoids, AI should also provide more efficient, quantitative, accurate, and fast solutions. In this review, we will first briefly outline the application areas of organoids and then discuss the shortcomings of traditional organoid measurement and analysis methods. Secondly, we will summarize the development from machine learning to deep learning and the advantages of the latter, and then describe how to utilize a convolutional neural network to solve the challenges in organoid observation and analysis. Finally, we will discuss the limitations of current AI used in organoid research, as well as opportunities and future research directions.

Graphic abstract

SpheroScan: a user-friendly deep learning tool for spheroid image analysis

BACKGROUND

In recent years, 3-dimensional (3D) spheroid models have become increasingly popular in scientific research as they provide a more physiologically relevant microenvironment that mimics in vivo conditions. The use of 3D spheroid assays has proven to be advantageous as it offers a better understanding of the cellular behavior, drug efficacy, and toxicity as compared to traditional 2-dimensional cell culture methods. However, the use of 3D spheroid assays is impeded by the absence of automated and user-friendly tools for spheroid image analysis, which adversely affects the reproducibility and throughput of these assays.

RESULTS

To address these issues, we have developed a fully automated, web-based tool called SpheroScan, which uses the deep learning framework called Mask Regions with Convolutional Neural Networks (R-CNN) for image detection and segmentation. To develop a deep learning model that could be applied to spheroid images from a range of experimental conditions, we trained the model using spheroid images captured using IncuCyte Live-Cell Analysis System and a conventional microscope. Performance evaluation of the trained model using validation and test datasets shows promising results.

CONCLUSION

SpheroScan allows for easy analysis of large numbers of images and provides interactive visualization features for a more in-depth understanding of the data. Our tool represents a significant advancement in the analysis of spheroid images and will facilitate the widespread adoption of 3D spheroid models in scientific research. The source code and a detailed tutorial for SpheroScan are available at https://github.com/FunctionalUrology/SpheroScan.

Application Progress of Organoids in Colorectal Cancer

Currently, colorectal cancer is still the third leading cause of cancer-related mortality, and the incidence is rising. It is a long time since the researchers used cancer cell lines and animals as the study subject. However, these models possess various limitations to reflect the cancer progression in the human body. Organoids have more clinical significance than cell lines, and they also bridge the gap between animal models and humans. Patient-derived organoids are three-dimensional cultures that simulate the tumor characteristics in vivo and recapitulate tumor cell heterogeneity. Therefore, the emergence of colorectal cancer organoids provides an unprecedented opportunity for colorectal cancer research. It retains the molecular and cellular composition of the original tumor and has a high degree of homology and complexity with patient tissues. Patient-derived colorectal cancer organoids, as personalized tumor organoids, can more accurately simulate colorectal cancer patients’ occurrence, development, metastasis, and predict drug response in colorectal cancer patients. Colorectal cancer organoids show great potential for application, especially preclinical drug screening and prediction of patient response to selected treatment options. Here, we reviewed the application of colorectal cancer organoids in disease model construction, basic biological research, organoid biobank construction, drug screening and personalized medicine, drug development, drug toxicity and safety, and regenerative medicine. In addition, we also displayed the current limitations and challenges of organoids and discussed the future development direction of organoids in combination with other technologies. Finally, we summarized and analyzed the current clinical trial research of organoids, especially the clinical trials of colorectal cancer organoids. We hoped to lay a solid foundation for organoids used in colorectal cancer research.