Rapid 3D phenotypic analysis of neurons and organoids using data-driven cell segmentation-free machine learning

Morphological profiling for drug discovery in the era of deep learning

Morphological profiling is a valuable tool in phenotypic drug discovery. The advent of high-throughput automated imaging has enabled the capturing of a wide range of morphological features of cells or organisms in response to perturbations at the single-cell resolution. Concurrently, significant advances in machine learning and deep learning, especially in computer vision, have led to substantial improvements in analyzing large-scale high-content images at high throughput. These efforts have facilitated understanding of compound mechanism of action, drug repurposing, characterization of cell morphodynamics under perturbation, and ultimately contributing to the development of novel therapeutics. In this review, we provide a comprehensive overview of the recent advances in the field of morphological profiling. We summarize the image profiling analysis workflow, survey a broad spectrum of analysis strategies encompassing feature engineering- and deep learning-based approaches, and introduce publicly available benchmark datasets. We place a particular emphasis on the application of deep learning in this pipeline, covering cell segmentation, image representation learning, and multimodal learning. Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.

Revealing the clinical potential of high-resolution organoids

The symbiotic interplay of organoid technology and advanced imaging strategies yields innovative breakthroughs in research and clinical applications. Organoids, intricate three-dimensional cell cultures derived from pluripotent or adult stem/progenitor cells, have emerged as potent tools for in vitro modeling, reflecting in vivo organs and advancing our grasp of tissue physiology and disease. Concurrently, advanced imaging technologies such as confocal, light-sheet, and two-photon microscopy ignite fresh explorations, uncovering rich organoid information. Combined with advanced imaging technologies and the power of artificial intelligence, organoids provide new insights that bridge experimental models and real-world clinical scenarios. This review explores exemplary research that embodies this technological synergy and how organoids reshape personalized medicine and therapeutics.

AI-organoid integrated systems for biomedical studies and applications

In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)-derived organoids. Stem cell-derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error-prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid-based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label-free organoid recognition, and three-dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI-organoid integration, focusing on the establishment of reliable AI model decision-making processes and the standardization of organoid research.

AI-enabled organoids: Construction, analysis, and application

Organoids, miniature and simplified in vitro model systems that mimic the structure and function of organs, have attracted considerable interest due to their promising applications in disease modeling, drug screening, personalized medicine, and tissue engineering. Despite the substantial success in cultivating physiologically relevant organoids, challenges remain concerning the complexities of their assembly and the difficulties associated with data analysis. The advent of AI-Enabled Organoids, which interfaces with artificial intelligence (AI), holds the potential to revolutionize the field by offering novel insights and methodologies that can expedite the development and clinical application of organoids. This review succinctly delineates the fundamental concepts and mechanisms underlying AI-Enabled Organoids, summarizing the prospective applications on rapid screening of construction strategies, cost-effective extraction of multiscale image features, streamlined analysis of multi-omics data, and precise preclinical evaluation and application. We also explore the challenges and limitations of interfacing organoids with AI, and discuss the future direction of the field. Taken together, the AI-Enabled Organoids hold significant promise for advancing our understanding of organ development and disease progression, ultimately laying the groundwork for clinical application.

A microwell platform for high-throughput longitudinal phenotyping and selective retrieval of organoids

Organoids are powerful experimental models for studying the ontogeny and progression of various diseases including cancer. Organoids are conventionally cultured in bulk using an extracellular matrix mimic. However, bulk-cultured organoids physically overlap, making it impossible to track the growth of individual organoids over time in high throughput. Moreover, local spatial variations in bulk matrix properties make it difficult to assess whether observed phenotypic heterogeneity between organoids results from intrinsic cell differences or differences in the microenvironment. Here, we developed a microwell-based method that enables high-throughput quantification of image-based parameters for organoids grown from single cells, which can further be retrieved from their microwells for molecular profiling. Coupled with a deep learning image-processing pipeline, we characterized phenotypic traits including growth rates, cellular movement, and apical-basal polarity in two CRISPR-engineered human gastric organoid models, identifying genomic changes associated with increased growth rate and changes in accessibility and expression correlated with apical-basal polarity. A record of this paper's transparent peer review process is included in the supplemental information.

Balance between the cell viability and death in 3D

Cell death is a phenomenon, frequently perceived as an absolute event for cell, tissue and the organ. However, the rising popularity and complexity of such 3D multicellular 'tissue building blocks' as heterocellular spheroids, organoids, and 'assembloids' prompts to revise the definition and quantification of cell viability and death. It raises several questions on the overall viability of all the cells within 3D volume and on choosing the appropriate, continuous, and non-destructive viability assay enabling for a single-cell analysis. In this review, we look at cell viability and cell death modalities with attention to the intrinsic features of such 3D models as spheroids, organoids, and bioprints. Furthermore, we look at emerging and promising methodologies, which can help define and understand the balance between cell viability and death in dynamic and complex 3D environments. We conclude that the recent innovations in biofabrication, biosensor probe development, and fluorescence microscopy can help answer these questions.

Organoid Cultures In Silico: Tools or Toys?

The implementation of stem-cell-based organoid culture more than ten years ago started a development that created new avenues for diagnostic analyses and regenerative medicine. In parallel, computational modelling groups realized the potential of this culture system to support their theoretical approaches to study tissues in silico. These groups developed computational organoid models (COMs) that enabled testing consistency between cell biological data and developing theories of tissue self-organization. The models supported a mechanistic understanding of organoid growth and maturation and helped linking cell mechanics and tissue shape in general. What comes next? Can we use COMs as tools to complement the equipment of our biological and medical research? While these models already support experimental design, can they also quantitatively predict tissue behavior? Here, we review the current state of the art of COMs and discuss perspectives for their application.

Organoids

Organoids have attracted increasing attention because they are simple tissue-engineered cell-based in vitro models that recapitulate many aspects of the complex structure and function of the corresponding in vivo tissue. They can be dissected and interrogated for fundamental mechanistic studies on development, regeneration, and repair in human tissues. Organoids can also be used in diagnostics, disease modeling, drug discovery, and personalized medicine. Organoids are derived from either pluripotent or tissue-resident stem (embryonic or adult) or progenitor or differentiated cells from healthy or diseased tissues, such as tumors. To date, numerous organoid engineering strategies that support organoid culture and growth, proliferation, differentiation and maturation have been reported. This Primer serves to highlight the rationale underlying the selection and development of these materials and methods to control the cellular/tissue niche; and therefore, structure and function of the engineered organoid. We also discuss key considerations for generating robust organoids, such as those related to cell isolation and seeding, matrix and soluble factor selection, physical cues and integration. The general standards for data quality, reproducibility and deposition within the organoid community is also outlined. Lastly, we conclude by elaborating on the limitations of organoids in different applications, and key priorities in organoid engineering for the coming years.

Patient-by-Patient Deep Transfer Learning for Drug-Response Profiling Using Confocal Fluorescence Microscopy of Pediatric Patient-Derived Tumor-Cell Spheroids

Image-based phenotypic drug profiling is receiving increasing attention in drug discovery and precision medicine. Compared to classical end-point measurements quantifying drug response, image-based profiling enables both the quantification of drug response and characterization of disease entities and drug-induced cell-death phenotypes. Here, we aim to quantify image-based drug responses in patient-derived 3D spheroid tumor cell cultures, tackling the challenges of a lack of single-cell-segmentation methods and limited patient-derived material. Therefore, we investigate deep transfer learning with patient-by-patient fine-tuning for cell-viability quantification. We fine-tune a convolutional neural network (pre-trained on ImageNet) with 210 control images specific to a single training cell line and 54 additional screen -specific assay control images. This method of image-based drug profiling is validated on 6 cell lines with known drug sensitivities, and further tested with primary patient-derived samples in a medium-throughput setting. Network outputs at different drug concentrations are used for drug-sensitivity scoring, and dense-layer activations are used in t-distributed stochastic neighbor embeddings of drugs to visualize groups of drugs with similar cell-death phenotypes. Image-based cell-line experiments show strong correlation to metabolic results ( R ≈ 0.7 ) and confirm expected hits, indicating the predictive power of deep learning to identify drug-hit candidates for individual patients. In patient-derived samples, combining drug sensitivity scoring with phenotypic analysis may provide opportunities for complementary combination treatments. Deep transfer learning with patient-by-patient fine-tuning is a promising, segmentation-free image-analysis approach for precision medicine and drug discovery.

Challenges and advances in optical 3D mesoscale imaging

Optical mesoscale imaging is a rapidly developing field that allows the visualisation of larger samples than is possible with standard light microscopy, and fills a gap between cell and organism resolution. It spans from advanced fluorescence imaging of micrometric cell clusters to centimetre-size complete organisms. However, with larger volume specimens, new problems arise. Imaging deeper into tissues at high resolution poses challenges ranging from optical distortions to shadowing from opaque structures. This manuscript discusses the latest developments in mesoscale imaging and highlights limitations, namely labelling, clearing, absorption, scattering, and also sample handling. We then focus on approaches that seek to turn mesoscale imaging into a more quantitative technique, analogous to quantitative tomography in medical imaging, highlighting a future role for digital and physical phantoms as well as artificial intelligence.

Seeing the Forest and Its Trees Together: Implementing 3D Light Microscopy Pipelines for Cell Type Mapping in the Mouse Brain

The brain is composed of diverse neuronal and non-neuronal cell types with complex regional connectivity patterns that create the anatomical infrastructure underlying cognition. Remarkable advances in neuroscience techniques enable labeling and imaging of these individual cell types and their interactions throughout intact mammalian brains at a cellular resolution allowing neuroscientists to examine microscopic details in macroscopic brain circuits. Nevertheless, implementing these tools is fraught with many technical and analytical challenges with a need for high-level data analysis. Here we review key technical considerations for implementing a brain mapping pipeline using the mouse brain as a primary model system. Specifically, we provide practical details for choosing methods including cell type specific labeling, sample preparation (e.g., tissue clearing), microscopy modalities, image processing, and data analysis (e.g., image registration to standard atlases). We also highlight the need to develop better 3D atlases with standardized anatomical labels and nomenclature across species and developmental time points to extend the mapping to other species including humans and to facilitate data sharing, confederation, and integrative analysis. In summary, this review provides key elements and currently available resources to consider while developing and implementing high-resolution mapping methods.

CODEX, a neural network approach to explore signaling dynamics landscapes

Current studies of cell signaling dynamics that use live cell fluorescent biosensors routinely yield thousands of single-cell, heterogeneous, multi-dimensional trajectories. Typically, the extraction of relevant information from time series data relies on predefined, human-interpretable features. Without a priori knowledge of the system, the predefined features may fail to cover the entire spectrum of dynamics. Here we present CODEX, a data-driven approach based on convolutional neural networks (CNNs) that identifies patterns in time series. It does not require a priori information about the biological system and the insights into the data are built through explanations of the CNNs' predictions. CODEX provides several views of the data: visualization of all the single-cell trajectories in a low-dimensional space, identification of prototypic trajectories, and extraction of distinctive motifs. We demonstrate how CODEX can provide new insights into ERK and Akt signaling in response to various growth factors, and we recapitulate findings in p53 and TGFβ-SMAD2 signaling.