Automated evaluation of tumor spheroid behavior in 3D culture using deep learning-based recognition

A deep learning pipeline for morphological and viability assessment of 3D cancer cell spheroids

Three-dimensional (3D) spheroid models have advanced cancer research by better mimicking the tumour microenvironment compared to traditional two-dimensional cell cultures. However, challenges persist in high-throughput analysis of morphological characteristics and cell viability, as traditional methods like manual fluorescence analysis are labour-intensive and inconsistent. Existing AI-based approaches often address segmentation or classification in isolation, lacking an integrated workflow. We propose a scalable, two-stage deep learning pipeline to address these gaps: (i) a U-Net model for precise detection and segmentation of 3D spheroids from microscopic images, achieving 95% prediction accuracy, and (ii) a CNN Regression Hybrid method for estimating live/dead cell percentages and classifying spheroids, with anR 2 value of 98%. This end-to-end pipeline automates cell viability quantification and generates key morphological parameters for spheroid growth kinetics. By integrating segmentation and analysis, our method addresses environmental variability and morphological characterization challenges, offering a robust tool for drug discovery, toxicity screening, and clinical research. This approach significantly improves efficiency and scalability of 3D spheroid evaluations, paving the way for advancements in cancer therapeutics.

Efficient spheroid morphology assessment with a ChatGPT data analyst: implications for cell therapy

BACKGROUND

Adipose-derived stem cells (ADSCs) exhibit promising potential for the treatment of various diseases, including osteoarthritis. Spheroids derived from ADSCs are a viable treatment option with enhanced anti-inflammatory effects and tissue repair capabilities.

OBJECTIVE

SphereRing® is a rotating donut-shaped tube that efficiently produces large quantities of spheroids. However, accurately measuring spheroid size for spheroid quality assessment is challenging. This study aimed to develop an automated method for measuring spheroid size using deep learning through the ChatGPT Data Analyst for image recognition and processing.

METHOD

The area, perimeter, and circularity of spheroids generated with the SphereRing system were analyzed using ChatGPT Data Analyst and ImageJ. Measurement accuracy was validated using Bland-Altman analysis and scatter plot correlation coefficients.

RESULTS

ChatGPT Data Analyst was consistent with ImageJ for all parameters. Bland-Altman plots demonstrated strong agreement; most data points were within the 95% limits.

CONCLUSION

The ChatGPT Data Analyst provides a reliable and efficient alternative for assessing spheroid quality. This method reduces human error and improves reproducibility to enhance spheroid quality control. Thus, this method has potential applications in regenerative medicine.

The Evolution of Anticancer 3D In Vitro Models: The Potential Role of Machine Learning and AI in the Next Generation of Animal-Free Experiments

The development of anticancer therapies has increasingly relied on advanced 3D in vitro models, which more accurately mimic the tumor microenvironment compared to traditional 2D cultures. This review describes the evolution of these 3D models, highlighting significant advancements and their impact on cancer research. We discuss the integration of machine learning (ML) and artificial intelligence (AI) in enhancing the predictive power and efficiency of these models, potentially reducing the dependence on animal testing. ML and AI offer innovative approaches for analyzing complex data, optimizing experimental conditions, and predicting therapeutic outcomes with higher accuracy. By leveraging these technologies, the next generation of 3D in vitro models could revolutionize anticancer drug development, offering effective alternatives to animal experiments.

Quantitative Study on the Charge-Dependent Uptake of Ultrasmall Fluorescent Gold Nanoclusters in 3D Spheroids of Cancer Cells

Gold nanoclusters (AuNCs) have garnered significant attention in biomedical applications, particularly in biosensing, cancer therapy, and imaging, due to their unique optical property, good biocompatibility, and distinct bioactivity. Understanding the cellular uptake behavior of AuNCs is critical to improve the efficacy of their applications, whose mechanism has not been adequately validated. In this work, we synthesized AuNCs with varying surface modifications to quantify the exact law of surface charge on the cellular uptake of AuNCs in a multidimensional manner by using 3D multicellular tumor spheroids of both HeLa cells and MCF-7 cells as the model system. By the combined use of fluorescence live cell imaging and inductively coupled plasma-mass spectrometry, we systematically investigated the effect of surface charge on their uptake rate, intracellular versus intercellular distribution, and penetration depth in a quantitative manner. Our results showed that the cellular uptake of AuNCs was strongly charge dependent, with uptake efficiency increasing with the degree of surface positive charges. A similar charge-dependent uptake behavior was observed in both 2D cell cultures and 3D multicellular tumor spheroids, but the difference in 3D spheroids was less pronounced, in comparison to the 2D model. The effect of AuNCs' surface charge on the cellular uptake has been quantified in multiple dimensions in this work, which also provides crucial knowledge for effective cancer therapeutics and imaging applications based on AuNCs and other nanomaterials.

A multi-stage weakly supervised design for spheroid segmentation to explore mesenchymal stem cell differentiation dynamics

There is a growing interest in utilizing 3D culture models for stem cell and cancer cell research due to their closer resemblance to in vivo environments. In this study, human mesenchymal stem cells (MSCs) were cultured using adipocytes and osteocytes as differentiative mediums on varying concentrations of chitosan substrate. Light microscopy was employed to capture cell images from the first day to the 21st day of differentiation. Accurate image segmentation is crucial for analyzing the morphological features of the spheroids during the experimental period and for understanding MSC differentiation dynamics for therapeutic applications. Therefore, we developed an innovative, weakly supervised model, aided by convolutional neural networks, to perform label-free spheroid segmentation. Since obtaining pixel-level ground truth labels through manual annotation is labor-intensive, our approach improves the overall quality of the ground-truth map by incorporating a multi-stage process within a weakly supervised learning framework. Additionally, we developed a robust learning scheme for spheroid detection, providing a reliable foundation to study MSC differentiation dynamics. The proposed framework was systematically evaluated using low-resolution microscopic data and challenging, noisy backgrounds. The experimental results demonstrate the effectiveness of our segmentation approach in accurately separating the spheroid from the background. Furthermore, it achieves performance comparable to fully supervised state-of-the-art approaches. To quantitatively evaluate our algorithm, extensive experiments were conducted using available annotated data, confirming the reliability and robustness of our method. Our computationally extracted features can confirm the experimental results regarding alterations in MSC viability, attachment, and differentiation dynamics among the substrates with three concentrations of chitosan used. We observed the formation of more compact spheroids with higher solidity and convex area, resulting improved cell attachment and viability on the 2% chitosan substrate. Additionally, this substrate exhibited a higher propensity for differentiation into osteocytes, as evidenced by the formation of smaller and more ellipsoid spheroids.

"Chitosan biofilms mimic in vivo environments for stem cell culture, advancing therapeutic and fundamental applications.” "Innovative weakly supervised model enables label-free spheroid segmentation in stem cell differentiation studies.” "Robust learning scheme achieves accurate spheroid separation, comparable to state-of-the-art approaches.”

Image segmentation of treated and untreated tumor spheroids by fully convolutional networks

BACKGROUND

Multicellular tumor spheroids (MCTS) are advanced cell culture systems for assessing the impact of combinatorial radio(chemo)therapy as they exhibit therapeutically relevant in vivo-like characteristics from 3-dimensional cell-cell and cell-matrix interactions to radial pathophysiological gradients. State-of-the-art assays quantify long-term curative endpoints based on collected brightfield image time series from large treated spheroid populations per irradiation dose and treatment arm. This analyses require laborious spheroid segmentation of up to 100,000 images per treatment arm to extract relevant structural information from the images (e.g., diameter, area, volume, and circularity). While several image analysis algorithms are available for spheroid segmentation, they all focus on compact MCTS with a clearly distinguishable outer rim throughout growth. However, they often fail for the common case of treated MCTS, which may partly be detached and destroyed and are usually obscured by dead cell debris.

RESULTS

To address these issues, we successfully train 2 fully convolutional networks, UNet and HRNet, and optimize their hyperparameters to develop an automatic segmentation for both untreated and treated MCTS. We extensively test the automatic segmentation on larger, independent datasets and observe high accuracy for most images with Jaccard indices around 90%. For cases with lower accuracy, we demonstrate that the deviation is comparable to the interobserver variability. We also test against previously published datasets and spheroid segmentations.

CONCLUSIONS

The developed automatic segmentation can not only be used directly but also integrated into existing spheroid analysis pipelines and tools. This facilitates the analysis of 3-dimensional spheroid assay experiments and contributes to the reproducibility and standardization of this preclinical in vitro model.

Next-Generation Approaches for Biomedical Materials Evaluation: Microfluidics and Organ-on-a-Chip Technologies

Biological evaluation of biomedical materials faces constraints imposed by the limitations of traditional in vitro and animal experiments. Currently, miniaturized and biomimetic microfluidic technologies and organ-on-chip systems have garnered widespread attention in the field of drug development. However, their exploration in the context of biomedical material evaluation and medical device development remains relatively limited. In this review, a summary of existing biological evaluation methods, highlighting their respective advantages and drawbacks is provided. The application of microfluidic technologies in the evaluation of biomedical materials, emphasizing the potential of organ-on-chip systems as highly biomimetic in vitro models in material evaluation is then focused. Finally, the challenges and opportunities associated with utilizing organ-on-chip systems to evaluate biomedical materials in the field of material evaluation are discussed. In conclusion, the integration of advanced microfluidic technologies and organ-on-chip systems presents a potential paradigm shift in the biological assessment of biomedical materials, offering the prospective of more accurate and predictive in vitro models in the development of medical devices.

High-throughput platform for label-free sorting of 3D spheroids using deep learning

End-stage liver diseases have an increasing impact worldwide, exacerbated by the shortage of transplantable organs. Recognized as one of the promising solutions, tissue engineering aims at recreating functional tissues and organs in vitro. The integration of bioprinting technologies with biological 3D models, such as multi-cellular spheroids, has enabled the fabrication of tissue constructs that better mimic complex structures and in vivo functionality of organs. However, the lack of methods for large-scale production of homogeneous spheroids has hindered the upscaling of tissue fabrication. In this work, we introduce a fully automated platform, designed for high-throughput sorting of 3D spheroids based on label-free analysis of brightfield images. The compact platform is compatible with standard biosafety cabinets and includes a custom-made microscope and two fluidic systems that optimize single spheroid handling to enhance sorting speed. We use machine learning to classify spheroids based on their bioprinting compatibility. This approach enables complex morphological analysis, including assessing spheroid viability, without relying on invasive fluorescent labels. Furthermore, we demonstrate the efficacy of transfer learning for biological applications, for which acquiring large datasets remains challenging. Utilizing this platform, we efficiently sort mono-cellular and multi-cellular liver spheroids, the latter being used in bioprinting applications, and confirm that the sorting process preserves viability and functionality of the spheroids. By ensuring spheroid homogeneity, our sorting platform paves the way for standardized and scalable tissue fabrication, advancing regenerative medicine applications.

Unveiling the Heart's Hidden Enemy: Dynamic Insights into Polystyrene Nanoplastic-Induced Cardiotoxicity Based on Cardiac Organoid-on-a-Chip

Exposure to micro- and nanoplastics (MNPs) has been implicated in potential cardiotoxicity. However, in vitro models based on cardiomyocyte cell lines lack crucial cardiac characteristics, while interspecies differences in animal models compromise the reliability of the conclusions. In addition, current research has predominantly focused on single-time point exposures to MNPs, neglecting comparative analyses of cardiac injury across early and late stages. Moreover, there remains a large gap in understanding the susceptibility to MNPs under pathological conditions. To address these limitations, this study integrated cardiac organoids (COs) and organ-on-a-chip (OoC) technology to develop the cardiac organoid-on-a-chip (COoC), which was validated for cardiotoxicity evaluation through multiple dimensions. Based on COoC, we conducted a dynamic observation of the cardiac damage caused by short- and long-term exposure to polystyrene nanoplastics (PS-NPs). Oxidative stress, inflammation, disruption of calcium ion homeostasis, and mitochondrial dysfunction were confirmed as the potential mechanisms of PS-NP-induced cardiotoxicity and the crucial events in the early stages, while cardiac fibrosis emerged as a prominent feature in late stages. Notably, low-dose exposure exacerbated myocardial infarction symptoms under pathological states, despite no significant cardiotoxicity shown in healthy models. In conclusion, these findings further deepened our understanding of PS-NP-induced cardiotoxic effects and introduced a promising in vitro platform for assessing cardiotoxicity.

AI for biofabrication

Biofabrication is an advanced technology that holds great promise for constructing highly biomimeticin vitrothree-dimensional human organs. Such technology would help address the issues of immune rejection and organ donor shortage in organ transplantation, aiding doctors in formulating personalized treatments for clinical patients and replacing animal experiments. Biofabrication typically involves the interdisciplinary application of biology, materials science, mechanical engineering, and medicine to generate large amounts of data and correlations that require processing and analysis. Artificial intelligence (AI), with its excellent capabilities in big data processing and analysis, can play a crucial role in handling and processing interdisciplinary data and relationships and in better integrating and applying them in biofabrication. In recent years, the development of the semiconductor and integrated circuit industries has propelled the rapid advancement of computer processing power. An AI program can learn and iterate multiple times within a short period, thereby gaining strong automation capabilities for a specific research content or issue. To date, numerous AI programs have been applied to various processes around biofabrication, such as extracting biological information, designing and optimizing structures, intelligent cell sorting, optimizing biomaterials and processes, real-time monitoring and evaluation of models, accelerating the transformation and development of these technologies, and even changing traditional research patterns. This article reviews and summarizes the significant changes and advancements brought about by AI in biofabrication, and discusses its future application value and direction.

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.

Advancing Intelligent Organ-on-a-Chip Systems with Comprehensive In Situ Bioanalysis

In vitro models are essential to a broad range of biomedical research, such as pathological studies, drug development, and personalized medicine. As a potentially transformative paradigm for 3D in vitro models, organ-on-a-chip (OOC) technology has been extensively developed to recapitulate sophisticated architectures and dynamic microenvironments of human organs by applying the principles of life sciences and leveraging micro- and nanoscale engineering capabilities. A pivotal function of OOC devices is to support multifaceted and timely characterization of cultured cells and their microenvironments. However, in-depth analysis of OOC models typically requires biomedical assay procedures that are labor-intensive and interruptive. Herein, the latest advances toward intelligent OOC (iOOC) systems, where sensors integrated with OOC devices continuously report cellular and microenvironmental information for comprehensive in situ bioanalysis, are examined. It is proposed that the multimodal data in iOOC systems can support closed-loop control of the in vitro models and offer holistic biomedical insights for diverse applications. Essential techniques for establishing iOOC systems are surveyed, encompassing in situ sensing, data processing, and dynamic modulation. Eventually, the future development of iOOC systems featuring cross-disciplinary strategies is discussed.

Bridging the organoid translational gap: integrating standardization and micropatterning for drug screening in clinical and pharmaceutical medicine

Synthetic organ models such as organoids and organ-on-a-chip have been receiving recognition from administrative agencies. Despite the proven success of organoids in predicting drug efficacy on laboratory scales, their translational advances have not fully satisfied the expectations for both clinical implementation and commercial applications. The transition from laboratory settings to clinical applications continues to encounter challenges. Employing engineering methodologies to facilitate the bridging of this gap for organoids represents one of the key directions for future advancement. The main measures to bridge the gap include environmental and phenotypic recapitulation, 3D patterning, matrix engineering, and multi-modality information acquisition and processing. Pilot whole-process clinical/pharmaceutical applications with fast and standardized organoid models will continuously offer convincing frontline optimization clues and driving forces to the organoid community, which is a promising path to translational organoid technologies.

Nondestructive, quantitative viability analysis of 3D tissue cultures using machine learning image segmentation

Ascertaining the collective viability of cells in different cell culture conditions has typically relied on averaging colorimetric indicators and is often reported out in simple binary readouts. Recent research has combined viability assessment techniques with image-based deep-learning models to automate the characterization of cellular properties. However, further development of viability measurements to assess the continuity of possible cellular states and responses to perturbation across cell culture conditions is needed. In this work, we demonstrate an image processing algorithm for quantifying features associated with cellular viability in 3D cultures without the need for assay-based indicators. We show that our algorithm performs similarly to a pair of human experts in whole-well images over a range of days and culture matrix compositions. To demonstrate potential utility, we perform a longitudinal study investigating the impact of a known therapeutic on pancreatic cancer spheroids. Using images taken with a high content imaging system, the algorithm successfully tracks viability at the individual spheroid and whole-well level. The method we propose reduces analysis time by 97% in comparison with the experts. Because the method is independent of the microscope or imaging system used, this approach lays the foundation for accelerating progress in and for improving the robustness and reproducibility of 3D culture analysis across biological and clinical research.

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.

Angio-Net: deep learning-based label-free detection and morphometric analysis of in vitro angiogenesis

Despite significant advancements in three-dimensional (3D) cell culture technology and the acquisition of extensive data, there is an ongoing need for more effective and dependable data analysis methods. These concerns arise from the continued reliance on manual quantification techniques. In this study, we introduce a microphysiological system (MPS) that seamlessly integrates 3D cell culture to acquire large-scale imaging data and employs deep learning-based virtual staining for quantitative angiogenesis analysis. We utilize a standardized microfluidic device to obtain comprehensive angiogenesis data. Introducing Angio-Net, a novel solution that replaces conventional immunocytochemistry, we convert brightfield images into label-free virtual fluorescence images through the fusion of SegNet and cGAN. Moreover, we develop a tool capable of extracting morphological blood vessel features and automating their measurement, facilitating precise quantitative analysis. This integrated system proves to be invaluable for evaluating drug efficacy, including the assessment of anticancer drugs on targets such as the tumor microenvironment. Additionally, its unique ability to enable live cell imaging without the need for cell fixation promises to broaden the horizons of pharmaceutical and biological research. Our study pioneers a powerful approach to high-throughput angiogenesis analysis, marking a significant advancement in MPS.

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.

High throughput generating stable spheroids with tip-refill wafer

Three-dimensional (3D) cell cultures have garnered significant attention in biomedical research due to their ability to mimic the in vivo cellular environment more accurately. The formation of 3D cell spheroids using hanging drops has emerged as a cost-effective and crucial method for generating uniformly-sized spheroids. This study aimed to validate the potential of a tip-refill wafer (TrW), a disposable laboratory item used to hold pipette tips, in facilitating 3D cell culture. The TrW allows for easy generation of hanging drops by pipetting the solution into the holes of the wafer. The mechanical stability of the hanging drops is ensured by the surface wettability and thickness of the TrW. Hanging drops containing 60-µL of solution remained securely attached to the TrW even when subjected to orbital shaking at 210 rpm. The exceptional resistance to mechanical shaking enabled the use of inertial focusing to facilitate spheroid formation. This was demonstrated through live/dead cell staining, quantitative polymerase chain reaction (qPCR) analysis, and cytoskeleton staining, which revealed that horizontal orbiting at 60 rpm for 15 min promoted cell aggregation and ultimately led to the formation of 3D spheroids. The spheroid harvest rate is 96.1% ± 3.5% across three TrWs, each containing 60 hanging drops. In addition to generating mono-culture 3D spheroids, the TrW-based hanging drop platform also enables the formation of multicellular spheroids, and on-demand pairing and fusion of spheroids. The TrW is a disposable item that does not require any fabrication or surface modification procedures, further enhancing its application potential in conventional biological laboratories.

Microfluidics-based patient-derived disease detection tool for deep learning-assisted precision medicine

Cancer spatial and temporal heterogeneity fuels resistance to therapies. To realize the routine assessment of cancer prognosis and treatment, we demonstrate the development of an Intelligent Disease Detection Tool (IDDT), a microfluidic-based tumor model integrated with deep learning-assisted algorithmic analysis. IDDT was clinically validated with liquid blood biopsy samples (n = 71) from patients with various types of cancers (e.g., breast, gastric, and lung cancer) and healthy donors, requiring low sample volume (∼200 μl) and a high-throughput 3D tumor culturing system (∼300 tumor clusters). To support automated algorithmic analysis, intelligent decision-making, and precise segmentation, we designed and developed an integrative deep neural network, which includes Mask Region-Based Convolutional Neural Network (Mask R-CNN), vision transformer, and Segment Anything Model (SAM). Our approach significantly reduces the manual labeling time by up to 90% with a high mean Intersection Over Union (mIoU) of 0.902 and immediate results (<2 s per image) for clinical cohort classification. The IDDT can accurately stratify healthy donors (n = 12) and cancer patients (n = 55) within their respective treatment cycle and cancer stage, resulting in high precision (∼99.3%) and high sensitivity (∼98%). We envision that our patient-centric IDDT provides an intelligent, label-free, and cost-effective approach to help clinicians make precise medical decisions and tailor treatment strategies for each patient.

Engineered organoids for biomedical applications

As miniaturized and simplified stem cell-derived 3D organ-like structures, organoids are rapidly emerging as powerful tools for biomedical applications. With their potential for personalized therapeutic interventions and high-throughput drug screening, organoids have gained significant attention recently. In this review, we discuss the latest developments in engineering organoids and using materials engineering, biochemical modifications, and advanced manufacturing technologies to improve organoid culture and replicate vital anatomical structures and functions of human tissues. We then explore the diverse biomedical applications of organoids, including drug development and disease modeling, and highlight the tools and analytical techniques used to investigate organoids and their microenvironments. We also examine the latest clinical trials and patents related to organoids that show promise for future clinical translation. Finally, we discuss the challenges and future perspectives of using organoids to advance biomedical research and potentially transform personalized medicine.

A deep learning-based pipeline for analyzing the influences of interfacial mechanochemical microenvironments on spheroid invasion using differential interference contrast microscopic images

Metastasis is the leading cause of cancer-related deaths. During this process, cancer cells are likely to navigate discrete tissue-tissue interfaces, enabling them to infiltrate and spread throughout the body. Three-dimensional (3D) spheroid modeling is receiving more attention due to its strengths in studying the invasive behavior of metastatic cancer cells. While microscopy is a conventional approach for investigating 3D invasion, post-invasion image analysis, which is a time-consuming process, remains a significant challenge for researchers. In this study, we presented an image processing pipeline that utilized a deep learning (DL) solution, with an encoder-decoder architecture, to assess and characterize the invasion dynamics of tumor spheroids. The developed models, equipped with feature extraction and measurement capabilities, could be successfully utilized for the automated segmentation of the invasive protrusions as well as the core region of spheroids situated within interfacial microenvironments with distinct mechanochemical factors. Our findings suggest that a combination of the spheroid culture and DL-based image analysis enable identification of time-lapse migratory patterns for tumor spheroids above matrix-substrate interfaces, thus paving the foundation for delineating the mechanism of local invasion during cancer metastasis.

Computer vision meets microfluidics: a label-free method for high-throughput cell analysis

In this paper, we review the integration of microfluidic chips and computer vision, which has great potential to advance research in the life sciences and biology, particularly in the analysis of cell imaging data. Microfluidic chips enable the generation of large amounts of visual data at the single-cell level, while computer vision techniques can rapidly process and analyze these data to extract valuable information about cellular health and function. One of the key advantages of this integrative approach is that it allows for noninvasive and low-damage cellular characterization, which is important for studying delicate or fragile microbial cells. The use of microfluidic chips provides a highly controlled environment for cell growth and manipulation, minimizes experimental variability and improves the accuracy of data analysis. Computer vision can be used to recognize and analyze target species within heterogeneous microbial populations, which is important for understanding the physiological status of cells in complex biological systems. As hardware and artificial intelligence algorithms continue to improve, computer vision is expected to become an increasingly powerful tool for in situ cell analysis. The use of microelectromechanical devices in combination with microfluidic chips and computer vision could enable the development of label-free, automatic, low-cost, and fast cellular information recognition and the high-throughput analysis of cellular responses to different compounds, for broad applications in fields such as drug discovery, diagnostics, and personalized medicine.

SpheroScan: A User-Friendly Deep Learning Tool for Spheroid Image Analysis

Background

In recent years, three-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 two-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.

Surface-Roughened SERS-Active Single Silver Nanowire for Simultaneous Detection of Intracellular and Extracellular pHs

The simultaneous and accurate detection of intracellular pH (pH_i) and extracellular pH (pH_e) is essential for studying the complex physiological activities of cancer cells and exploring pH-related therapeutic mechanisms. Here, we developed a super-long silver nanowire-based surface-enhanced Raman scattering (SERS) detection strategy for simultaneous sensing of pH_i and pH_e. A surface-roughened silver nanowire (AgNW) with a high aspect ratio is prepared at a nanoelectrode tip using a Cu-mediated oxidation process, which is then modified by pH-sensitive 4-mercaptobenzoic acid (4-MBA) to form 4-MBA@AgNW as a pH sensing probe. With the assistance of a 4D microcontroller, 4-MBA@AgNW is efficient in simultaneously detecting pH_i and pH_e in both 2D and 3D culture cancer cells by SERS, with minimal invasiveness, high sensitivity, and spatial resolution. Further investigation proves that the surface-roughened single AgNW can also be used in monitoring the dynamic variation of pH_i and pH_e of cancer cells upon stimulation with anticancer drugs or under a hypoxic environment.

Tumor Organoid and Spheroid Models for Cervical Cancer

Cervical cancer is one of the most common malignant diseases in women worldwide. Despite the global introduction of a preventive vaccine against the leading cause of cervical cancer, human papillomavirus (HPV) infection, the incidence of this malignant disease is still very high, especially in economically challenged areas. New advances in cancer therapy, especially the rapid development and application of different immunotherapy strategies, have shown promising pre-clinical and clinical results. However, mortality from advanced stages of cervical cancer remains a significant concern. Precise and thorough evaluation of potential novel anti-cancer therapies in pre-clinical phases is indispensable for efficient development of new, more successful treatment options for cancer patients. Recently, 3D tumor models have become the gold standard in pre-clinical cancer research due to their capacity to better mimic the architecture and microenvironment of tumor tissue as compared to standard two-dimensional (2D) cell cultures. This review will focus on the application of spheroids and patient-derived organoids (PDOs) as tumor models to develop novel therapies against cervical cancer, with an emphasis on the immunotherapies that specifically target cancer cells and modulate the tumor microenvironment (TME).

Quantifying the drug response of patient-derived organoid clusters by aggregated morphological indicators with multi-parameters based on optical coherence tomography

Patient-derived organoids (PDOs) serve as excellent tools for personalized drug screening to predict clinical outcomes of cancer treatment. However, current methods for efficient quantification of drug response are limited. Herein, we develop a method for label-free, continuous tracking imaging and quantitative analysis of drug efficacy using PDOs. A self-developed optical coherence tomography (OCT) system was used to monitor the morphological changes of PDOs within 6 days of drug administration. OCT image acquisition was performed every 24 h. An analytical method for organoid segmentation and morphological quantification was developed based on a deep learning network (EGO-Net) to simultaneously analyze multiple morphological organoid parameters under the drug's effect. Adenosine triphosphate (ATP) testing was conducted on the last day of drug treatment. Finally, a corresponding aggregated morphological indicator (AMI) was established using principal component analysis (PCA) based on the correlation analysis between OCT morphological quantification and ATP testing. Determining the AMI of organoids allowed quantitative evaluation of the PDOs responses to gradient concentrations and combinations of drugs. Results showed that there was a strong correlation (correlation coefficient >90%) between the results using the AMI of organoids and those from ATP testing, which is the standard test used for bioactivity measurement. Compared with single-time-point morphological parameters, the introduction of time-dependent morphological parameters can reflect drug efficacy with improved accuracy. Additionally, the AMI of organoids was found to improve the efficiency of 5-fluorouracil(5FU) against tumor cells by allowing the determination of the optimum concentration, and the discrepancies in response among different PDOs using the same drug combinations could also be measured. Collectively, the AMI established by OCT system combined with PCA could quantify the multidimensional morphological changes of organoids under the drug's effect, providing a simple and efficient tool for drug screening in PDOs.

Primary Human Pancreatic Cancer Cells Cultivation in Microfluidic Hydrogel Microcapsules for Drug Evaluation

Chemotherapy is an essential postoperative treatment for pancreatic cancer, while due to the lack of effective drug evaluation platforms, the therapeutic outcomes are hampered by tumor heterogeneity among individuals. Here, a novel microfluidic encapsulated and integrated primary pancreatic cancer cells platform is proposed for biomimetic tumor 3D cultivation and clinical drug evaluation. These primary cells are encapsulated into hydrogel microcapsules of carboxymethyl cellulose cores and alginate shells based on a microfluidic electrospray technique. Benefiting from the good monodispersity, stability, and precise dimensional controllability of the technology, the encapsulated cells can proliferate rapidly and spontaneously form 3D tumor spheroids with highly uniform size and good cell viability. By integrating these encapsulated tumor spheroids into a microfluidic chip with concentration gradient channels and culture chambers, dynamic and high-throughput drug evaluation of different chemotherapy regimens could be realized. It is demonstrated that different patient-derived tumor spheroids show different drug sensitivity on-chip, which is significantly consistent with the clinical follow-up study after the operation. The results demonstrate that the microfluidic encapsulated and integrated tumor spheroids platform has great application potential in clinical drug evaluation.

Fractionation and Characterization of Triterpenoids from Vaccinium vitis-idaea L. Cuticular Waxes and Their Potential as Anticancer Agents

Fruit and leaf cuticular waxes are valuable source materials for the isolation of triterpenoids that can be applied as natural antioxidants and anticancer agents. The present study aimed at the semi-preparative fractionation of triterpenoids from cuticular wax extracts of Vaccinium vitis-idaea L. (lingonberry) leaves and fruits and the evaluation of their cytotoxic potential. Qualitative and quantitative characterization of obtained extracts and triterpenoid fractions was performed using HPLC-PDA method, followed by complementary analysis by GC-MS. For each fraction, cytotoxic activities towards the human colon adenocarcinoma cell line (HT-29), malignant melanoma cell line (IGR39), clear renal carcinoma cell line (CaKi-1), and normal endothelial cells (EC) were determined using MTT assay. Furthermore, the effect of the most promising samples on cancer spheroid growth and viability was examined. This study allowed us to confirm that particular triterpenoid mixtures from lingonberry waxes may possess stronger cytotoxic activities than crude unpurified extracts. Fractions containing triterpenoid acids plus fernenol, complexes of oleanolic:ursolic acids, and erythrodiol:uvaol were found to be the most potent therapeutic candidates in the management of cancer diseases. The specificity of cuticular wax extracts of lingonberry leaves and fruits, leading to different purity and anticancer potential of obtained counterpart fractions, was also enclosed. These findings contribute to the profitable utilization of lingonberry cuticular waxes and provide considerable insights into the anticancer effects of particular triterpenoids and pharmacological interactions.

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

A storm in a teacup -- A biomimetic lung microphysiological system in conjunction with a deep-learning algorithm to monitor lung pathological and inflammatory reactions

Creating a biomimetic in vitro lung model to recapitulate the infection and inflammatory reactions has been an important but challenging task for biomedical researchers. The 2D based cell culture models - culturing of lung epithelium - have long existed but lack multiple key physiological conditions, such as the involvement of different types of immune cells and the creation of connected lung models to study viral or bacterial infection between different individuals. Pioneers in organ-on-a-chip research have developed lung alveoli-on-a-chip and connected two lung chips with direct tubing and flow. Although this model provides a powerful tool for lung alveolar disease modeling, it still lacks interactions among immune cells, such as macrophages and monocytes, and the mimic of air flow and aerosol transmission between lung-chips is missing. Here, we report the development of an improved human lung physiological system (Lung-MPS) with both alveolar and pulmonary bronchial chambers that permits the integration of multiple immune cells into the system. We observed amplified inflammatory signals through the dynamic interactions among macrophages, epithelium, endothelium, and circulating monocytes. Furthermore, an integrated microdroplet/aerosol transmission system was fabricated and employed to study the propagation of pseudovirus particles containing microdroplets in integrated Lung-MPSs. Finally, a deep-learning algorithm was developed to characterize the activation of cells in this Lung-MPS. This Lung-MPS could provide an improved and more biomimetic sensory system for the study of COVID-19 and other high-risk infectious lung diseases.

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.

Evaluation of AMG510 Therapy on KRAS-Mutant Non-Small Cell Lung Cancer and Colorectal Cancer Cell Using a 3D Invasive Tumor Spheroid System under Normoxia and Hypoxia

A 3D tumor spheroid has been increasingly applied in pharmaceutical development for its simulation of the tumor structure and microenvironment. The embedded-culture of a tumor spheroid within a hydrogel microenvironment could help to improve the mimicking of in vivo cell growth and the development of 3D models for tumor invasiveness evaluation, which could enhance its drug efficiency prediction together with cell viability detection. NCI-H23 spheroids and CT-26 spheroids, from a non-small cell lung cancer and colorectal cancer cell line, respectively, together with extracellular matrix were generated for evaluating their sensitivity to AMG510 (a KRAS^G12C inhibitor) under normoxia and hypoxia conditions, which were created by an on-stage environmental chamber. Results demonstrated that NCI-H23, the KRAS^G12C moderate expression cell line, only mildly responded to AMG510 treatment in normal 2D and 3D cultures and could be clearly evaluated by our system in hypoxia conditions, while the negative control CT-26 (G12D-mutant) spheroid exhibited no significant response to AMG510 treatment. In summary, our system, together with a controlled microenvironment and imaging methodology, provided an easily assessable and effective methodology for 3D in vitro drug efficiency testing and screenings.

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.

A comprehensive review on recent approaches for cancer drug discovery associated with artificial intelligence

Through the revolutionization of artificial intelligence (AI) technologies in clinical research, significant improvement is observed in diagnosis of cancer. Utilization of these AI technologies, such as machine and deep learning, is imperative for the discovery of novel anticancer drugs and improves existing/ongoing cancer therapeutics. However, building a model for complicated cancers and their types remains a challenge due to lack of effective therapeutics that hinder the establishment of effective computational tools. In this review, we exploit recent approaches and state-of-the-art in implementing AI methods for anticancer drug discovery, and discussed how advances in these applications need to be considered in the current cancer therapeutics. Considering the immense potential of AI, we explore molecular docking and their interactions to recognize metabolic activities that support drug design. Finally, we highlight corresponding strategies in applying machine and deep learning methods to various types of cancer with their pros and cons.

Super-Long SERS Active Single Silver Nanowires for Molecular Imaging in 2D and 3D Cell Culture Models

Establishing a systematic molecular information analysis strategy for cell culture models is of great significance for drug development and tissue engineering technologies. Here, we fabricated single silver nanowires with high surface-enhanced Raman scattering activity to extract SERS spectra in situ from two-dimensional (2D) and three-dimensional (3D) cell culture models. The silver nanowires were super long, flexible and thin enough to penetrate through multiple cells. A single silver nanowire was used in combination with a four-dimensional microcontroller as a cell endoscope for spectrally analyzing the components in cell culture models. Then, we adopted a machine learning algorithm to analyze the obtained spectra. Our results show that the abundance of proteins differs significantly between the 2D and 3D models, and that nucleic acid-rich and protein-rich regions can be distinguished with satisfactory accuracy.

Application of medical imaging methods and artificial intelligence in tissue engineering and organ-on-a-chip

Organ-on-a-chip (OOC) is a new type of biochip technology. Various types of OOC systems have been developed rapidly in the past decade and found important applications in drug screening and precision medicine. However, due to the complexity in the structure of both the chip-body itself and the engineered-tissue inside, the imaging and analysis of OOC have still been a big challenge for biomedical researchers. Considering that medical imaging is moving towards higher spatial and temporal resolution and has more applications in tissue engineering, this paper aims to review medical imaging methods, including CT, micro-CT, MRI, small animal MRI, and OCT, and introduces the application of 3D printing in tissue engineering and OOC in which medical imaging plays an important role. The achievements of medical imaging assisted tissue engineering are reviewed, and the potential applications of medical imaging in organoids and OOC are discussed. Moreover, artificial intelligence - especially deep learning - has demonstrated its excellence in the analysis of medical imaging; we will also present the application of artificial intelligence in the image analysis of 3D tissues, especially for organoids developed in novel OOC systems.

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.

Assay establishment and validation of a high-throughput organoid-based drug screening platform

BACKGROUND

Organoids are three-dimensional structures that closely recapitulate tissue architecture and cellular composition, thereby holding great promise for organoid-based drug screening. Although growing in three-dimensional provides the possibility for organoids to recapitulate main features of corresponding tissues, it makes it incommodious for imaging organoids in two-dimensional and identifying surviving organoids from surrounding dead cells after organoids being treated by irradiation or chemotherapy. Therefore, significant work remains to establish high-quality controls to standardize organoid analyses and make organoid models more reproducible.

METHODS

In this study, the Z-stack imaging technique was used for the imaging of three-dimensional organoids to gather all the organoids' maximum cross sections in one imaging. The combination of live cell staining fluorescent dye Calcein-AM and ImageJ assessment was used to analyze the survival of organoids treated by irradiation or chemotherapy.

RESULTS

We have established a novel quantitative high-throughput imaging assay that harnesses the scalability of organoid cultures. Using this assay, we can capture organoid growth over time, measure multiple whole-well organoid readouts, and show the different responses to drug treatments.

CONCLUSIONS

In summary, combining the Z-stack imaging technique and fluorescent labeling methods, we established an assay for the imaging and analysis of three-dimensional organoids. Our data demonstrated the feasibility of using organoid-based platforms for high-throughput drug screening assays.

PBPK Modeling on Organs-on-Chips: An Overview of Recent Advancements

Organ-on-a-chip (OoC) is a new and promising technology, which aims to improve the efficiency of drug development and realize personalized medicine by simulating in vivo environment in vitro. Physiologically based pharmacokinetic (PBPK) modeling is believed to have the advantage of better reflecting the absorption, distribution, metabolism and excretion process of drugs in vivo than traditional compartmental or non-compartmental pharmacokinetic models. The combination of PBPK modeling and organ-on-a-chip is believed to provide a strong new tool for new drug development and have the potential to replace animal testing. This article provides the recent development of organ-on-a-chip technology and PBPK modeling including model construction, parameter estimation and validation strategies. Application of PBPK modeling on Organ-on-a-Chip (OoC) has been emphasized, and considerable progress has been made. PBPK modeling on OoC would become an essential part of new drug development, personalized medicine and other fields.

Vascularized Tumor Spheroid-on-a-Chip Model Verifies Synergistic Vasoprotective and Chemotherapeutic Effects

Prolyl hydroxylases (PHD) inhibitors have been observed to improve drug distribution in mice tumors via blood vessel normalization, increasing the effectiveness of chemotherapy. These effects are yet to be demonstrated in human cell models. Tumor spheroids are three-dimensional cell clusters that have demonstrated great potential in drug evaluation for personalized medicine. Here, we used a perfusable vascularized tumor spheroid-on-a-chip to simulate the tumor microenvironment in vivo and demonstrated that the PHD inhibitor dimethylallyl glycine prevents the degradation of normal blood vessels while enhancing the efficacy of the anticancer drugs paclitaxel and cisplatin in human esophageal carcinoma (Eca-109) spheroids. Our results point to the potential of this model to evaluate anticancer drugs under more physiologically relevant conditions.

From cell spheroids to vascularized cancer organoids: Microfluidic tumor-on-a-chip models for preclinical drug evaluations

Chemotherapy is one of the most effective cancer treatments. Starting from the discovery of new molecular entities, it usually takes about 10 years and 2 billion U.S. dollars to bring an effective anti-cancer drug from the benchtop to patients. Due to the physiological differences between animal models and humans, more than 90% of drug candidates failed in phase I clinical trials. Thus, a more efficient drug screening system to identify feasible compounds and pre-exclude less promising drug candidates is strongly desired. For their capability to accurately construct in vitro tumor models derived from human cells to reproduce pathological and physiological processes, microfluidic tumor chips are reliable platforms for preclinical drug screening, personalized medicine, and fundamental oncology research. This review summarizes the recent progress of the microfluidic tumor chip and highlights tumor vascularization strategies. In addition, promising imaging modalities for enhancing data acquisition and machine learning-based image analysis methods to accurately quantify the dynamics of tumor spheroids are introduced. It is believed that the microfluidic tumor chip will serve as a high-throughput, biomimetic, and multi-sensor integrated system for efficient preclinical drug evaluation in the future.