AI-organoid integrated systems for biomedical studies and applications

Abstract

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.

Keywords: artificial intelligence; deep learning; disease modeling; drug evaluation; human pluripotent stem cells (hPSCs); machine learning; organoid; regenerative medicine.

FIGURE 1

Integration of AI‐organoid system. Step 1: dataset construction from organoid imaging, function measurement, and multiomics; Step 2: data preprocessing based on data type; and Step 3: machine/deep learning model creation with a closed‐loop optimization by parameter/hyperparameter tuning, validation, and data visualization.

FIGURE 2

Overview of AI algorithms used in hPSC‐derived organoid research. (a) Linear regression for linear fitting. (b) Logistic regression for binary classification. (c) Support vector machine (SVM) showing maximized margins to determine an optimal hyperplane for classification purposes. (d) kNN with different k‐values for classification purposes. (e) Simple 2‐layerdecision tree hierarchy, (f) which can be further expanded into a random forest for classification purposes. (g) Artificial Neural Network (ANN) comprised of 10 neurons in three hidden layers with bias factors for classification purposes. (h) Convoluted Neural Network (CNN) with a 18‐layer ResNet architecture for image classification.

FIGURE 3

AI applications in hPSC‐organoids. AI‐enabled hPSC organoid research comprises a sequential workflow of organoid development and characterization, AI model establishment and optimization, and AI‐driven data analytics and predictions on organoid structural morphology, functional outputs, and drug responses.