Differentiating Engineered Tissue Images and Experimental Factors to Classify Cardiomyocyte Content.

In this study, we used machine learning (ML) to classify the cardiomyocyte (CM) content on day 10 of the differentiation of human-induced pluripotent stem cell (hiPSC)-laden microspheroids using easily acquirable nondestructive phase-contrast images taken in the middle of differentiation and tunable experimental parameters. Scale-up suspension culture, use of engineered tissues to support stem cell differentiation, and CM production for improved control over cellular microenvironment in the suspension system need nondestructive methods to track engineered tissue development. The ability to couple images that capture experimenter perceived "good" or "bad" batches based on visualization at early differentiation time points with actual experimental outcomes in an unbiased way is a step toward building these methods. In recent years, ML techniques have been successfully applied to identify critical process parameters and use this information to build models that describe process outcomes in cell production and hiPSC differentiation. Building upon these successes, here, we utilize convolutional neural networks (CNNs) to build a binary classifier model for CM content on differentiation day 10 (dd10) for hiPSC-CMs. We consider two separate data sets as potential input features for the classification models. The first set includes phase-contrast images of microspheroid tissues taken on days 3 and 5 of the differentiation batches at different experimental conditions. The second set supplements the images with tunable experimental differentiation parameters, such as cell concentration and microspheroids' size. The CM content classes were sufficient and insufficient. The accuracy of the CNN classifier using images only was 63%. The addition of experimental features increased the accuracy to 85%, indicating the importance of tunable parameters in predicting CM content. Impact statement Machine learning approaches were used to predict the final cardiomyocyte (CM) content class (sufficient vs. insufficient) of engineered cardiac tissue microspheroids produced through suspension-based cardiac differentiation of human-induced pluripotent stem cell-laden engineered tissue microspheroids. The models used specified experimental features and data collected using nondestructive inexpensive methods, specifically phase-contrast images taken during the initial days of differentiation as inputs. The best model was a convolutional neural network trained using experimental features and differentiation day 5 images. It classified the CM content with 85% accuracy and replicated and formalized experimenter's visual intuition about differentiation outcomes by incorporating images from early time points.

Human Induced Pluripotent Stem Cell Encapsulation Geometry Impacts Three-Dimensional Developing Human Engineered Cardiac Tissue Functionality.

Cardiac tissue engineering has been working to alleviate the immense burden of cardiovascular disease for several decades. To improve cardiac tissue homogeneity and cardiomyocyte (CM) maturation, in this study, we investigated altering initial encapsulation geometry in a three-dimensional (3D) direct cardiac differentiation platform. Traditional engineered cardiac tissue production utilizes predifferentiated CMs to produce 3D cardiac tissue and often involves various cell selection and exogenous stimulation methods to promote CM maturation. Starting tissue formation directly with human induced pluripotent stem cells (hiPSCs), rather than predifferentiated CMs, simplifies the engineered cardiac tissue formation process, making it more applicable for widespread implementation and scale-up. In this study, hiPSCs were encapsulated in poly (ethylene glycol)-fibrinogen in three tissue geometries (disc-shaped microislands, squares, and rectangles) and subjected to established cardiac differentiation protocols. Resulting 3D engineered cardiac tissues (3D-ECTs) from each geometry displayed similar CM populations (∼65%) and gene expression over time. Notably, rectangular tissues displayed less tissue heterogeneity and suggested more advanced features of maturing CMs, including myofibrillar alignment and Z-line formation. In addition, rectangular tissue showed significantly higher anisotropic contractile properties compared to square and microisland tissues (MI 0.28 ± 0.03, SQ 0.35 ± 0.05, RT 0.79 ± 0.04). This study demonstrates a straightforward method for simplifying and improving 3D-ECT production without the use of exogenous mechanical or electrical pacing and has the potential to be utilized in bioprinting and drug testing applications. Impact statement Current methods for improving cardiac maturation postdifferentiation remain tedious and complex. In this study, we examined the impact of initial encapsulation geometry on improvement of three-dimensional engineered cardiac tissue (3D-ECT) production and postdifferentiation maturation for three tissue geometries, including disc-shaped microislands, squares, and rectangles. Notably, rectangular 3D-ECTs displayed less tissue heterogeneity and more advanced features of maturing cardiomyocytes, including myofibrillar alignment, Z-line formation, and anisotropic contractile properties, compared to microisland and square tissues. This study demonstrates an initial human induced pluripotent stem cell-encapsulated rectangular tissue geometry can improve cardiac maturation, rather than implementing cell selection or tedious postdifferentiation manipulation, including exogenous mechanical and/or electrical pacing.

Engineered cardiac tissue microsphere production through direct differentiation of hydrogel-encapsulated human pluripotent stem cells.

Engineered cardiac tissues that can be directly produced from human induced pluripotent stem cells (hiPSCs) in scalable, suspension culture systems are needed to meet the demands of cardiac regenerative medicine. Here, we demonstrate successful production of functional cardiac tissue microspheres through direct differentiation of hydrogel encapsulated hiPSCs. To form the microspheres, hiPSCs were suspended within the photocrosslinkable biomaterial, PEG-fibrinogen (25 million cells/mL), and encapsulated at a rate of 420,000 cells/minute using a custom microfluidic system. Even at this high cell density and rapid production rate, high intra-batch and batch-to-batch reproducibility was achieved. Following microsphere formation, hiPSCs maintained high cell viability and continued to grow within and beyond the original PEG-fibrinogen matrix. These initially soft microspheres (<250 Pa) supported efficient cardiac differentiation; spontaneous contractions initiated by differentiation day 8, and the microspheres contained >75% cardiomyocytes (CMs). CMs responded appropriately to pharmacological stimuli and exhibited 1:1 capture up to 6.0 Hz when electrically paced. Over time, cells formed cell-cell junctions and aligned myofibril fibers; engineered cardiac microspheres were maintained in culture over 3 years. The capability to rapidly generate uniform cardiac microsphere tissues is critical for advancing downstream applications including biomanufacturing, multi-well plate drug screening, and injection-based regenerative therapies.