Objective:

Our study develops a generative adversarial network (GAN)-based method that generates faithful synthetic image data of human cardiomyocytes at varying stages in their maturation process, as a tool to significantly enhance the classification accuracy of cells and ultimately assist the throughput of computational analysis of cellular structure and functions.

Methods:

Human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) were cultured on micropatterned collagen coated hydrogels of varied stiffness on which structural and optical measurements were performed to analyze their structural and functional maturation. Control groups were cultured on collagen coated glass well plates. These image recordings were used as the real data to train the GAN model.

Results:

: The GAN approach was able to replicate true features from the real data, and inclusion of such synthetic data significantly improved the classification accuracy compared to he exclusive usage of only real experimental data limited in scale and diversity.

Conclusion:

The proposed model outperformed four conventional machine learning algorithms by incorporating synthetic data to improve both data generalization and classification. Significance: This work demonstrates the potential utility of integrating synthetic data to effectively address the challenges imposed by constrained data.