Evolution of Metastasis Study Models toward Metastasis-On-A-Chip: The Ultimate Model?

For decades, several attempts have been made to obtain a mimetic model for the study of metastasis, the reason of most of deaths caused by cancer, in order to solve the unknown phenomena surrounding this disease. To better understand this cellular dissemination process, more realistic models are needed that are capable of faithfully recreating the entire and essential tumor microenvironment (TME). Thus, new tools known as tumor-on-a-chip and metastasis-on-a-chip have been recently proposed. These tools incorporate microfluidic systems and small culture chambers where TME can be faithfully modeled thanks to 3D bioprinting. In this work, a literature review has been developed about the different phases of metastasis, the remaining unknowns and the use of new models to study this disease. The aim is to provide a global vision of the current panorama and the great potential that these systems have for in vitro translational research on the molecular basis of the pathology. In addition, these models will allow progress toward a personalized medicine, generating chips from patient samples that mimic the original tumor and the metastatic process to perform a precise pharmacological screening by establishing the most appropriate treatment protocol.

Using deep learning for predicting the dynamic evolution of breast cancer migration.

BACKGROUND: Breast cancer (BC) remains a prevalent health concern, with metastasis as the main driver of mortality. A detailed understanding of metastatic processes, particularly cell migration, is fundamental to improve therapeutic strategies. The wound healing assay, a traditional two-dimensional (2D) model, offers insights into cell migration but presents scalability issues due to data scarcity, arising from its manual and labor-intensive nature. METHOD: To overcome these limitations, this study introduces the Prediction Wound Progression Framework (PWPF), an innovative approach utilizing Deep Learning (DL) and artificial data generation. The PWPF comprises a DL model initially trained on artificial data that simulates wound healing in MCF-7 BC cell monolayers and spheres, which is subsequently fine-tuned on real-world data. RESULTS: Our results underscore the model's effectiveness in analyzing and predicting cell migration dynamics within the wound healing context, thus enhancing the usability of 2D models. The PWPF significantly contributes to a better understanding of cell migration processes in BC and expands the possibilities for research into wound healing mechanisms. CONCLUSIONS: These advancements in automated cell migration analysis hold the potential for more comprehensive and scalable studies in the future. Our dataset, models, and code are publicly available at https://github.com/frangam/wound-healing.