Related Experiment Video
Updated: Jun 25, 2025
Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
Published on: April 30, 2021
Deep learning unlocks label-free viability assessment of cancer spheroids in microfluidics
Chun-Cheng Chiang1,2, Rajiv Anne1,3, Pooja Chawla3
1UPMC Hillman Cancer Center, University of Pittsburgh, 5115 Centre Ave, Pittsburgh, PA 15232, USA. cheny25@upmc.edu.
Abstract:
Despite recent advances in cancer treatment, refining therapeutic agents remains a critical task for oncologists. Precise evaluation of drug effectiveness necessitates the use of 3D cell culture instead of traditional 2D monolayers. Microfluidic platforms have enabled high-throughput drug screening with 3D models, but current viability assays for 3D cancer spheroids have limitations in reliability and cytotoxicity. This study introduces a deep learning model for non-destructive, label-free viability estimation based on phase-contrast images, providing a cost-effective, high-throughput solution for continuous spheroid monitoring in microfluidics. Microfluidic technology facilitated the creation of a high-throughput cancer spheroid platform with approximately 12 000 spheroids per chip for drug screening. Validation involved tests with eight conventional chemotherapeutic drugs, revealing a strong correlation between viability assessed via LIVE/DEAD staining and phase-contrast morphology. Extending the model's application to novel compounds and cell lines not in the training dataset yielded promising results, implying the potential for a universal viability estimation model. Experiments with an alternative microscopy setup supported the model's transferability across different laboratories. Using this method, we also tracked the dynamic changes in spheroid viability during the course of drug administration. In summary, this research integrates a robust platform with high-throughput microfluidic cancer spheroid assays and deep learning-based viability estimation, with broad applicability to various cell lines, compounds, and research settings.
Insights
This study presents a deep learning model for non-destructive, label-free cancer spheroid viability assessment using phase-contrast imaging. This cost-effective, high-throughput method enhances drug screening in microfluidic platforms.
Area of Science:
- Oncology
- Biotechnology
- Artificial Intelligence
Background:
- Refining cancer therapeutics requires accurate drug effectiveness evaluation using 3D cell cultures.
- Traditional 2D cell cultures and current 3D viability assays have limitations in reliability and cytotoxicity.
- Microfluidic platforms offer high-throughput screening capabilities for 3D cancer models.
Purpose of the Study:
- To develop a non-destructive, label-free deep learning model for estimating cancer spheroid viability.
- To establish a cost-effective, high-throughput solution for continuous spheroid monitoring in microfluidic drug screening.
- To validate the model's performance and assess its potential for universal application.
Main Methods:
- Development of a deep learning model analyzing phase-contrast images of 3D cancer spheroids.
- Utilization of microfluidic technology to create a high-throughput platform for generating approximately 12,000 spheroids per chip.
- Validation using eight conventional chemotherapeutic drugs and comparison with LIVE/DEAD staining.
Main Results:
- The deep learning model demonstrated strong correlation with traditional viability assays.
- The model showed promising results with novel compounds and cell lines, suggesting potential for universal applicability.
- The method proved transferable across different microscopy setups and allowed tracking of dynamic viability changes.
Conclusions:
- The integrated platform combines high-throughput microfluidic assays with deep learning for robust spheroid viability estimation.
- This approach offers a cost-effective and reliable alternative for cancer drug screening.
- The model has broad applicability across various cell lines, compounds, and research settings.
