ORIGINAL RESEARCH article
Front. Comput. Sci.
Sec. Computer Vision
Volume 7 - 2025 | doi: 10.3389/fcomp.2025.1562358
This article is part of the Research TopicFoundation Models for Healthcare: Innovations in Generative AI, Computer Vision, Language Models, and Multimodal SystemsView all 8 articles
Leveraging Foundation Models and Goal-Dependent Annotations for Automated Cell Confluence Assessment
Provisionally accepted
- 1Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Leipzig University, Leipzig, Germany
- 2Center for Regenerative Therapies Dresden, Technical University Dresden, Dresden, Lower Saxony, Germany
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Mesenchymal stem cell therapy shows promising results for difficult-to-treat diseases, but manufacturing requires robust quality control through cell confluence monitoring. While deep learning can automate confluence estimation, research on cost-effective dataset curation and the role of foundation models in this task is limited. We investigate effective strategies for AI-based confluence estimation by studying active learning, goal-dependent labeling, and foundation models without any training and labeling effort (zero-shot). Here, we show that zero-shot inference with the Segment Anything Model (SAM) achieves excellent confluence estimation without any task-specific training, outperforming even fine-tuned and specialized models. Further, our findings demonstrate that active learning does not significantly improve training and performance compared to random selection of training samples in homogeneous cell datasets. We show that streamlined labeling approaches tailored to specific goals perform similarly to exhaustive, time-consuming annotation methods.Our results challenge common assumptions about dataset curation and model training: neither active learning nor extensive fine-tuning provided significant benefits for our real-world scenarios. Instead, we found that leveraging SAM's zero-shot capabilities and goal-dependent labeling offers the most cost-effective approach for AI-based confluence monitoring. Our work provides practical guidelines for implementing automated cell quality control in MSC manufacturing, demonstrating that extensive dataset curation may be unnecessary when foundation models can effectively handle the task out of the box
Keywords: Active Learning, deep learning, Cell segmentation, Segment Anything Model, Computer Vision
Received: 17 Jan 2025; Accepted: 03 Jun 2025.
Copyright: © 2025 Joas, Freund, Haase, Rahm and Ewald. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Maximilian Joas, Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Leipzig University, Leipzig, Germany
Jan Ewald, Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Leipzig University, Leipzig, Germany
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.