Abstract LB109: An automated approach for real-time monitoring of circulating tumor cells (CTC) tumoroid development

Abstract Monitoring circulating tumor cells (CTC) tumoroid formation remains a critical challenge in cancer research, with current methods heavily dependent on subjective microscopic assessment. This study presents an automated methodology for quantitative and real-time monitoring of CTC tumoroid development with an advanced image segmentation AI model. Our novel approach enables objective characterization of tumoroid formation by distinguishing target cells from complex culture backgrounds, thereby eliminating personnel bias and reducing reliance on expertise. Leveraging SAM2’s enhanced tracking capabilities and improved zero-shot segmentation accuracy, our system extracts critical parameters including cell count, area, and clustering patterns. The integration of time-series image analysis enables comprehensive monitoring of culture progression and early detection of potential amplification failures. This methodology provides researchers with reliable, standardized metrics for assessing CTC culture and tumoroid-forming status prior to chemical bioactivity testing.The potential implications of this research are significant, as it highlights the ability to reduce patient waiting times by enabling early determination of culture success. This, in turn, minimizes the need for sample recollection and facilitates further application and analysis, such as anti-tumor drug testing. This advancement represents a crucial step toward optimizing personalized cancer treatment strategies. Citation Format: Hao-Ting Lee, Po-Han Chen, Ting-Ying Chien, Shihpei Wu, Wei-Hsin Dai, Ting-Chun Liu. An automated approach for real-time monitoring of circulating tumor cells (CTC) tumoroid development [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_2):Abstract nr LB109.