AI summaryⓘ
The authors developed a method to better identify types of circulating tumor cells (CTCs) by analyzing their movement through a special microfluidic device without using labels. They created a deep learning technique called Subsequence (SubSeq) that focuses on small parts of the cell’s path to improve learning from limited data. This method not only enhances classification accuracy but also helps explain which parts of the trajectory and device influence the predictions. Their work shows that short trajectory segments carry important physical information, suggesting full paths may have redundant data. Overall, the study offers new insights into how microfluidic devices capture cell properties and how these can be used to design better diagnostic tools.
circulating tumor cellsmicrofluidicstrajectory analysisdeep neural networksdata augmentationcell deformabilitygradient-weighted class activation mappingphenotype classificationbiophysical propertieslabel-free detection
Authors
Serena Su, Yifan Wang, Senwei Liang
Abstract
Accurate classification of circulating tumor cell (CTC) phenotypes can provide valuable information for assessing metastatic potential. Label free microfluidic devices provide a hydrodynamic obstacle course that transforms subtle biophysical characteristics of CTCs, including size and deformability, into distinct kinematic trajectories. However, the highly nonlinear fluid structure interactions governing these trajectories make the inverse problem of inferring cellular phenotype from trajectory data analytically intractable. While deep neural networks (DNNs) have emerged as a powerful approach for addressing this inverse problem, their effectiveness is constrained by the limited availability of trajectory data and the lack of physical interpretability. To address these challenges, we propose an interpretable and data efficient DNN framework for trajectory based CTC classification. To mitigate the scarcity of data, we develop Subsequence (SubSeq), a targeted augmentation strategy that randomly extracts informative local trajectory segments during training to promote learning from localized patterns. We further apply Gradient Weighted Class Activation Mapping to identify the trajectory features and physical regions of the microfluidic device that drive model predictions. Experimental results demonstrate that SubSeq improves classification accuracy over the evaluated baseline and augmentation methods. Furthermore, interpretability analysis suggests that localized trajectory segments contain substantial biophysical information relevant to accurate classification. This provides justification for SubSeq and also highlights the redundancy of full-length trajectories. More broadly, the proposed framework views microfluidic geometries as physical encoders of cellular mechanical properties, providing mechanistic insights that may inform the future design of diagnostic devices.