Circulating tumor cells (CTCs) are essential biomarkers for cancer prognosis, yet their extreme rarity and biological heterogeneity pose significant challenges for label-free detection. This study presents an automated, non-invasive classification framework integrating a self-assembly cell array (SACA) microfluidic chip with hyperspectral imaging (HSI) and deep learning. By utilizing the SACA chip’s 5 µm gap design, patient-derived blood samples were organized into a flattened monolayer, ensuring high-purity spectral acquisition by minimizing cell overlapping. We implemented two deep-learning pipelines: an Attention-Based Adaptive Spectral–Spatial Kernel ResNet (A2S2K-ResNet) for pixel-level feature extraction and a modified ResNet50 for structural image analysis. While spectral classification achieved ~80% accuracy for cultured cell lines, its performance on patient-derived CTCs was hindered by subtle spectral overlap with white blood cells (WBCs). To overcome this, a multi-band ensemble strategy using majority voting across seven optimized spectral bands (470–900 nm) was developed. This hybrid approach significantly enhanced detection robustness, achieving an overall accuracy of >93.5% and precision exceeding 92%. These results demonstrate that combining microfluidic spatial control with multi-band deep learning offers a reliable, label-free pipeline for clinical liquid biopsy and real-time cancer monitoring.
Wu et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: