Abstract—Circulating Tumor Cells (CTC) are expected to be a useful biomarker for cancer metastasis. CTC analysis can be used to assess cancer status and the therapeutic effects of anticancer drugs. Pathologists analyze blood samples from images taken with a fluorescence microscope. However, the number of CTCs in blood is very small, which is a time-consuming task. In this paper, we propose an automatic CTC identification method from fluorescence microscopy images. In the proposed method, we detect cell regions using a selective enhancement filter and blob analysis. Then, we identify the CTC using a SqueezeNet-based Convolutional Neural Network (CNN) model with Spatial Pyramid Pooling (SPP). We apply the proposed method to 5040 microscopy images and evaluate its effectiveness. The experimental results show that the proposed method has a true positive rate of 97.30%, a false positive rate of 2.069%, and an Area Under the Curve (AUC) of 0.991.
 
Keywords—Circulating Tumor Cells (CTC), fluorescence microscopy images, SqueezeNet, Spatial Pyramid Pooling (SPP)


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).