Classification of Circulating Tumor Cells in Fluorescence Microscopy Images Based on SqueezeNet
説明
Circulating Tumor Cells (CTC) is expected as a useful biomarker test that can evaluate cancer metastasis. CTC exists in the blood of cancer patients and is considered to be an incentive of cancer metastasis. Pathologists analyze the blood to find these metastasis cancers from three colors of fluorescence microscopy images, but the manual analysis is time-consuming. In this paper, we develop an automatic CTC classification method in fluorescence microscopy images to reduce the burden of pathologists. In the proposed method, we detect cell regions by the bacterial foraging-based edge detection (BFED) algorithm and classify CTC by SqueezeNet, which is the kind of convolutional neural network (CNN). We apply the proposed method to 5040 microscopy images (6 samples) and evaluate the effectiveness. The experimental results demonstrate that the proposed method has a true positive rate is 89.86% and a false positive rate is 3.27%.
収録刊行物
-
- 2019 19th International Conference on Control, Automation and Systems (ICCAS)
-
2019 19th International Conference on Control, Automation and Systems (ICCAS) 1042-1045, 2019-10
IEEE