Abstract
Robust detection and numeration of circulating tumor cells (CTCs) in scanned microscopic images of peripheral blood is essential to clinical diagnosis, individualized treatment, and prognosis judgement evaluation. Automated detection algorithm based on machine learning methods helps to reduce the subjectivity and labor intensity of cytologists in their clinical practice. In this paper, a robust CTCs detection algorithm based on cascading of two stages of detectors is proposed. Firstly, a morphological rule based detector is applied to screen out most normal cells. Based on the detection results of the first stage detection, hard negative sample selection is performed according to confidence score values of an integrated deep classifier. Finally, a second stage faster R-CNN detector is trained on positive and negative samples to obtain the detection results. Experimental results carried out on a self-established CTCs database show that the proposed algorithm achieves robust and quasi-realtime CTCs detection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Plaks, V., Koopman, C.D., Werb, Z.: Circulating tumor cells. Cancer Biol. Ther. 341(6151), 1186–1188 (2013)
Paterlini-Brechot, P., Benali, N.L.: Circulating tumor cells (CTC) detection: clinical impact and future directions. Cancer Lett. 253(2), 180–204 (2007)
Mostert, B., Sleijfer, S., Foekens, J.A., et al.: Circulating tumor cells (CTCs): detection methods and their clinical relevance in breast cancer. Cancer Treat. Rev. 35(5), 463 (2009)
Heo, Y.J., Lee, D., Kang, J., Lee, K., Chung, W.K.: Real-time image processing for microscopy-based label-free imaging flow cytometry in a microfluidic chip. Sci. Rep. 7(1), 11651 (2017)
Adams, D.L., et al.: Cytometric characterization of circulating tumor cells captured by microfiltration and their correlation to the cellsearch® CTC test. Cytometry A 87(2), 137–144 (2015)
Svensson, C.M., Krusekopf, S., Lücke, J., Thilo, F.M.: Automated detection of circulating tumor cells with naive bayesian classifiers. Cytometry Part A 85(6), 501–511 (2014)
Pinzani, P., Salvadori, B., Simi, L., et al.: Isolation by size of epithelial tumor cells in peripheral blood of patients with breast cancer: correlation with real-time reverse transcriptase–polymerase chain reaction results and feasibility of molecular analysis by laser microdissection. Hum. Pathol. 37(6), 711–718 (2006)
Ntouroupi, T.G., Ashraf, S.Q., McGregor, S.B., et al.: Detection of circulating tumour cells in peripheral blood with an automated scanning fluorescence microscope. Br. J. Cancer 99(5), 789–795 (2008)
Liu, Y.X., Yang, Y., Chen, Y.H.: Automatic detection of circulating tumor cells based on microscopic images. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 769–773. IEEE (2017)
Xu, J., Xiang, L., Liu, Q., et al.: Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE Trans. Med. Imaging 35(1), 119–130 (2016)
Xie, Y., Xing, F., Shi, X., et al.: Efficient and robust cell detection: a structured regression approach. Med. Image Anal. 44, 245–254 (2018)
Zhang, A., Zou, Z., Liu, Y., et al.: Automated detection of circulating tumor cells using faster region convolution neural network. J. Med. Imaging Health Inform. 9(1), 167–174 (2019)
Hofman, V., Long, E., Ilie, M., Llie, M., Vignaud, J.M., Fléjou, J.F.: Morphological analysis of circulating tumour cells in patients undergoing surgery for non-small cell lung carcinoma using the isolation by size of epithelial tumour cell (ISET) method. Cytopathology Off. J. Br. Soc. Clin. Cytol. 23(1), 30–38 (2012)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Addison Wesley, San Francisco (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, YX., Zhang, AJ., Meng, QF., Chen, YJ., Yang, Y., Chen, YH. (2019). Robust Circulating Tumor Cells Detection in Scanned Microscopic Images with Cascaded Morphological and Faster R-CNN Deep Detectors. In: Huang, DS., Jo, KH., Huang, ZK. (eds) Intelligent Computing Theories and Application. ICIC 2019. Lecture Notes in Computer Science(), vol 11644. Springer, Cham. https://doi.org/10.1007/978-3-030-26969-2_70
Download citation
DOI: https://doi.org/10.1007/978-3-030-26969-2_70
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26968-5
Online ISBN: 978-3-030-26969-2
eBook Packages: Computer ScienceComputer Science (R0)