Abstract
It is necessary to realize the automatic detection of cervical cells in Pap Smears. We present an automatic cervical cell detection approach based on the so-called Dense-Cascade R-CNN (Dense-Cascade Region-based Convolutional Neural Networks). The approach consists of three modules: data augmentation, training set balancing (TSB), and the Dense-Cascade R-CNN. The data augmentation module carries out operations such as rotation, scale, flip, etc. on input images to increase the samples. The TSB module is used to balance the number of cervical cell samples of various classes in the training set after data augmentation. As for the Dense-Cascade R-CNN module, the residual neural network (ResNet) with 101 layers in a Cascade R-CNN is replaced by a dense connected convolution neural network (DenseNet) with 121 layers so as to improve the detection performance of cervical cells. We evaluated the proposed method on the Herlev dataset. The results show that our approach can improve both mean average precision (mAP) and mean average recall (mAR) for Cascade R-CNN. Our cervical cell automatic detection approach can be used as an auxiliary diagnostic tool for cervical cancer screening.
L. Yi and Y. Lei—These authors contributed equally to this work and should be considered co-first authors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, P., Wang, L., Li, Y., Song, Q., Lv, S., Hu, X.: Automatic cell nuclei segmentation and classification of cervical pap smear images. Biomed. Sig. Process. Control 48, 93–103 (2019)
Kurnianingsih, et al.: Segmentation and classification of cervical cells using deep learning. IEEE Access 7, 116925–116941 (2019)
Sompawong, N., et al.: Automated pap smear cervical cancer screening using deep learning. In: 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 7044–7048. Institute of Electrical and Electronics Engineers Inc., Berlin (2019)
Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936–944. Institute of Electrical and Electronics Engineers Inc., Honolulu (2017)
Kermany, D.S., et al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5), 1122–1131 (2018)
Zhang, L., Lu, L., Nogues, I., Summers, R.M., Liu, S., Yao, J.: DeepPap: deep convolutional networks for cervical cell classification. IEEE J. Biomed. Health Inform. 21(6), 1633–1643 (2017)
Liu, R., Zhang, Y., Zheng, Y., Liu, Y., Zhao, Y., Yi, L.: Automated detection of vulnerable plaque for intravascular optical coherence tomography images. Cardiovasc. Eng. Technol. 10(4), 590–603 (2019). https://doi.org/10.1007/s13239-019-00425-2
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)
Chiu, T.Y.: Understanding generalized whitening and coloring transform for universal style transfer. In: 17th IEEE/CVF International Conference on Computer Vision (ICCV), pp. 4451–4459. Institute of Electrical and Electronics Engineers Inc., Seoul (2019)
Reiche, B., Moody, A.R., Khademi, A.: Effect of image standardization on FLAIR MRI for brain extraction. SIViP 9(1 supplement), 11–16 (2015)
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386–397 (2018)
Gao, H., Zhuang, L., Maaten, L.V.D., Weinberger, K.Q.: Densely connected convolutional networks. In: 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269. Institute of Electrical and Electronics Engineers Inc., Honolulu (2017)
Singh, K.R., Chaudhury, S.: A cascade network for the classification of rice grain based on single rice Kernel. Complex Intell. Syst. 6, 321–334 (2020)
Acknowledgment
This work was supported in part by the Fundamental Research Funds for the Central Universities (2018CDXYJSJ0026, 2019CDYGZD004); the Chongqing Foundation and Advanced Research Project (cstc2019jcyj-msxmX0622); the Science and Technology Research Program of Chongqing Municipal Education Commission (KJQN201800111), the Sichuan Science and Technology Program (2019YFSY0026), and the Entrepreneurship and Innovation Program for Chongqing Overseas Returned Scholars (No. cx2017094).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
The supplementary materials (including the source code of the proposed approach) for this paper can be downloaded from https://github.com/threedteam/cell_detection.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yi, L., Lei, Y., Fan, Z., Zhou, Y., Chen, D., Liu, R. (2020). Automatic Detection of Cervical Cells Using Dense-Cascade R-CNN. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12306. Springer, Cham. https://doi.org/10.1007/978-3-030-60639-8_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-60639-8_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60638-1
Online ISBN: 978-3-030-60639-8
eBook Packages: Computer ScienceComputer Science (R0)