ABSTRACT
Detection and quantification of cells in general is one of the key challenges in many clinical trials for disease diagnosis and monitoring. Automation of this task enables quantitative analysis of digital images with a high processing rate, which is a support to pathologist at various kind of analyses. Recent studies have already indicated that deep learning usually yield superior accuracy in the field of digital pathology. One of the challenges tackled by the researches is to detect cells in images when cells are highly overlapped, over illuminated or partially occluded with the noise. Therefore, we focused on two conceptually different deep learning models, specifically U-Net and Mask R-CNN, in order to evaluate their capability and performance on the detection of overlapping cells. The dataset used in the study contains different types of images, possible observed under different lighting conditions, and the amount of target cells may range from tens to thousands, therefore the algorithm is required to be flexible enough.
- Höfener, H., Homeyer, A., Weiss, N., Molin, J., Lundström, C. F. and Hahn, H. K. 2018. Deep learning nuclei detection: A simple approach can deliver state-of-the-art results. Computerized Medical Imaging and Graphics, 70, 43--52. DOI= 10.1016/j.compmedimag.2018.08.010.Google ScholarCross Ref
- Xing, F. and Yang L. 2016. Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review. IEEE Rev Biomed Eng. 9, 234--263. DOI= 10.1109/RBME.2016.2515127.Google ScholarCross Ref
- Xue, Y. and Ray, N. 2018. Cell Detection in Microscopy Images with Deep Convolutional Neural Network and Compressed Sensing, 1--29 arXiv:1708.03307, https://arxiv.org/abs/1708.03307Google Scholar
- Deng, L. and Yu, D. (2013). Deep learning: methods and applications. Foundations and Trends in Signal Processing, 3(3-4). 197--387Google ScholarDigital Library
- LeCun, Y., Bengio, Y. and Hinton, G. 2015. Deep learning. Nature, 521(28), 436--444.Google ScholarCross Ref
- Khoshdeli, M., Cong, R. and Parvin, B. 2017. Detection of nuclei in H&E stained sections using convolutional neural networks. IEEE EMBS Int Conf Biomed Health Inform, 105--108. DOI= doi: 10.1109/BHL.2017.7897216Google Scholar
- Song, Y., Zhang, L., Chen, S., Ni, D., Lei, B. and Wang, T. 2015. Accurate segmentation of cervical cytoplasm and nuclei based on multi-scale convolutional network and graph partitioning. IEEE Trans. Biomed. Eng., 62(10), 2421--2433.Google ScholarCross Ref
- Xie, Y., Kong, X., Xing, F., Liu, F., Su, H. and Yang, L. 2015. Deep Voting: A Robust Approach Toward Nucleus Localization in Microscopy Images. Med Image Comput. Assist. Interv., 9351, 374--382. DOI: 10.1007/978-3-319-24574-4_45.Google Scholar
- Shu, J., Fu, H., Qiu, G., Kaye. P. and Ilyas, M. 2013. Segmenting overlapping cell nuclei in digital histopathology images. In Proc. IEEE 35th Annu. Int. Conf. Eng. Med. Biol. Soc., 5445--5448. DOI: 10.1109/EMBC.2013.6610781Google Scholar
- Kong, J., Cooper, L., Kurc, T., Brat, D. and Saltz, J. 2011. Towards building computerized image analysis framework for nucleus discrimination in microscopy images of diffuse glioma. In Proc. IEEE 33rd Annu. Int. Conf. Eng. Med. Biol. Soc., USA, 6605--6608.Google Scholar
- Veta, M., Huisman, A., Viergever, M. A., van Diest, P. J. and Pluim, J. P. W. 2011. Marker-controlled watershed segmentation of nuclei in H & E stained breast cancer biopsy images. In Proc. 8th IEEE Int. Symp. Biomed. Imag., 618--621.Google Scholar
- Ali, S. and Madabhushi, A. 2012. An integrated region boundary, shape based active contour for multiple object overlap solution in histological imagery. IEEE Trans. Med. Imag., 31(7), 1448--1460.Google ScholarCross Ref
- Jung, C., Kim, C., Chae, S.W. and Oh, S. 2010. Unsupervised segmentation of overlapped nuclei using Bayesian classification. IEEE Trans. Biomed. Eng., 57(12), 2825--2832.Google ScholarCross Ref
- Vuola, A. O., Ullah, S. and Kannala, A. J. 2019. Mask-RCNN and U-Net Ensembled for Nuclei Segmentation. In IEEE International Symposium on Biomedical Imaging (ISBI) 2019, 1--5. arXiv:1901.10170, https://arxiv.org/pdf/1901.10170.pdfGoogle Scholar
- Ronneberger, O., Fischer, P. and Brox, T. 2015. U-Net: Convolutional Networks for Biomedical Image segmentation. arXiv:1505.04597, https://arxiv.org/abs/1505.04597Google Scholar
- He, K., Gkioxari, G., Dollar, P. and Girshick, R. B. (2017). Mask R-CNN. arXiv:1703.06870, https://arxiv.org/abs/1703.06870Google Scholar
- Arbuckle, C. L., Greenberg, M. L. and Linstead, E. J. 2015. Detection and tracking of T cells in time-lapse imaging. In BCB '15 Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics (Atlanta, Georgia -- September 09-12, 2015). ACM, New York, NY, 545--546. DOI= 10.1145/2808719.2811457Google ScholarDigital Library
Index Terms
- Deep Learning-based Detection of Overlapping Cells
Recommendations
Accurate segmentation of overlapping cells in cervical cytology with deep convolutional neural networks
AbstractAccurate cell segmentation is essential for computer-aided diagnosis of cervical precancerous lesions in cytology images. Automated segmentation poses a great challenge due to the presence of fuzzy and overlapping cells, noisy ...
Splitting of Overlapping Cells in Peripheral Blood Smear Images by Concavity Analysis
IWCIA 2014: Proceedings of the 16th International Workshop on Combinatorial Image Analysis - Volume 8466The diagnosis of a patient's pathological condition, through theï źstudy of peripheral blood smear images, is a highly complicated process, the results of which require high levels of precision. In order to analyze the cells in the images individually, ...
Subtype Cell Detection with an Accelerated Deep Convolution Neural Network
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016AbstractRobust cell detection in histopathological images is a crucial step in the computer-assisted diagnosis methods. In addition, recent studies show that subtypes play an significant role in better characterization of tumor growth and outcome ...
Comments