Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2023, 6(11); doi: 10.25236/AJCIS.2023.061112.

Research on the nucleus segmentation method based on improved U-Net network


Ruohuan Tang, Zhiyong Liu, Jianqiang Jia

Corresponding Author:
Ruohuan Tang

School of Intelligent Engineering and Intelligent Manufacturing, Hunan University of Technology and Business, Changsha, China


Medical image segmentation is a key technology in the field of medical image processing and analysis, which aims to segment special parts of medical images and extract relevant features to provide a reliable basis for clinical diagnosis and pathology research, and to assist doctors in making accurate judgments. Accurate nuclear segmentation is the basis of cell detection, cell classification and tumor grading, and has gradually attracted great attention from researchers in recent years. Due to the low contrast of nucleus images, large differences in the spatial distribution of nuclei, and easy formation of adhesions between cells, the accurate segmentation of nucleus images has become one of the difficult problems in medical image analysis. Based on the deep learning image segmentation algorithm and the U-Net network model, this paper designs a nucleus segmentation model based on ResNet residual blocks, and optimizes its network structure to achieve accurate segmentation of nucleus images.


nucleus segmentation; U-Net; ResNet; pathological images

Cite This Paper

Ruohuan Tang, Zhiyong Liu, Jianqiang Jia. Research on the nucleus segmentation method based on improved U-Net network. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 11: 88-94. https://doi.org/10.25236/AJCIS.2023.061112.


[1] Dytrych T, Launey KD, Draayer J P, et al. Physics of nuclei: Key role of an emergent symmetry[J].Physical Review Letters, 2020, 124(4):1-6.

[2] Phoulady H A, Goldgof D, Hall L O, et al. A framework for nucleus and overlapping cytoplasm segmentation in cervical cytology extended depth of field and volume images[J]. Computerized Medical Imaging and Graphics, 2017, 59: 38-49.

[3] Rajyalakshmi U, Rao S K, Prasad K S. Supervised classification of breast cancer malignancy using integrated modified marker controlled watershed approach[C]/2017 IEEE 7th International Advance Computing Conference (IACC). IEEE, 2017: 584-589.

[4] Kass M, Witkin A, Terzopoulous D. Snake: active contour models [C]//Proceedings of the 1st International Conference Oil Computer Vision London: IF_ Computer Society Press, 1987:259-268.

[5] Cui Y, Zhang G, Liu Z, et al. A deep learning algorithm for one-step contour aware nuclei segmentation of histopathology images[J]. Medical & biological engineering & computing, 2019, 57: 2027-2043.

[6] Kothari S, Chaudry Q, Wang M D. Automated cell counting and cluster segmentation using concavity detection and ellipse fitting techniques[C]//Boston, USA, IEEE International Symposium on Biomedical Imaging, 2009: 795-798.

[7] Oyebode K O, Tapamo J R. Adaptive parameter selection for graph cut-based segmentation on cell images[J]. Image Analysis Stereology, 2016, 35(1): 29-37.

[8] Li Y, Shen L, Yu S. HEp-2 specimen image segmentation and classification using very deep fully convolutional network[J]. IEEE Transactions on Medical Imaging, 2017, 36(7):1561-1572.

[9] Naylor, P., Laé, M., Reyal, F., Walter, T. Segmentation of nuclei in histopathology images by deep regression of the distance map[J]. IEEE Trans. Med. Imaging. 2018.

[10] Yang L, Xing FY, Xie YP. An automatic learning-based framework for robust nucleus segmentation[J]. IEEE Transactions on Medical Imaging, 2016, 35(2): 550-566.

[11] Fakhry A, Peng HC, Ji S. Deep models for brain EM image segmentation: Novel insights and improved performance. Bioinformtics, 2016, 32(15): 2352-2358.

[12] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation: MICCAI 2015, Cham, 2015[C]. Springer International Publishing, 2015.

[13] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.

[14] Ho Y, Wookey S. The real-world-weight cross-entropy loss function: Modeling the costs of mislabeling[J]. IEEE access, 2019, 8: 4806-4813.

[15] Deng M, Brägelmann J, Schultze J L, et al. Web-TCGA: an online platform for integrated analysis of molecular cancer data sets[J]. BMC bioinformatics, 2016, 17: 1-7.

[16] Shorten C, Khoshgoftaar T M. A survey on image data augmentation for deep learning[J]. Journal of big data, 2019, 6(1): 1-48.

[17] O'Shea K, Nash R. An introduction to convolutional neural networks[J]. arXiv preprint arXiv:1511.08458, 2015.