Comparative analysis of deep learning neural networks for the segmentation of cancer cell nuclei on immunohistochemical fluorescent images

Authors

  • Silun Xu Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus
  • Viktor V. Skakun Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus

Keywords:

immunohistochemical images, cancer cells images, nuclear segmentation, neural networks, deep learning, U-Net

Abstract

The analysis of histological and immunohistochemical images forms the basis for the diagnosis of many types of cancer. The process of automating the analysis of digital images, in particular, the segmentation of cell nuclei on them, is of great attention recently. Due to the excellent performance of deep learning neural networks and the relatively high level of reliability of the obtained results, it becomes possible to combine manual and automated image processing. To date, many neural network architectures have been created for segmenting objects in images. However, the high variability of images of cancer cells does not allow creating an universal algorithm for segmenting the cells nuclei on images of different types of tissues obtained using different techniques. In this paper, a comparative analysis of the architectures of deep learning neural networks for segmentation of cancer cell nuclei on immunohistochemical fluorescent images of breast cancer was carried out. It was established that networks based on the U-Net architecture give consistently good results. The UNet 3+ architecture showed the best segmentation quality.

Author Biographies

  • Silun Xu , Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus

    competitor at the department of system analysis and computer simulation, faculty of radiophysics and computer technologies



  • Viktor V. Skakun, Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus

    PhD (physics and mathematics), docent; associate professor at the department of system analysis and computer simulation, faculty of radiophysics and computer technologies

     

References

  1. Chung GG, Zerkowski MP, Ghosh S, Camp RL, Rimm DL. Quantitative analysis of estrogen receptor heterogeneity in breast cancer. Laboratory Investigation. 2007;87(7):662–669. DOI: 10.1038/labinvest.3700543.
  2. Camp RL, Chung GG, Rimm DL. Automated subcellular localization and quantification of protein expression in tissue microarrays. Nature Medicine. 2002;8(11):1323–1328. DOI: 10.1038/nm791.
  3. Todewale NS. Lesion segmentation from mammogram images using a U-Net deep learning network. International Journal of Engineering Research and Technology. 2020;9(2):406–411.
  4. Lagree A, Mohebpour M, Meti N, Saednia K, Lu Fang-I, Slodkowska E, et al. A review and comparison of breast tumor cell nuclei segmentation performances using deep convolutional neural networks. Scientific Reports. 2021;11:8025. DOI: 10.1038/s41598-021-87496-1.
  5. Lisitsa YV, Yatskou MM, Apanasovich VV, Apanasovich TV. Algorithm for automatic segmentation of nuclear boundaries in cancer cells in three-channel luminescent images. Journal of Applied Spectroscopy. 2015;82(4):634–643. DOI: 10.1007/s10812-015-0156-2.
  6. Saood A, Hatem I. COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet. BMC Medical Imaging. 2021;21:19. DOI: 10.1186/s12880-020-00529-5.
  7. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556v1 [Preprint]. 2014 [cited 2022 March 18]: [10 p.]. Available from: https://arxiv.org/abs/1409.1556v1.
  8. He Kaiming, Zhang Xiangyu, Ren Shaoqing, Sun Jian. Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR); 2016 June 27–30; Las Vegas, USA. [S. l.]: IEEE; 2016. p. 770–778. DOI: 10.1109/CVPR.2016.90.
  9. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. arXiv:1411.4038v1 [Preprint]. 2014 [cited 2022 March 18]: [10 p.]. Available from: https://arxiv.org/abs/1411.4038v1.
  10. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF, editors. Medical image computing and computer-assisted intervention (MICCAI-2015). Proceedings of the 18th International conference; 2015 October 5–9; Munich, Germany. Part 3. Cham: Springer; 2015. p. 234–241 (Goos G, Hartmanis J, van Leeuwen J, editors. Lecture notes in computer science; volume 9351). DOI: 10.1007/978-3-319-24574-4_28.
  11. Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017;39(12):2481–2495. DOI: 10.1109/TPAMI.2016.2644615.
  12. Jégou S, Drozdzal M, Vazquez D, Romero A, Bengio Y. The one hundred layers tiramisu: fully convolutional DenseNets for semantic segmentation. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW); 2017 July 21–26; Honolulu, USA. [S. l.]: IEEE; 2017. p. 1175–1183. DOI: 10.1109/CVPRW.2017.156.
  13. Zhou Zongwei, Siddiquee MMR, Tajbakhsh N, Liang Jianming. UNet++: a nested U-Net architecture for medical image segmentation. In: Stoyanov D, Taylor Z, Carneiro G, Syeda-Mahmood T, Martel A, Maier-Hein L, et al., editors. Deep learning in medical image analysis and multimodal learning for clinical decision support. Proceedings of the 4th International workshop DLMIA-2018 and 8th International workshop ML-CDS-2018 held in conjunction with MICCAI-2018; 2018 September 20; Granada, Spain. Cham: Springer; 2018. p. 3–11 (Goos G, Hartmanis J, van Leeuwen J, editors. Lecture notes in computer science; volume 11045). DOI: 10.1007/978-3-030-00889-5_1.
  14. Ibtehaz N, Rahman MS. MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Networks. 2020;121:74–87. DOI: 10.1016/j.neunet.2019.08.025.
  15. Saxena N, Kishore Babu N, Raman B. Semantic segmentation of multispectral images using Res-Seg-net model. In: 2020 IEEE 14th International conference on semantic computing (ICSC); 2020 February 3–5; San Diego, USA. [S. l.]: IEEE; 2020. p. 154–157. DOI: 10.1109/ICSC.2020.00030.
  16. Huang Huimin, Lin Lanfen, Tong Ruofeng, Hu Hongjie, Zhang Qiaowei, Iwamoto Y, et al. UNet 3+: a full-scale connected U-Net for medical image segmentation. In: 2020 IEEE International conference on acoustics, speech and signal processing (ICASSP); 2020 May 4–8; Barcelona, Spain. [S. l.]: IEEE; 2020. p. 1055–1059. DOI: 10.1109/ICASSP40776.2020.9053405.
  17. Chen Jieneng, Lu Yongyi, Yu Qihang, Luo Xiangde, Adeli E, Wang Yan, et al. TransUNet: transformers make strong encoders for medical image segmentation. arXiv:2102.04306 [Preprint]. 2021 [cited 2022 March 21]: [13 p.]. Available from: https://arxiv.org/abs/2102.04306.
  18. Xu Silun, Skakun V. Comparison of deep learning preprocessing algorithms of nuclei segmentation on fluorescence immunohistology images of cancer cells. In: Tuzikov AV, Belotserkovsky AM, Lukashevich MM, editors. Pattern recognition and information processing. Revised selected papers of the 15th International conference PRIP-2021; 2021 September 21–24; Minsk, Belarus. Cham: Springer; 2022. p. 166–177 (Communications in computer and information science; volume 1562). DOI: 10.1007/978-3-030-98883-8_12.
  19. Huang Gao, Liu Zhuang, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR); 2017 July 21–26; Honolulu, USA. [S. l.]: IEEE; 2017. p. 2261–2269. DOI: 10.1109/CVPR.2017.243.
  20. Pan Bin, Shi Zhenwei, Xu Xia, Shi Tianyang, Zhang Ning, Zhu Xinzhong. CoinNet: copy initialization network for multispectral imagery semantic segmentation. IEEE Geoscience and Remote Sensing Letters. 2019;16(5):816–820. DOI: 10.1109/LGRS.2018.2880756.

Downloads

Additional Files

Published

2024-04-11

Issue

No. 1 (2024): Journal of the Belarusian State University. Mathematics and Informatics

Section

Theoretical Foundations of Computer Science

License

The authors who are published in this journal agree to the following:

  1. The authors retain copyright on the work and provide the journal with the right of first publication of the work on condition of license Creative Commons Attribution-NonCommercial. 4.0 International (CC BY-NC 4.0).
  2. The authors retain the right to enter into certain contractual agreements relating to the non-exclusive distribution of the published version of the work (e.g. post it on the institutional repository, publication in the book), with the reference to its original publication in this journal.
  3. The authors have the right to post their work on the Internet (e.g. on the institutional store or personal website) prior to and during the review process, conducted by the journal, as this may lead to a productive discussion and a large number of references to this work. (See The Effect of Open Access.)

How to Cite

[1]
Xu , S. and Skakun, V.V. 2024. Comparative analysis of deep learning neural networks for the segmentation of cancer cell nuclei on immunohistochemical fluorescent images. Journal of the Belarusian State University. Mathematics and Informatics. 1 (Apr. 2024), 59–70.