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

X. Silun ; V. V. Skakun

Journal of the Belarusian State University. Mathematics and Informatics, Tome 1 (2024), pp. 59-70.

Résumé

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.

Détail

Keywords: Immunohistochemical images; cancer cells images; nuclear segmentation; neural networks; deep learning; U-Net.

Bibliographie

[1] G. G. Chung, M. P. Zerkowski, S. Ghosh, R. L. Camp, D. L. Rimm, “Quantitative analysis of estrogen receptor heterogeneity in breast cancer”, Laboratory Investigation, 87(7) (2007), 662–669 | DOI

[2] R. L. Camp, G. G. Chung, D. L. Rimm, “Automated subcellular localization and quantification of protein expression in tissue microarrays”, Nature Medicine, 8(11) (2002), 1323–1328 | DOI

[3] N. S. Todewale, “Lesion segmentation from mammogram images using a U-Net deep learning network”, International Journal of Engineering Research and Technology, 9(2) (2020), 406–411

[4] A. Lagree, M. Mohebpour, N. Meti, K. Saednia, F. I. Lu, E. Slodkowska, “A review and comparison of breast tumor cell nuclei segmentation performances using deep convolutional neural networks”, Scientific Reports, 11 (2021), 8025 | DOI

[5] Y. V. Lisitsa, M. M. Yatskou, V. V. Apanasovich, T. V. Apanasovich, “Algorithm for automatic segmentation of nuclear boundaries in cancer cells in three-channel luminescent images”, Journal of Applied Spectroscopy, 82(4) (2015), 634–643 | DOI

[6] A. Saood, I. Hatem, “COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet”, BMC Medical Imaging, 21 (2021), 19 | DOI

[7] K. Simonyan, A. Zisserman, “Very deep convolutional networks for large-scale image recognition”, arXiv, 2014, 10 | DOI

[8] Kaiming. He, Xiangyu. Zhang, Shaoqing. Ren, Jian. Sun, “Deep residual learning for image recognition”, 2016 IEEE conference on computer vision and pattern recognition (Las Vegas, USA), IEEE, 2016, 770–778 | DOI

[9] J. Long, E. Shelhamer, T. Darrell, “Fully convolutional networks for semantic segmentation”, arXiv, 2014, 10 | DOI

[10] O. Ronneberger, P. Fischer, T. Brox, “U-Net: convolutional networks for biomedical image segmentation”, Medical image computing and computer-assisted intervention (MICCAI-2015). Proceedings of the 18th International conference. Part 3 (Munich, Germany), Springer, Cham, 2015, 234–241 (Lecture notes in computer science; volume 9351) | DOI

[11] V. Badrinarayanan, A. Kendall, R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12) (2017), 2481–2495 | DOI

[12] S. Jegou, M. Drozdzal, D. Vazquez, A. Romero, Y. Bengio, “The one hundred layers tiramisu: fully convolutional DenseNets for semantic segmentation”, 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW) (Honolulu, USA), IEEE, 2017, 1175–1183 | DOI

[13] Zongwei. Zhou, MMR. Siddiquee, N. Tajbakhsh, Jianming. Liang, “UNet++: a nested U-Net architecture for medical image segmentation”, 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 (Granada, Spain), Springer, Cham, 2018, 3–11 (Lecture notes in computer science; volume 11045) | DOI

[14] N. Ibtehaz, M. S. Rahman, “MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation”, Neural Networks, 121 (2020), 74–87 | DOI

[15] N. Saxena, Babu. Kishore, B. Raman, “Semantic segmentation of multispectral images using Res-Seg-net model”, 2020 IEEE 14th International conference on semantic computing (ICSC) (San Diego, USA), IEEE, 2020, 154–157 | DOI

[16] Huimin. Huang, Lanfen. Lin, Ruofeng. Tong, Hongjie. Hu, Qiaowei. Zhang, Y. Iwamoto, “UNet 3+: a full-scale connected U-Net for medical image segmentation”, 2020 IEEE International conference on acoustics, speech and signal processing (ICASSP) (Barcelona, Spain), IEEE, 2020, 1055–1059 | DOI

[17] Jieneng. Chen, Yongyi. Lu, Qihang. Yu, Xiangde. Luo, E. Adeli, Yan. Wang, “TransUNet: transformers make strong encoders for medical image segmentation”, arXiv, 2021, 13 | DOI

[18] Silun. Xu, V. Skakun, “Comparison of deep learning preprocessing algorithms of nuclei segmentation on fluorescence immunohistology images of cancer cells”, Pattern recognition and information processing. Revised selected papers of the 15th International conference PRIP-2021 (Minsk, Belarus), Springer, Cham, 2022, 166–177 (Communications in computer and information science; volume 1562) | DOI

[19] Gao. Huang, Zhuang. Liu, Der. Van, K. Q. Weinberger, “Densely connected convolutional networks”, 2017 IEEE conference on computer vision and pattern recognition (CVPR) (Honolulu, USA), IEEE, 2017, 2261–2269 | DOI

[20] Bin. Pan, Zhenwei. Shi, Xia. Xu, Tianyang. Shi, Ning. Zhang, Xinzhong. Zhu, “CoinNet: copy initialization network for multispectral imagery semantic segmentation”, IEEE Geoscience and Remote Sensing Letters, 16(5) (2019), 816–820 | DOI