A comparison of U-net backbone architectures for the automatic white blood cells segmentation
Keywords:white blood cells segmentation, deep Learning, transfer learning, U-NET, Loss Function, cytological image’s dataset
Reliable recognition of white blood cells is an essential step in the diagnosis of several types of cancer. Therefore, the segmentation of white blood cells plays an essential role and is an important part of the medical diagnostic system. Manual cell diagnosis involves doctors visually examining microscopic images to detect any cellular abnormalities. This step is costly and time-consuming. An automated system based on white blood cell identification provides a more accurate result than the manual method. Image segmentation is one of the crucial contributions of a deep learning community to the medical field. In this paper, we demonstrate how the U-Net type architecture can be improved by the use of the pre-trained encoder, a comparison of several efficient methods for automatic recognition of white blood cells using the original U-NET, different pre-trained classification networks are used as the backbone to obtain better performance. The architecture of RESNET-50 obtains the best segmentation results on testing data for automatic recognition in cytological images with a less amount of training epochs.
Al-Dulaimi, K.A.K.; Banks, J.; Chandran, V.; Tomeo-Reyes, I.; Thanh, K.N. Classification of white blood cell types from microscope images:Techniques and challenges. In Microscopy science: Last approaches on educational programs and applied research (Microscopy Book Series, 8); Mendez-Vilas, A., Torres-Hergueta, E., Eds.; Formatex Research Center: Spain, 2018; pp. 17–25.
Blumenreich, M.S. The White Blood Cell and Differential Count. BTI - Clinical Methods: The History, Physical, and Laboratory Examinations. In; H Kenneth Walker W Dallas Hall, J.W.H., Ed.; Butterworths: Emory University School of Medicine, Atlanta, Georgia FAU - Blumenreich, Martin S, 1990.
Yu, T.-C.; Chou, W.-C.; Yeh, C.-Y.; Yang, C.-K.; Huang, S.-C.; Tien, F.M.; Yao, C.-Y.; Cheng, C.-L.; Chuang, M.-K.; Tien, H.-F.; et al. Automatic Bone Marrow Cell Identification and Classification By Deep Neural Network. Blood 2019, 134, 2084, doi:10.1182/blood-2019-125322.
Ramakrishna, R.R.; Abd Hamid, Z.; Zaki, W.M.D.W.; Huddin, A.B.; Mathialagan, R. Stem cell imaging through convolutional neural networks: current issues and future directions in artificial intelligence technology. PeerJ 2020, 8, e10346.
Anilkumar, K.K.; Manoj, V.J.; Sagi, T.M. A survey on image segmentation of blood and bone marrow smear images with emphasis to automated detection of Leukemia. Biocybern. Biomed. Eng. 2020, 40, pp. 1406–1420, doi:https://doi.org/10.1016/j.bbe.2020.08.010.
Benazzouz, M.; Baghli, I.; Chikh, M.A. Microscopic image segmentation based on pixel classiﬁcation and dimensionality reduction. Int. J. Imaging Systems and Technology 2013, 23, pp. 22–28.
Baghli, I.; Nakib, A.; Sellam, E.; Benazzouz, M.; Chikh, A.; Petit, E. Hybrid framework based on evidence theory for blood cell image segmentation. Medical Imaging 2014: Biomedical Applications in Molecular, Structural, and Functional Imaging; Molthen, R.C.; Weaver, J.B., Eds. International Society for Optics and Photonics, SPIE, 2014, Vol. 9038, pp. 314 – 321.doi:black10.1117/12.2042142.
Benomar, M.L.; Chikh, A.; Descombes, X.; Benazzouz, M. Multi-feature-based approach for white blood cells segmentation and classiﬁcation in peripheral blood and bone marrow images. International Journal of Biomedical Engineering and Technology 2021, 35, pp. 223–241.
Settouti, N.; Bechar, M.E.A.; El Habib Daho, M.; Chikh, M.A. An optimised pixel-based classiﬁcation approach for automatic white blood cells segmentation. International Journal of Biomedical Engineering and Technology 2020, 32, pp. 144–160.
Saidi, M.; Bechar, M.E.A.; Settouti, N.; Chikh, M.A. Instances selection algorithm by ensemble margin. Journal of Experimental & Theoretical Artiﬁcial Intelligence 2018, 30, pp. 457–478, doi:black10.1080/0952813X.2017.1409283.
Settouti, N.; Saidi, M.; Bechar, M.E.A.; El Habib Daho, M.; Chikh, M.A. An instance and variable selection approach in pixel-based classiﬁcation for automatic white blood cells segmentation. Pattern Analysis and Applications 2020, 23, pp. 1709–1726.
Bechar, M.E.A.; Settouti, N.; Daho, M.E.H.; Adel, M.; Chikh, M.A. Inﬂuence of normalization and color features on super-pixel classiﬁcation: application to cytological image segmentation. Australasian Physical & Engineering Sciences in Medicine 2019, 42, pp. 427–441.
Bechar, M.E.A.; Settouti, N.; Daho, M.E.H. Semi-supervised Super-pixels classiﬁcation for White Blood Cells segmentation. 2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS), 2018, pp. 1–8. doi:black10.1109/PAIS.2018.8598521.
Khouani, A.; El Habib Daho, M.; Mahmoudi, S.A.; Chikh, M.A.; Benzineb, B. Automated recognition of white blood cells using deep learning. Biomedical Engineering Letters 2020, 10, pp. 359–367.
Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention. Springer, 2015, pp. 234–241.
Ioﬀe, S.; Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv e-prints 2015.
Iglovikov, V.; Shvets, A. Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation. arXiv preprint arXiv:1801.05746 2018.
Chang, S.W.; Liao, S.W. KUnet: microscopy image segmentation with deep unet based convolutional networks. 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). IEEE, 2019, pp. 3561–3566.
Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. Mobilenets: Eﬃcient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 2017.
Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 2014.
He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; others. Imagenet large scale visual recognition challenge. International journal of computer vision 2015, 115, pp. 211–252.
Yakubovskiy, P. Segmentation Models. https://github.com/qubvel/ segmentation_models, 2019.
Prechelt, L. Early stopping-but when? In Neural Networks: Tricks of the trade; Springer, 1998; pp. 55–69.
Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 2014.
Yi-de, M.; Qing, L.; Zhi-Bai, Q. Automated image segmentation using improved PCNN model based on cross-entropy. Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004. IEEE, 2004, pp. 743–746.
Sudre, C.H.; Li, W.; Vercauteren, T.; Ourselin, S.; Cardoso, M.J. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In Deep learning in medical image analysis and multimodal learning for clinical decision support; Springer, 2017; pp. 240–248.