Segmentation of Microscopic Blood Cell Images with Current Deep Learning Architectures

Yıl 2023, , 135 - 141, 30.04.2023

Murat Toptaş , Davut Hanbay

https://doi.org/10.46387/bjesr.1261689

Cited By: 1

Öz

Blood cells are the basic components of blood, and they play an important role in the healthy functioning of the human body. The shape, number, size, and other characteristics of blood cells are dependent on various factors, and changes in these properties can be associated with many diseases. Therefore, the detection, classification, and segmentation of blood cells have become a very important issue in the field of health. With the high performance effect of deep learning architectures on medical images, the number of automatic diagnosis systems on these blood cells has increased. In this article, cell segmentation was performed on microscopic blood cell images using DeepLabv3+, U-Net, and FCN architectures. The best accuracy result was the accuracy with a score of 0.9575 in the DeepLabv3+ architecture. The experimental results support the robustness of the proposed method.

Anahtar Kelimeler

Cell, Segmentation, DeepLabV3+

Mikroskobik Kan Hücre Görüntülerinin Güncel Derin Öğrenme Mimarileri ile Bölütlemesi

Öz

Kan hücreleri, kanın temel bileşenleridir. Bu bileşenler insan vücudunun sağlıklı bir şekilde çalışmasında önemli rol oynarlar. Kan hücrelerinin şekli, sayısı, boyutu ve diğer özellikleri çeşitli faktörlere bağlıdır. Bu özelliklerin değişimleri birçok hastalıkla ilişkilendirilebilmektedir. Bu nedenle, kan hücrelerinin tespit edilmesi, sınıflandırılması ve bölütlenmesi sağlık alanında çok önemli bir konu haline gelmiştir. Derin öğrenme mimarilerinin medikal görüntüler üzerinde göstermiş olduğu yüksek performans etkisiyle bu kan hücreleri üzerinde otomatik tanı sistemlerinin sayısı artmıştır. Bu makalede, DeepLabv3+, U-Net ve FCN mimarileri ile mikroskobik kan hücresi görüntüleri üzerinde hücre bölütlemesi yapılmıştır. En iyi doğruluk sonucuna 0.9575 ile DeepLabv3+ mimarisinde ulaşılmıştır. Deneysel sonuçlar, önerilen yöntemin sağlamlığını destekler niteliktedir.

Anahtar Kelimeler

Hücre, Bölütleme, DeepLabV3+, U-Net, FCN

Kaynakça

• B. Toptaş and D. Hanbay “Retinal blood vessel segmentation using pixel-based feature vector”, Biomed Signal Process Control, vol. 70, p. 103053, 2021.
• N. Şahin, N. Alpaslan, and D. Hanbay “Robust optimization of SegNet hyperparameters for skin lesion segmentation”, Multimed Tools Appl, vol. 81, no. 25, pp. 36031–36051, 2022.
• D.R. Nayak, N. Padhy, and B.K. Swain “Blood cell image segmentation using modified fuzzy divergence with morphological transforms”, Mater Today Proc, vol. 37, pp. 2708–2718, 2021.
• D. Kumar et al. “Automatic Detection of White Blood Cancer From Bone Marrow Microscopic Images Using Convolutional Neural Networks”, IEEE Access, vol. 8, pp. 142521–142531, 2020.
• D.S. Depto et al. “Automatic segmentation of blood cells from microscopic slides: A comparative analysis”, Tissue Cell, vol. 73, p. 101653, 2021.
• S.S. Savkare, A.S. Narote, and S.P. Narote “Automatic Blood Cell Segmentation Using K-Mean Clustering from Microscopic Thin Blood Images,” in Proceedings of the Third International Symposium on Computer Vision and the Internet, pp. 8–11, 2016.
• K. Nawa, E. Suryani, and H. Prasetyo “Dengue Virus Infected Leukocyte Classification on Microscopic Images with Image Histogram Based Support Vector Machine”, in 2019 5th International Conference on Science and Technology (ICST), pp. 1–5, 2019.
• S. Mohapatra, D. Patra, and S. Satpathi “Image analysis of blood microscopic images for acute leukemia detection”, in 2010 International Conference on Industrial Electronics, Control and Robotics, pp. 215–219, 2010
• M.I. Razzak and S. Naz “Microscopic Blood Smear Segmentation and Classification Using Deep Contour Aware CNN and Extreme Machine Learning”, in 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 801–807, 2017
• A. Arbelle and T.R. Raviv “Microscopy Cell Segmentation via Adversarial Neural Networks”, In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018.
• Z. Zhou, M.M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang “UNet++: A Nested U-Net Architecture for Medical Image Segmentation”, pp. 3–11, 2018.
• C. Huang, C. Huang, H. DIng, and C. Liu “Segmentation of Cell Images Based on Improved Deep Learning Approach”, IEEE Access, vol. 8, pp. 110189–110202, 2020.
• S.E.A. Raza et al. “Micro-Net: A unified model for segmentation of various objects in microscopy images”, Med Image Anal, vol. 52, pp. 160–173, 2019.
• S.K. Sadanandan, P. Ranefall, S. le Guyader, and C. Wählby “Automated Training of Deep Convolutional Neural Networks for Cell Segmentation”, Sci Rep, vol. 7, no. 1, p. 7860, 2017.
• W. Jiang, L. Wu, S. Liu, and M. Liu “CNN-based two-stage cell segmentation improves plant cell tracking”, Pattern Recognit Lett, vol. 128, pp. 311–317, 2019.
• Z. Zhang, Q. Li, W. Song, P. Wei, and J. Guo “A novel concavity based method for automatic segmentation of touching cells in microfluidic chips”, Expert Syst Appl, vol. 202, p. 117432, 2022.
• K. Nishimura, C. Wang, K. Watanabe, D. Fei Elmer Ker, and R. Bise “Weakly supervised cell instance segmentation under various conditions”, Med Image Anal, vol. 73, Oct. 2021.
• Y. Zhao, C. Fu, S. Xu, L. Cao, and H. feng Ma “LFANet: Lightweight feature attention network for abnormal cell segmentation in cervical cytology images”, Comput Biol Med, vol. 145, 2022.
• O. Ronneberger, P. Fischer, and T. Brox “U-Net: Convolutional Networks for Biomedical Image Segmentation”, May 2015.
• J. Long, E. Shelhamer, and T. Darrell “Fully convolutional networks for semantic segmentation”, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440, 2015.
• L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille “Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs”, 2014.
• L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille “DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs”, IEEE Trans Pattern Anal Mach Intell, vol. 40, no. 4, pp. 834–848, 2018.
• L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam, “Rethinking Atrous Convolution for Semantic Image Segmentation”, Jun. 2017.
• L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam “Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation”, 2018.