Image classification of leukemia cancer using Wavelet deep neural network

• Autorzy: Habchi Yassine , Bouddou Riyadh , Aimer Ameur Fethi

Identyfikatory

DOI

10.15199/48.2024.03.42

Warianty tytułu

PL

Klasyfikacja obrazu raka białaczki za pomocą głębokiej sieci neuronowej Wavelet

• Języki publikacji: EN

Abstrakty

EN

Classification of blood cell images, through color and morphological features, is essential for medical diagnostic processes. This paper proposes an efficient method using LeGall5/3 wavelet transform (LeGall5/3WT) based on Convolutional Neural Network (CNN) for leukemia cancer image classification. The proposed algorithm is applied on 108leukemia images, including 49 blast cell images and 59 healthy cell images. All these images are obtained from the acute lymphoblastic leukemia image database for image processing (ALL-IDB). The data augmentation technique provided 7776 images, including3528 blast cell images and 4248 healthy cells. LeGall5/3WT feature extraction results are used as inputs to the CNN for leukemia cancer classification. The network system architecture contains three convolutions, three aggregate layers, a fully connected layer, a Soft Max layer, and an output layer with two classes. The proposed algorithm achieves accurate results (accuracy of 100%, sensitivity of 100%, specificity of 100%) for ALL-LDB1 database.

PL

Klasyfikacja obrazów krwinek pod kątem cech kolorystycznych i morfologicznych jest niezbędna w procesach diagnostyki medycznej. W artykule zaproponowano wydajną metodę wykorzystującą transformatę falkową LeGall5/3 (LeGall5/3WT) opartą na konwolucyjnej sieci neuronowej (CNN) do klasyfikacji obrazów raka białaczki. Proponowany algorytm jest stosowany na 108 obrazach białaczki, w tym 49 obrazach komórek blastycznych i 59 obrazach zdrowych komórek. Wszystkie te obrazy uzyskano z bazy danych obrazów ostrej białaczki limfoblastycznej do przetwarzania obrazów (ALL-IDB). Technika powiększania danych dostarczyła 7776 obrazów, w tym 3528 obrazów komórek blastycznych i 4248 zdrowych komórek. Wyniki ekstrakcji cech LeGall5/3WT są wykorzystywane jako dane wejściowe do CNN w celu klasyfikacji raka białaczki. Architektura systemu sieciowego zawiera trzy sploty, trzy warstwy agregatów, warstwę w pełni połączoną, warstwę Soft Max i warstwę wyjściową z dwiema klasami. Zaproponowany algorytm pozwala uzyskać dokładne wyniki (dokładność 100%, czułość 100%, specyficzność 100%) dla bazy danych ALL-LDB1.

Słowa kluczowe

EN

artificial intelligence; convolutional neural network; image classification; LeGall5/3 wavelets transform; leukemia

PL

sztuczna inteligencja; konwolucyjna sieć neuronowa; klasyfikacja obrazu; transformacja falkowa LeGall5/3; białaczka

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 3
• Strony: 238--243
• Opis fizyczny: Bibliogr. 32 poz., rys., tab.

Twórcy

autor

Habchi Yassine

• Department of Electrical Engineering, Institute of Technology, University Center of Naama, Algeria

• https://orcid.org/0000-0002-8764-9675

autor

Bouddou Riyadh

• Department of Electrical Engineering, Institute of Technology, University Center of Naama, Algeria

• https://orcid.org/0000-0001-6555-5785

autor

Aimer Ameur Fethi

• Diagnosis group, LDEE Laboratory (USTO-Oran), Department of Electrical Engineering, University of Saida, Algeria

• https://orcid.org/0000-0003-4933-109X

Bibliografia

• [1] The Global Cancer Observatory, Available online: https://gco.iarc.fr/, accessed: 2023-0303.
• [2] Z. Gao, A. Mao, K. Wu, Y. Li, L. Zhao, X. Zhang, J. Wu, L. Yu, C. Xing, T. Gong et al., “Childhood leukemia classification via information bottle-neck enhanced hierarchical multi-instance learning,” IEEE Transactions on Medical Imaging, 2023.
• [3] N. Bibi, M. Sikandar, I. Ud Din, A. Almogren, and S. Ali, “Iomt-basedautomated detection and classification of leukemia using deep learning,”Journal of healthcare engineering, vol. 2020, pp. 1–12, 2020.
• [4] G. R. Spinner, C. Federau, and S. Kozerke, “Bayesian inference using hierar-chical and spatial priors for intravoxel incoherent motion mr imaging in the brain: Analysis of cancer and acute stroke,” Medical image analysis, vol. 73,p. 102144, 2021.
• [5] A. Bodzas, P. Kodytek, and J. Zidek, “Automated detection of acute lymphoblastic leukemia from microscopic images based on human visual perception,” Frontiers in Bioengineering and Biotechnology, vol. 8, p. 1005, 2020.
• [6] J.-N. Eckardt, M. Bornh ̈auser, K. Wendt, and J. M. Middeke, “Applicationof machine learning in the management of acute myeloid leukemia: current practice and future prospects,” Blood Advances, vol. 4, no. 23, pp. 6077–6085, 2020.
• [7] N. Ouyang, W. Wang, L. Ma, Y. Wang, Q. Chen, S. Yang, J. Xie, S. Su,Y. Cheng, Q. Cheng et al., “Diagnosing acute promyelocytic leukemia byusing convolutional neural network,” Clinica Chimica Acta, vol. 512, pp.1–6, 2021.
• [8] N. Ahmed, A. Yigit, Z. Isik, and A. Alpkocak, “Identification of leukemiasubtypes from microscopic images using convolutional neural network,” Diagnostics, vol. 9, no. 3, p. 104, 2019.
• [9] R. M. Roy and P. Ameer, “Segmentation of leukocyte by semantic segmen-tation model: A deep learning approach,” Biomedical Signal Processing andControl, vol. 65, p. 102385, 2021.
• [10] R. Khandekar, P. Shastry, S. Jaishankar, O. Faust, and N. Sampathila,“Automated blast cell detection for acute lymphoblastic leukemia diagnosis,”Biomedical Signal Processing and Control, vol. 68, p. 102690, 2021.
• [11] S. Patil, G. Naik, R. Pai, and R. Gad, “Stacked autoencoder for classificationof glioma grade iii and grade iv,” Biomedical Signal Processing and Control,vol. 46, pp. 67–75, 2018.
• [12] G. Liang, H. Hong, W. Xie, and L. Zheng, “Combining convolutional neuralnetwork with recursive neural network for blood cell image classification,”IEEE access, vol. 6, pp. 36 188–36 197, 2018.
• [13] S. Shah, W. Nawaz, B. Jalil, and H. A. Khan, “Classification of normal andleukemic blast cells in b-all cancer using a combination of convolutional and recurrent neural networks,” in ISBI 2019 C-NMC Challenge: Classificationin Cancer Cell Imaging: Select Proceedings. Springer, 2019, pp. 23–31.
• [14] M. Hess, S. Lenz, T. J. Bl ̈atte, L. Bullinger, and H. Binder, “Partitionedlearning of deep boltzmann machines for snp data,” Bioinformatics, vol. 33,no. 20, pp. 3173–3180, 2017.
• [15] M. Tuba and E. Tuba, “Generative adversarial optimization (goa) foracute lymphocytic leukemia detection,” Studies in Informatics and Control,vol. 28, no. 3, pp. 245–254, 2019.
• [16] L. Ma, R. Shuai, X. Ran, W. Liu, and C. Ye, “Combining dc-gan withresnet for blood cell image classification,” Medical & biological engineering& computing, vol. 58, pp. 1251–1264, 2020.
• [17] S. Kumar, S. Mishra, and P. Asthana, “Automated detection of acuteleukemia using k-mean clustering algorithm,” in Advances in Computer andComputational Sciences: Proceedings of ICCCCS 2016, Volume 2. Springer, 2018, pp. 655–670.
• [18] Y. Habchi, A. F. Aimer, M. Beladgham, and R. Bouddou, “Ultra low bitrate retinal image compression using integer lifting scheme and subbandencoder,” Indonesian Journal of Electrical Engineering and Computer Sci-ence (IJEECS), vol. 24, no. 1, pp. 295–307, 2021.
• [19] Y. Habchi, M. Beladgham, A. MOULAY LAKHDAR, A. Bassou, and T.-A.Abdelmalik, “Low bit-rate medical video coding using dwt.” Electrotehnica,Electronica, Automatica, vol. 63, no. 1, 2015.
• [20] Y. Habchi, M. Beladgham, H. Benlabbes, and A. T. Abdelmalik, “Hybriddct-dbt algorithm for medical video compression,” Electrotehnica, Electronica, Automatica, vol. 64, no. 2, p. 97, 2016.
• [21] B. Sdiri, M. Kaaniche, F. A. Cheikh, A. Beghdadi, and O. J. Elle, “Efficient enhancement of stereo endoscopic images based on joint wavelet decompo- sition and binocular combination,” IEEE transactions on medical imaging,vol. 38, no. 1, pp. 33–45, 2018.
• [22] E. Kang, W. Chang, J. Yoo, and J. C. Ye, “Deep convolutional framelet denosing for low-dose ct via wavelet residual network,” IEEE transactions on medical imaging, vol. 37, no. 6, pp. 1358– 1369, 2018.
• [23] J. Shi, Y. Zhao, W. Xiang, V. Monga, X. Liu, and R. Tao, “Deep scatteringnetwork with fractional wavelet transform,” IEEE Transactions on SignalProcessing, vol. 69, pp. 4740– 4757, 2021.
• [24] A. P. D. G. Savi ́c, M. Prokin, V. M. Rajovi ́c, and D. Prokin, “Memory efficient hardware architecture for 5/3 lifting-based 2-d forward discrete wavelettransform,” Microprocessors and Microsystems, vol. 87, p. 104176, 2021.
• [25] L. Ding and W. Chen, “The analysis and research of lifting scheme based onwavelet transform,” in Cyber Security Intelligence and Analytics. Springer,2020, pp. 1377–1382.
• [26] M. Shaban, R. Awan, M. M. Fraz, A. Azam, Y.-W. Tsang, D. Snead, and N. M. Rajpoot, “Context-aware convolutional neural network for grading of colorectal cancer histology images,” IEEE transactions on medical imaging, vol. 39, no. 7, pp. 2395– 2405, 2020.
• [27] R. Gu, G. Wang, T. Song, R. Huang, M. Aertsen, J. Deprest, S. Ourselin, T. Vercauteren, and S. Zhang, “Ca-net: Comprehensive attention convolutional neural networks for explainable medical image segmentation,” IEEE transactions on medical imaging, vol. 40, no. 2, pp. 699 711, 2020.
• [28] D. Karimi and S. E. Salcudean, “Reducing the hausdorff distance in medical image segmentation with convolutional neural networks,” IEEE Trans- actions on medical imaging, vol. 39, no. 2, pp. 499–513, 2019.
• [29] R. Baig, A. Rehman, A. Almuhaimeed, A. Alzahrani, and H. T. Rauf, “Detecting malignant leukemia cells using microscopic blood smear images: Adeep learning approach,” Applied Sciences, vol. 12, no. 13, p. 6317, 2022.
• [30] A. Abhishek, R. K. Jha, R. Sinha, and K. Jha, “Automated classification ofacute leukemia on a heterogeneous dataset using machine learning and deeplearning techniques,” Biomedical Signal Processing and Control, vol. 72, p.103341, 2022.
• [31] R. Khandekar, P. Shastry, S. Jaishankar, O. Faust, and N. Sampathila,“Automated blast cell detection for acute lymphoblastic leukemia diagnosis,”Biomedical Signal Processing and Control, vol. 68, p. 102690, 2021.
• [32] M. Zakir Ullah, Y. Zheng, J. Song, S. Aslam, C. Xu, G. D. Kiazolu, andL. Wang, “An attention-based convolutional neural network for acute lymphoblastic leukemia classification,” Applied Sciences, vol. 11, no. 22, p.10662, 2021.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).