Deciphering Blood Cells - Method for Blood Cell Analysis using Microscopic Images
DOI:
https://doi.org/10.71426/jmt.v1.i1.pp9-18Keywords:
RBC (Red Blood Cells), WBC (White Blood Cells), Mean Average Precision (mAP), Intersection of Union, Classification, Segmentation, AUC.Abstract
Blood cell analysis of RBC and WBC from smear images is crucial for identifying disorders caused by abnormal blood cells, such as leukemia, anemia, frequent infections, and other diseases, including cancer. Pathologists find it challenging to distinguish between abnormal and normal cells in smear images. Manually counting each element is tedious and prone to human errors. Image processing techniques are used to enhance the smear image quality before segmentation. Identifying and segmenting smear images remains a challenge for pathologists. In this research, we propose an approach for identifying and segmenting smear images, followed by classifying normal and abnormal cells. This work implements Mask CNN for segmentation and two different algorithms: EfficientNet-B3 and DenseNet-121 for classification. The Mask CNN model's results for identification and segmentation are evaluated using mAP and IOU. For RBC, the best mAP value is 0.52 and IOU is 0.45. For WBC, the best mAP value is 0.56 and IOU is 0.52. Classification results outperform previous studies, with experiments on six different classes based on RBC and WBC cell normality and abnormality. The average overall accuracy for EfficientNet-B3 is 95% and DenseNet-121 is 97%, respectively.
References
[1] Ajad A, Sadhwani KJ. Cares: Knowledge infused chest x-ray report generation scheme. In RSNA 2020-106th Annual Meeting. RSNA; 2020.
[2] Aliyu HA, Razak MA, Sudirman R. Normal and abnormal red blood cell recognition using image processing. Indonesian Journal of Electrical Engineering and Computer Science. 2019 Apr;14(1):100-104. Available from: https://doi.org/10.11591/ijeecs.v14.i1.pp96-100
[3] Cao F, Lu J, Chu J, Zhou Z, Zhao J, Chen G. Leukocyte image segmentation using feed forward neural networks with random weights. In: 2015 11th International Conference on Natural Computation (ICNC); 2015 Aug 15. p. 736-742. IEEE. Available from: https://doi.org/10.1109/ICNC.2015.7378082
[4] Harms H, Aus HM, Haucke M, Gunzer U. Segmentation of stained blood cell images measured at high scanning density with high magnification and high numerical aperture optics. Cytometry: The Journal of the International Society for Analytical Cytology. 1986 Nov;7(6):522-531. Available from: https://doi.org/10.1002/cyto.990070605
[5] Sohail M, Shoukat IA, Fatima H, Jafri MR, Yaqub MA, Liotta A. Deep learning based multi pose human face matching system. IEEE Access. 2024 Feb 14;12:26046-26061. Available from: https://doi.org/10.1109/ACCESS.2024.3366451
[6] Kalnoor G, Gowrishankar S. A model for intrusion detection system using hidden Markov and variational Bayesian model for IoT based wireless sensor network. International Journal of Information Technology. 2022 Jun;14(4):2021-2033. Available from: https://doi.org/10.1007/s41870-021-00748-1
[7] Jha KK, Das BK, Dutta HS. Detection of abnormal blood cells on the basis of nucleus shape and counting of WBC. In: 2014 International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE); 2014. p. 1-5. Available from: https://doi.org/10.1109/ICGCCEE.2014.6922219
[8] Jiang K, Liao QM, Dai SY. A novel white blood cell segmentation scheme using scale-space filtering and watershed clustering. In: Proceedings of the 2003 International Conference on Machine Learning and Cybernetics; 2003 Nov 5;5:2820-2825. IEEE. Available from: https://doi.org/10.1109/ICMLC.2003.1260033
[9] Naruenatthanaset K, Chalidabhongse TH, Palasuwan D, Anantrasirichai N, Palasuwan A. Red blood cell segmentation with overlapping cell separation and classification on imbalanced dataset. arXiv preprint arXiv:2012.01321. 2020 Dec 2. Available from: https://doi.org/10.48550/arXiv.2012.01321
[10] Nguyen HT, Worring M, Van Den Boomgaard R. Watersnakes: Energy-driven watershed segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003 Mar 31;25(3):330-342. Available from: https://doi.org/10.1109/TPAMI.2003.1182096
[11] Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics. 1979 Jan 31;9(1):62-66. Available from: https://doi.org/10.1109/TSMC.1979.4310076
[12] Parab MA, Mehendale ND. Red blood cell classification using image processing and CNN. SN Computer Science. 2021 Apr;2(2):70. Available from: https://doi.org/10.1007/s42979-021-00458-2
[13] Park JS, Keller JM. Fuzzy patch label relaxation in bone marrow cell segmentation. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics: Computational Cybernetics and Simulation; 1997 Oct 12;2:1133-1138. IEEE. Available from: https://doi.org/10.1109/ICSMC.1997.638102
[14] Poon SS, Ward RK, Palcic B. Automated image detection and segmentation in blood smears. Cytometry: The Journal of the International Society for Analytical Cytology. 1992;13(7):766-774. Available from: https://doi.org/10.1002/cyto.990130713
[15] Pradhan J, Ajad A, Pal AK, Banka H. Multi-level colored directional motif histograms for content-based image retrieval. The Visual Computer. 2020 Sep;36(9):1847-1868. Available from: https://doi.org/10.1007/s00371-019-01773-9
[16] Putzu L, Caocci G, Di Ruberto C. Leucocyte classification for leukaemia detection using image processing techniques. Artificial Intelligence in Medicine. 2014 Nov 1;62(3):179-191. Available from: https://doi.org/10.1016/j.artmed.2014.09.002
[17] Ray N, Acton ST. Motion gradient vector flow: An external force for tracking rolling leukocytes with shape and size constrained active contours. IEEE Transactions on Medical Imaging. 2004 Nov 30;23(12):1466-1478. Available from: https://doi.org/10.1109/TMI.2004.835603
[18] Safabakhsh R, Zamani F. A robust multi-orientation Gabor based system for discriminating touching white and red cells in microscopic blood image. In: 2006 2nd International Conference on Information & Communication Technologies; 2006 Apr 24;1:1135-1139. Available from: https://doi.org/10.1109/ICTTA.2006.1684534
[19] Song TH, Cao M, Min J, Im H, Lee H, Lee K. Deep learning-based phenotyping of breast cancer cells using lens-free digital in-line holography. bioRxiv. 2021. Available from: https://www.cell.com/biophysj/fulltext/S0006-3495(22)02535-8
[20] Tan M, Le Q. EfficientNet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning; 2019 May 24. p. 6105-6114. PMLR. Available from: https://proceedings.mlr.press/v97/tan19a.html?ref=ji
[21] Wang M, Zheng S, Li X, Qin X. A new image denoising method based on Gaussian filter. In: Proceedings of the International Conference on Information Science, Electronics and Electrical Engineering. Sapporo, Japan: IEEE; 2014. p. 163-167. Available from: https://doi.org/10.1109/InfoSEEE.2014.6948089
[22] Xu Q, Zhu Z, Ge H, Zhang Z, Zang X. Effective face detector based on YOLOv5 and superresolution reconstruction. Computational and Mathematical Methods in Medicine. 2021;2021:7748350. Available from: https://doi.org/10.1155/2021/7748350
[23] Meimban RJ, Fernando AR, Monsura A, Rañada J, Apduhan JC. Blood cells counting using python OpenCV. In2018 14th IEEE International Conference on Signal Processing (ICSP) 2018 Aug 12 (pp. 50-53). IEEE.
Available from: https://doi.org/10.1109/ICSP.2018.8652384
[24] Bharti R, Khamparia A, Shabaz M, Dhiman G, Pande S, Singh P. Prediction of heart disease using a combination of machine learning and deep learning. Computational Intelligence and Neuroscience. 2021;2021:8387680. Available from: https://doi.org/10.1155/2021/8387680
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Sandeep Kumar Aazad, Taniya Saini, Ashok Ajad, Kritika Chaudhary, Ebrahim E. Elsayed (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The Journal of Modern Technology publishes all articles under the Creative Commons Attribution–NonCommercial 4.0 International License (CC BY-NC 4.0). This license permits others to copy, distribute, reproduce, remix, adapt, and build upon the published work for non-commercial purposes, provided appropriate credit is given to the original authors and the source. By publishing in the Journal of Modern Technology, all authors agree to these licensing terms as a condition of publication.
