Comparison of traditional image processing and deep learning approaches for classification of white blood cells in peripheral blood smear images

• Autorzy: Hegde, Roopa B. , Prasad, Keerthana , Hebbar, Harishchandra , Singh, Brij Mohan Kumar
• Języki publikacji: EN

Abstrakty

EN

Automated classification and morphological analysis of white blood cells has been addressed since last four decades, but there is no optimal method which can be used as decision support system in laboratories due to biologically complex nature of the cells. Automated blood cell analysis facilitates quick and objective results and can also handle massive amount of data without compromising with efficiency. In the present study, we demonstrate classification of white blood cells into six types namely lymphocytes, monocytes, neutrophils, eosinophils, basophils and abnormal cells. We provide the comparison of traditional image processing approach and deep learning methods for classification of white blood cells. We evaluated neural network classifier results for hand-crafted features and obtained the average accuracy of 99.8%. We also used full training and transfer learning approaches of convolutional neural network for the classification. An accuracy around 99% was obtained for full training CNN.

Słowa kluczowe

PL

analiza rozmazu krwi; krwinki białe; uczenie maszynowe; uczenie głębokie

EN

peripheral blood smear analysis; white blood cells; machine learning; deep learning

• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 2
• Strony: 382--392
• Opis fizyczny: Bibliogr. 42 poz., rys., tab., wykr.

Twórcy

autor

Hegde, Roopa B.

• School of Information Sciences, MAHE, Manipal, India; Dept. of ECE, NMAM Institute of Technology, Nitte, Karkala, India

autor

Prasad, Keerthana

• School of Information Sciences, MAHE, Manipal 576104, India,

autor

Hebbar, Harishchandra

• School of Information Sciences, MAHE, Manipal, India

autor

Singh, Brij Mohan Kumar

• Dept. of Immunohematology and Blood Transfusion, KMC, MAHE, Manipal, Karnataka, India

Bibliografia

• [1] Jianwei Z, Minshu Z, Zhenghua Z, Jianjun C, Feilong C. Automatic detection and classification of leukocytes using convolutional neural network. Med Biol Eng Comput 2017;55(8):1287.
• [2] Fuyong X, Lin Y. Robust nucleus/cell detection and segmentation in digital pathology and microscoy images: a comprehensive review. IEEE Rev Biomed Eng 2016;9:234.
• [3] Moshavash Z, Danyali H, Helfroush MS. An automatic and robust decision support system for accurate acute leukemia diagnosis from blood microscopic images. J Digital Imag 2018;1–16.
• [4] Humayun I, Antoine V, Ludovic R, Daniel R. Methods for nuclei detection, segmentation and classification in digital histopathology: a review current status and future potential. IEEE Rev Biomed Eng 2014;7:97.
• [5] Cao F, Cai M, Chu J, Zhao J, Zhou Z. A novel segmentation algorithm for nucleus in white blood cells based on low-rank representation. Neural Comput Appl 2017;28(1):503.
• [6] Pan C, Park DS, Yang Y, Yoo HM. Leukocyte image segmentation by visual attention and extreme learning machine. Neural Comput Appl 2012;21(6):1217.
• [7] Muhammad R, Saeeda Imran N. Microscopic blood smear segmentation and classification using deep contour aware CNN and extreme machine learning. Proc IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2017. pp. 49–55. 10.1109/CVPRW.2017.111.
• [8] Andrew J, Anant M. Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases. J Pathol Inform 2016;7(29):18.
• [9] Shin HC, Orton MR, Collins DJ, Oran SJ, Leach MO. Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Trans Pattern Anal Mach Intell 2013;35(8):1930–43.
• [10] Andrew J, Ajay B, Anant M. Stain normalization using sparse autoencoders (StaNoSA): application to digital pathology. Comput Med Imaging Graph 2017;57:50.
• [11] Dolz J, Betrouni N, Quidet M, Kharroubi D, Leroy HA, Reyns N. Stacking de-noising autoencoders in deep network to segment the brainstem on MRI brain cancer patients: a clinical study. Comput Med Imaging Graph 2016;52:8.
• [12] Bejoy A, Madhu SN. Computer-aided diagnosis of clinically significant prostate cancer from MRI images using sparse autoencoder and random forest classifier. Biocybern Biomed Eng 2018;38(3):733.
• [13] Jaroonrut P, Charnchai P. Segmentation of white blood cells and comparison of cell morphology by linear and nave bayes classifiers. Biomed Eng Online 2015;14(63). http://dx.doi.org/10.1186/s12938-015-0037-1.
• [14] Mathur A, Tripathi S, Kuse M. Scalable system for classification of white blood cells from Leishman stained blood stain images. J Pathol Inform 2013;4(15):6.
• [15] Sedat N, Deniz K, Tuncay E, Murat S, Husnu, Osman K, et al. Automatic segmentation, counting, size determination and classification of white blood cells. J Measure 2014;55:58.
• [16] Hamid Seyed R, Soltanian Hamid Z. Automatic recognition of five types of white blood cells in peripheral blood. Comp Med Imaging Graph 2011;35:333.
• [17] Neelam S, Ramakrishnan GA. Automation of differential blood count. Proc IEEE Conference on Convergent Technologies for the Asia-Pacific Region, vol. 2. 2003. p. 547.
• [18] Qingli L, yiting W, Hongying L, Xinofu H, Dongrong X, Jianbiao W, et al. Leukocytes cells identification and quantitative morphometry based on molecular hyperspectral imaging technology. Comp Med Imaging Graph 2014;38:171.
• [19] Omid S, Hossein R, Ardeshir T, Hossein B, Yousefi. Selection of the best features for leukocytes classification in blood smear microscopic images. Proc. SPIE – Progress in Biomedical Optics and Imaging, vol. 9041. 2014. p. 8.
• [20] Siroić R, Osowski S, Markiewicz T, Siwek K. Application of support vector machine and genetic algorithm for improved blood cell recognition. IEEE Trans Instr Measure 2009;58(7):2159.
• [21] Morteza A, Moradi, Saeed K, Ardeshir T, Mostafa O, Ghelich. Recognition of acute lymphoblastic leukemia cells in microscopic images using k-means clustering and support vector machine classifier. J Med Signals Sensors 2015;5(1):49.
• [22] Jyoti R, Annapurna S, Bhadauria H, Jitendra V, Singh JD. Computer assisted classification framework for prediction of acute lymphoblastic and acute myeloblastic leukemia. Biocybern Biomed Eng 2017;37(4):637.
• [23] Mohapatra S, Patra D, Satpathy S. An ensemble classifier system for early diagnosis of acute lymphoblastic leukemia in blood microscopic images. Neural Comput Appl 2014;24(7):1887.
• [24] Madhloom T, Kareem HA, Ariffin SH, Zaidan A, Alanazi AO, Zaidan HB. An automated white blood cell nucleus localization and segmentation using image arithmetic and automatic threshold. J Appl Sci 2010;10(11):959.
• [25] Zhang J, Zhong YH, Wang X, Ni G, Du X, Liu J, et al. Computerized detection of leukocytes in microscopic leukorrhea images. Med Phys 2017;44(9):4620–9.
• [26] Zhao J, Zhang M, Zhou Z, Chu J, Cao F. Automatic detection and classification of leukocytes using convolutional neural networks. Med Biol Eng Comput 2017;55(8):1287–301.
• [27] Shahin AI, Yanhui Guo, Aminc KM, Amr Sharawi A. White blood cells identification system based on convolutional deep neural learning networks. Comp Methods Programs Biomed 2017. http://dx.doi.org/10.1016/j.cmpb.2017.11.015.
• [28] Vogado LHS, Veras RMS, Araujo FHD, Silva RRV, Aires KRT. Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification. Eng Appl Artif Intell 2018;72:415–22.
• [29] Qin F, Gao N, Peng Y, Wu Z, Shen S, Grudtsin A. Fine-grained leukocyte classification with deep residual learning for microscopic images. Comp Methods Prog Biomed 2018;162:243–52.
• [30] Choi JW, Ku Y, Yoo BW, Kim Jung-A, Lee DS, Chai YJ, et al. White blood cell differential count of maturation stages in bone marrow smear using dual-stage convolutional neural networks. PLoS One 2017;12:e0189259.
• [31] Tiwari P, Qian J, Li Q, Wang B, Gupta D, Khanna A, et al. Detection of subtype blood cells using deep learning. Cogn Syst Res 2018;52:1036–44.
• [32] Rehman A, Abbas N, Saba T, Ijaz ur Rahman S, Mehmood Z, Kolivand H. Classification of acute lymphoblastic leukemia using deep learning. Microsc Res Techn 2018. http://dx.doi.org/10.1002/jemt.23139.
• [33] Sarmad S, Samabia S. Acute lymphoblastic leukemia detection and classification of its subtypes using pre-trained deep convolutional neural networks. Technol Cancer Res Treat 2018;17:1–7.
• [34] Zhimin G, Lei W, Luping Z, Jianjia Z. HEp-2 cell image classification with deep convolutional neural networks. IEEE J Biomed Health Inform 2017;21(2):416.
• [35] Zhaohui L, Andrew P, Ilker E, Mahdieh P, Kamolrat S, Kannappan P, et al. CNN based image analysis for malaria diagnosis. Proc IEEE International Conference on Bioinformatics and Biomedicine. 2016. pp. 493–6.
• [36] Yuhang D, Zhuocheng J, Hongda S, David W, Pan A, Lance aVRVB, et al. Evaluations of deep convolutional neural networks for automatic identification of malaria infected cells. Proc IEEE International Conference on Biomedical and Health Informatics. 2017. pp. 101–4.
• [37] Rani P, Oomman, Kaushik SK, Jeny R, Sabu M. Automatic detection of tuberculosis bacilli from microscopic sputum smear images using deep learning methods. Biocybern Biomed Eng 2018;38(3):691.
• [38] Charan J, Biswas T. How to calculate sample size for different study designs in medical research? Indian J Psychol Med 2013;35(2):121–6.
• [39] Roopa BH, Keerthana P, Harishchandra H, Mohan BKS. Development of a robust algorithm for detection of nuclei and classification of white blood cells in peripheral blood smear images. J Med Systems 2018;42:1.
• [40] Di H, Caifeng S, Mohsen A, Yunhong W, Liming C. Local binary patterns and its application to facial image analysis: a survey. IEEE Trans Syst Man Cyber C (Appl Rev) 2011;41 (6):765781.
• [41] Kennith I. Laws, Rapid texture identification. Proc SPIE Image Processing for Missile Guidance, vol. 238. 1980. p. 376.
• [42] Alex K, Ilya S, Geoffrey E. Hinton, ImageNet classification with deep convolutional neural networks. Proc 25th International Conference on Neural Information Processing Systems, vol. 1. 2012. p. 1097.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).

Identyfikatory

DOI

10.1016/j.bbe.2019.01.005