Abstract
Poikilocytosis affects the human body because it causes changes in the shape of Red Blood Cells (RBCs). This aberrant shape and structure of RBCs lead to a number of health issues in our bodies. These issues include lack of oxygen, protein, nutrients, and other substances. In addition, it leads to a number of disorders such as Anemia, Thalassemia, etc. Detection and classification of such cells in Peripheral Blood Smear (PBS) is time-consuming, especially in geographically underserved regions where there is a paucity of hematologists. Hence, the deployment of deep learning for the classification of such cells reduces the workload of hematologists. In this work, a novel hybrid approach using K-mean color quantization segmented-based attention-deep Convolution Neural Network (CNN) with an Extreme Gradient Boosting (XGBoost) algorithm for classifying poikilocytosis has been proposed for detection and classification of abnormal cells.The proposed hybrid model has outperformed the lightweight CNN model and benchmark models on two data sets: one publicly accessible Chula-PIC-Lab data set and one privately collected dataset. On the Chula-PIC-Lab and CCHRC datasets, the proposed model obtains \(95.38\%\) and \(93.43\%\) of \(F_1\)-score on segmentation, \(98.44\%\) and \(98.24\%\) of accuracy on classification; \(98.55\%\) and \(98.28\%\)of \(F_1\)-score on poikilocytosis classification respectively.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
One publicly available Chula-PIC-Lab data set was used in this work.
References
Agrawal T, Choudhary P (2021) FocusCovid: automated COVID-19 detection using deep learning with chest x-ray images. Evol Syst. https://doi.org/10.1007/s12530-021-09385-2
Bandaru SS, Killeen RB, Gupta V Poikilocytosis (2023) Poikilocytosis. National Library of Medicine (NIH): National Center for Biotechnology Information, USA https://www.ncbi.nlm.nih.gov/books/NBK562141/. 21 Feb 2023
Campos Souza PV, Lughofer E (2023) Evolving fuzzy neural classifier that integrates uncertainty from human-expert feedback. Evol Syst 14(2):319–341
Cordelli E, Maulucci G, De Spirito M, Rizzi A, Pitocco D, Soda P (2018) A decision support system for type 1 diabetes mellitus diagnostics based on dual channel analysis of red blood cell membrane fluidity. Comput Methods Programs Biomed 162:263–271
Dhar P, Suganya Devi K, Satti SK, Srinivasan P (2022) Efficient detection and partitioning of overlapped red blood cells using image processing approach. Innov Syst Softw Eng. https://doi.org/10.1007/s11334-022-00478-y
Dhar P, Kothandapani SD, Satti SK, Padmanabhan S (2023) HPKNN: hyper-parameter optimized KNN classifier for classification of poikilocytosis. Int J Imaging Syst Technol. https://doi.org/10.1002/ima.22841
Dhar P, Devi KS, Sekar K, Srinivasan P (2023) Morphology of red blood cells classification using deep learning approach. In: 2023 IEEE 3rd International Conference on Technology, Engineering, Management for Societal Impact Using Marketing, Entrepreneurship and Talent (TEMSMET), pp. 1–6. IEEE
Frackiewicz M, Mandrella A, Palus H (2019) Fast color quantization by k-means clustering combined with image sampling. Symmetry 11(8):963
Goenka N, Tiwari S (2022) Multi-class classification of Alzheimer’s disease through distinct neuroimaging computational approaches using florbetapir pet scans. Evol Syst 1:1–24
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778
Inoue H (2018) Data augmentation by pairing samples for images classification. arXiv preprint arXiv:1801.02929
Jiang M, Shao M, Yang X, He L, Peng T, Wang T, Ke Z, Wang Z, Fang S, Mao Y et al (2022) Automatic classification of red blood cell morphology based on quantitative phase imaging. Int J Optics. https://doi.org/10.1155/2022/1240020
Jiao W, Hao X, Qin C (2021) The image classification method with CNN-XGBoost model based on adaptive particle swarm optimization. Information 12(4):156
Jones KW (2009) Evaluation of cell morphology and introduction to platelet and white blood cell morphology. Clinical hematology and fundamentals of hemostasis. FA Davis Company, pp 93–116
Juang L-H, Wu M-N (2010) Mri brain lesion image detection based on color-converted k-means clustering segmentation. Measurement 43(7):941–949
Khan MS, Salsabil N, Alam MGR, Dewan MAA, Uddin MZ (2022) Cnn-xgboost fusion-based affective state recognition using eeg spectrogram image analysis. Sci Rep 12(1):14122
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Lee H, Chen Y-PP (2014) Cell morphology based classification for red cells in blood smear images. Pattern Recogn Lett 49:155–161
Lucas F, Costa P, Batalha R, Leite D, Škrjanc I (2020) Fault detection in smart grids with time-varying distributed generation using wavelet energy and evolving neural networks. Evol Syst 11:165–180
Malcangi M, Nano G (2021) Biofeedback: E-health prediction based on evolving fuzzy neural network and wearable technologies. Evol Syst 12(3):645–653
Malcangi M, Quan H, Vaini E, Lombardi P, Di Rienzo M (2020) Evolving fuzzy-neural paradigm applied to the recognition and removal of artefactual beats in continuous seismocardiogram recordings. Evol Syst 11:443–452
Melo F et al (2013) Area under the roc curve. Encyclopedia of systems biology 2013
Naruenatthanaset K, Chalidabhongse TH, Palasuwan D, Anantrasirichai N, Palasuwan A (2020) Red blood cell segmentation with overlapping cell separation and classification on imbalanced dataset. arXiv preprint arXiv:2012.01321
Nobakht M, Javidan R, Pourebrahimi A (2022) Demd-iot: a deep ensemble model for iot malware detection using cnns and network traffic. Evolving Systems 1–17
Pang L, Wang J, Zhao L, Wang C, Zhan H (2019) A novel protein subcellular localization method with CNN-XGBoost model for Alzheimer’s disease. Front Genet 9:751
Pasupa K, Tungjitnob S, Vatathanavaro S (2020) Semi-supervised learning with deep convolutional generative adversarial networks for canine red blood cells morphology classification. Multimed Tools Appl 79:34209–34226
Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621
Rana P, Sowmya A, Meijering E, Song Y (2022) Data augmentation with improved regularisation and sampling for imbalanced blood cell image classification. Sci Rep 12(1):18101
Ren X, Guo H, Li S, Wang S, Li J (2017) A novel image classification method with cnn-xgboost model. In: Digital Forensics and Watermarking: 16th International Workshop, IWDW 2017, Magdeburg, Germany, August 23-25, 2017, Proceedings 16, pp. 378–390. Springer
Rodrigues FPS, Silva AM, Lemos AP (2022) Evolving fuzzy predictor with multivariable gaussian participatory learning and multi-innovations recursive weighted least squares: efmi. Evol Syst 13(5):667–686
Sengar N, Burget R, Dutta MK (2022) A vision transformer based approach for analysis of plasmodium vivax life cycle for malaria prediction using thin blood smear microscopic images. Comput Methods Programs Biomed 224:106996
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Suganya Devi K, Arutperumjothi G, Srinivasan P (2021) Diagnosis evaluation and interpretation of qualitative abnormalities in peripheral blood smear images-a review. Health informatics: a computational perspective in healthcare. Springer, pp 341–365
Thongsuwan S, Jaiyen S, Padcharoen A, Agarwal P (2021) Convxgb: a new deep learning model for classification problems based on CNN and XGBoost. Nucl Eng Technol 53(2):522–531
Tong B, Wen T, Du Y, Pan T (2023) Cell image instance segmentation based on polarmask using weak labels. Comput Methods Programs Biomed 231:107426
Wong A, Anantrasirichai N, Chalidabhongse TH, Palasuwan D, Palasuwan A, Bull D (2021) Analysis of vision-based abnormal red blood cell classification. arXiv preprint arXiv:2106.00389
Wu M-N, Lin C-C, Chang C-C (2007) Brain tumor detection using color-based k-means clustering segmentation. In: Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP 2007), vol. 2, pp. 245–250. IEEE
Yi F, Moon I, Javidi B (2016) Cell morphology-based classification of red blood cells using holographic imaging informatics. Biomed Opt Express 7(6):2385–2399
Acknowledgements
The Cachar Cancer Hospital & Research Center (CCHRC) in Silchar, India has provided ongoing assistance in clinical areas, and the National Institute of Technology in Silchar, India has supported the research. This work acknowledges this organization.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest.
Informed consent
In this study, informed consent is not required.
Research involving human participants and/or animals
In this study, human or animal participation is not required.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dhar, P., Suganya Devi, K., Satti, S.K. et al. An hybrid soft attention based XGBoost model for classification of poikilocytosis blood cells. Evolving Systems 15, 523–539 (2024). https://doi.org/10.1007/s12530-023-09549-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12530-023-09549-2