Abstract
Sickle Cell Anemia (SCA) is a disorder in Red Blood Cells (RBCs) of human blood. Children under five years and pregnant women are mostly affected by SCA. Early diagnosis of this ailment can save lives. In recent years, the computer aided diagnosis of SCA is preferred to resolve this issue. A novel and effective deep learning approach for identification of sickle cell anemia is proposed in this work. Around nine hundred microscopic images of human red blood cells are obtained from the public database ‘erythrocytes IDB’. All the images are resized uniformly. About 2048 deep features are extracted from the fully connected layer of pre-trained model InceptionV3. These features are further subjected to classification using optimization-based methods. An improved wrapper-based feature selection technique is implemented using Multi- Objective Binary Grey Wolf Optimization (MO-BGWO) approach with KNN and SVM for classification. The detection of sickle cell is also performed using typical InceptionV3 model by using SoftMax layer. It is observed that the performance of the proposed system seems to be high when compared to the classification using the original InceptionV3 model. The results are validated by various evaluation metrics such as accuracy, precision, sensitivity, specificity and F1-score. The SVM classifier yields high accuracy of about 96%. The optimal subset of deep features along with SVM enhances the system performance in the proposed work. Thus, the proposed approach is appropriate for pathologists to take early clinical decisions on detection of sickle cells.
-
Research funding: Not applicable.
-
Author contributions: (1) All authors contributed their ideas and concepts in identifying recent research problem. (2) Design of the work formed by corresponding author and it is corrected and approved by co-authors. (3) The acquisition of microscopic images from public database, analysis, interpretation of data for the work and drafting the work are carried out by corresponding author. (4) Further, critical review and revisions are guided by co-authors starting from spell check to intellectual content. All corrections are incorporated and approved by all. (5) The final manuscript is completely team work and sculptured by all authors. (6) The authors ensure the accuracy or integrity of the work. The proposed research article is unique which is not submitted before anywhere.
-
Competing interests: The authors have no conflict of interest (financial, personal or professional) in connection with manuscript.
-
Informed consent: Not applicable.
-
Ethical approval: Not applicable.
References
1. Kato, GJ, Gladwin, MT, Steinberg, MH. Deconstructing sickle cell disease: reappraisal of the role of hemolysis in the development of clinical sub phenotypes. Blood Rev 2017;21:37–47. https://doi.org/10.1016/j.blre.2006.07.001.Search in Google Scholar PubMed PubMed Central
2. Piety, NZ, Shevkoplyas, SS. Paper based diagnostics: rethinking conventional sickle cell screening to improve access to high quality health care in resource limited settings. IEEE Pulse 2017;8:1–10. https://doi.org/10.1109/mpul.2017.2678658.Search in Google Scholar
3. Li, Q, He, X, Wang, Y, Liu, H, Xu, D, Guo, F. Review of spectral imaging technology in biomedical engineering: achievements and challenges. Biomed Opt 2013;18:100901. https://doi.org/10.1117/1.jbo.18.10.100901.Search in Google Scholar PubMed
4. Wang, Q, Wang, J, Zhou, M, Li, Q, Wang, Y. Spectral-spatial feature-based neural network method for acute lymphoblastic leukemia cell identification via microscopic hyperspectral imaging technology. Biomed Opt Express 2017;8:3017–28. https://doi.org/10.1364/boe.8.003017.Search in Google Scholar PubMed PubMed Central
5. Qian, W, Jianbiao, W, Mei, Z, Qingli, L, Ying, W, Junhao, C. A 3D attention networks for classification of white blood cells from microscopy hyperspectral images. Opt Laser Technol 2021;139:106931. https://doi.org/10.1016/j.optlastec.2021.106931.Search in Google Scholar
6. Biaosheng, S, Mei, Z, Menghan, H, Qingli, L, Li, S, Ying, W. A blood cell dataset for lymphoma classification using faster R-CNN. Biotechnol Biotechnol Equip 2020;34:413–20. https://doi.org/10.1080/13102818.2020.1765871.Search in Google Scholar
7. Mohamad, AS, Halim, NSA, Nordin, MN, Hamzah, R, Sathar, J. Automated detection of human RBC in diagnosing sickle cell anemia with laplacian of gaussian filter. In: 2018 IEEE conference on systems, process and control (ICSPC 2018). Melaka, Malaysia; 2018.10.1109/SPC.2018.8704128Search in Google Scholar
8. Abdulraheem, FM, Humaidi, AJ, Oleiwi, SR. Image processing-based diagnosis of sickle cell anemia in erythrocytes. In: IEEE annual conference on new trends in information and communications technology applications – (NTICT’2017) Baghdad, Iraq; 2017.10.1109/NTICT.2017.7976124Search in Google Scholar
9. Di, RC, Loddo, A, Putzu, L. Detection of red and white blood cells from microscopic blood images using a region proposal approach. Comput Biol Med 2019;116:1–27.10.1016/j.compbiomed.2019.103530Search in Google Scholar PubMed
10. Fatimah, AH, Shiroq, AM, Heba, K. Red blood cell segmentation by thresholding and Canny detector. Procedia Comput Sci 2018;141:327–34. https://doi.org/10.1016/j.procs.2018.10.193.Search in Google Scholar
11. Too, J, Abdullah, AR, Saad, NM, Ali, NM, Tee, W. A new competitive binary grey wolf optimizer to solve the feature selection problem in EMG signals classification. Computers 2018;7:58. https://doi.org/10.3390/computers7040058.Search in Google Scholar
12. Vijayalakshmi, A, Rajesh, KB. Deep learning approach to detect malaria from microscopic images. Multimed Tools 2020;79:15297–317. https://doi.org/10.1007/s11042-019-7162-y.Search in Google Scholar
13. Hany, AE. Healthy and unhealthy red blood cell detection in human blood smears using neural networks. Micron 2016;83:32–41. https://doi.org/10.1016/j.micron.2016.01.008.Search in Google Scholar PubMed
14. Hany, AE. Detecting distorted and benign blood cells using the Hough transform based on neural networks and decision trees. In: Emerging trends in image processing computer vision and pattern recognition. Amsterdam, Netherlands: Elsevier; 2015, vol. 30:1–10 pp.Search in Google Scholar
15. Khan, MA, Ashraf, I, Alhaisoni, M, Damasevicius, R, Scherer, R, Bukhari, RA. Multimodal brain tumor classification using deep learning and robust feature selection: a machine learning application for radiologists. Diagnostics 2020;10:565. https://doi.org/10.3390/diagnostics10080565.Search in Google Scholar PubMed PubMed Central
16. Chantar, H, Mafarja, M, Alsawalqah, H, Ali Asghar, H, Ibrahim, A, Faris, H. Feature selection using binary grey wolf optimizer with elite-based crossover for Arabic text classification. Neural Comput Appl 2019;32:1–20. https://doi.org/10.1007/s00521-019-04368-6.Search in Google Scholar
17. Emary, E, Zawbaa, HM, Grosan, C, Hassenian, AE. Feature subset selection approach by gray-wolf optimization. In: Afro-European conference for industrial advancement (AECIA). Advances in intelligent systems and computing; 2018, vol 334:1–10 pp.10.1007/978-3-319-13572-4_1Search in Google Scholar
18. Seyedali, M, Seyed, MM, Andrew, L. Grey wolf optimizer. Adv Eng Software 2014;69:46–61.10.1016/j.advengsoft.2013.12.007Search in Google Scholar
19. Hossam, MZ, Hassanien, EE. Binary grey wolf optimization approaches for feature selection. Neurocomputing 2016;172:371–81.10.1016/j.neucom.2015.06.083Search in Google Scholar
20. Too, J, Abdul, RA. Opposition based competitive grey wolf optimizer for EMG feature selection. Evol Intell 2020;14:22–30. https://doi.org/10.1007/s12065-020-00441-5.Search in Google Scholar
21. Cszegedy, S, Vanhoucke, V, Ioffe, S, Shlens, J, Wojna, Z. Rethinking the inception architecture for computer vision. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA; 2016.10.1109/CVPR.2016.308Search in Google Scholar
22. Takarli, F, Aghagolzadeh, A, Seyedarabi, H. Combination of high-level features with low-level features for detection of pedestrian. Signal Image Video Process 2016;10:93–101. https://doi.org/10.1007/s11760-014-0706-8.Search in Google Scholar
23. Emary, E, Waleed, Y, Hassanien, AE, Snasel, V. Multi-objective gray-wolf optimization for attribute reduction. Procedia Comput Sci 2015;65:623–32. https://doi.org/10.1016/j.procs.2015.09.006.Search in Google Scholar
24. Chy, TS, Rahaman, MA. Automatic sickle cell anemia detection using image processing technique. In: 2018 international conference on advancement in electrical and electronic engineering (ICAEEE). Gazipur, Bangladesh; 2018.10.1109/ICAEEE.2018.8642984Search in Google Scholar
25. Patgiri, C, Ganguly, A. Red blood cell and sickle cell detection from microscopic blood images of sickle cell anemic patient. In: 2019 international conference on wireless communications signal processing and networking (WiSPNET), Chennai, India; 2019.10.1109/WiSPNET45539.2019.9032790Search in Google Scholar
26. Chy, TS, Rahaman, MA. A comparative analysis by KNN, SVM & ELM classification to detect sickle cell anemia. In: 2019 international conference on robotics, electrical and signal processing techniques (ICREST). Dhaka, Bangladesh; 2019.10.1109/ICREST.2019.8644410Search in Google Scholar
27. Ilyas, S, Sher, M, Du, E, Asghar, W. Smartphone-based sickle cell disease detection and monitoring for point-of-care settings. Biosens Bioelectron 2020;165:1–7. https://doi.org/10.1016/j.bios.2020.112417.Search in Google Scholar PubMed PubMed Central
28. Laith, A, Mohammed, AF, Omran, AS, Zhang, J, Ye, D. Deep learning models for classification of red blood cells in microscopy images to aid in sickle cell anemia diagnosis. Electronics 2020;9:1–18.10.3390/electronics9030427Search in Google Scholar
29. Laith, A, Omran, AS, Fadhel, MA, Farhan, L, Zhang, J. Classification of red blood cells in sickle cell anemia using deep convolutional neural network. Nature 2020;940:550–9.10.1007/978-3-030-16657-1_51Search in Google Scholar
30. Hajara, AA, Mohd, AAR, Sudirman, RS, Ramli, N. A deep learning AlexNet model for classification of red blood cells in sickle cell anemia. IAES Int J Artif Intell 2021;9:221–8. https://doi.org/10.11591/ijai.v9.i2.pp221-228.Search in Google Scholar
31. Zhang, M, Xiang, L, Mengjia, X, Quanzheng, L. Image segmentation and classification for sickle cell disease using deformable U-Net. q-bio.CB 2017;1710:1–10.Search in Google Scholar
32. Kevin, CKH, Rivenson, Y. Automated screening of sickle cells using a Smartphone-based microscope and deep learning. Nature, NPJ Digit Med 2020;76:1–8.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
