journal article·2021-01Open access

Classification of white blood cells using weighted optimized deformable convolutional neural networks

Xufeng Yao, Kai Sun, Xixi Bu, Congyi Zhao, Yu Jin

Abstract

BACKGROUND: Machine learning (ML) algorithms have been widely used in the classification of white blood cells (WBCs). However, the performance of ML algorithms still needs to be addressed for being short of gold standard data sets, and even the implementation of the proposed algorithms. METHODS: In this study, the method of two-module weighted optimized deformable convolutional neural networks (TWO-DCNN) was proposed for WBC classification. Our algorithm is characterized as two-module transfer learning and deformable convolutional (DC) layers for the betterment of robustness. To validate the performance, our method was compared with classical MLs of VGG16, VGG19, Inception-V3, ResNet-50, support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT) and random forest (RF) on our undisclosed WBC data set and public BCCD data set. RESULTS: TWO-DCNN achieved the best performance with the precisions (PREs) of 95.7%, 94.5% and 91.6%, recalls (RECs) of 95.7%, 94.5% and 91.6%, F1-scores (F1s) of 95.7%, 94.5% and 91.6%, area under curves (AUCs) of 0.98, 0.97 and 0.95 for low-resolution and noisy undisclosed data sets, BCCD data set, respectively. CONCLUSIONS: With accurate feature extraction and optimized network weights, the proposed TWO-DCNN showed the best performance in WBC classification for low-resolution and noisy data sets. It could be used as an alternative method for clinical applications.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Digital Imaging for Blood Diseases · AI in cancer detection · Biosensors and Analytical Detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

College of Medical Imaging, Jiading District Central Hospital, Shanghai University of Medicine and Health Sciences, Shanghai, China

Shanghai Key Laboratory of Molecular Imaging, Shanghai University of Medicine and Health Sciences, Shanghai, China

School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai, China

References (49)

Show source-provided references
1. 10.1002/ijc.2921010.1002/ijc.29210 ↗
2. 10.3322/caac.2133810.3322/caac.21338 ↗
3. 10.3324/haematol.2016.15065610.3324/haematol.2016.150656 ↗
4. 10.1016/j.mpmed.2017.01.01110.1016/j.mpmed.2017.01.011 ↗
5. 10.1002/pbc.2613910.1002/pbc.26139 ↗
6. 10.1088/1757-899X/396/1/01203810.1088/1757-899X/396/1/012038 ↗
7. 10.1016/j.cmpb.2018.05.02410.1016/j.cmpb.2018.05.024 ↗
8. 10.1016/j.measurement.2014.04.00810.1016/j.measurement.2014.04.008 ↗
9. Othman MZ, Mohammed TS, Ali AB. Neural network classification of white blood cell using microscopic images. Int J Adv Comput Sci Appl. 2017;8(5):99–104.
10. 10.3109/21691401.2015.100850610.3109/21691401.2015.1008506 ↗
11. 10.1002/cyto.a.2379410.1002/cyto.a.23794 ↗
12. Habibzadeh M, Krzyżak A, Fevens T. Comparative study of shape, intensity and texture features and support vector machine for white blood cell classification. J Theor Appl Comput Sci. 2013;7(1):20–35.
13. Tingting H, Jianwei Z, Feilong C, et al. A classification algorithm for white blood cells based on the synthetic feature and random forest. J China Univ Metro. 2015;26(4):474–479.
14. 10.1080/21681163.2016.123494810.1080/21681163.2016.1234948 ↗
15. Al-Dulaimi K, Chandran V, Banks J, et al. Classification of white blood cells using bispectral invariant features of nuclei shape. Int Conf Digit Image Comput Tech Appl. Canberra, Australia. 2018;1–8.
16. 10.1016/j.optlastec.2018.11.05710.1016/j.optlastec.2018.11.057 ↗
17. 10.7763/IJCTE.2018.V10.119810.7763/IJCTE.2018.V10.1198 ↗
18. 10.1109/ACCESS.2018.284668510.1109/ACCESS.2018.2846685 ↗
19. Macawile MJ, Qui Ones VV, Ballado A, et al. White blood cell classification and counting using convolutional neural network. Int Conf Control Robot Eng. Nagoya, Japan. 2018;259–263.
20. Yu W, Chang J, Yang C, et al. Automatic classification of leukocytes using deep neural network. Proc Int Conf ASIC. Guiyang, China. 2017:1041–1044.
21. 10.1142/S021800141857006910.1142/S0218001418570069 ↗
22. 10.3233/JIFS-19100010.3233/JIFS-191000 ↗
23. 10.1016/j.irbm.2020.08.00510.1016/j.irbm.2020.08.005 ↗
24. 10.1007/s11517-016-1590-x10.1007/s11517-016-1590-x ↗
25. 10.1007/s10916-018-0962-110.1007/s10916-018-0962-1 ↗
26. Şengür A, Akbulut Y, Budak Ü, et al. White blood cell classification based on shape and deep features. Int Conf Artif Intell Data Process Symp, IDAP. Malatya, Turkey. 2019;:1–4.
27. 10.1038/s41598-020-59215-910.1038/s41598-020-59215-9 ↗
28. 10.1016/j.media.2017.07.00510.1016/j.media.2017.07.005 ↗
29. 10.1016/j.compmedimag.2020.10169910.1016/j.compmedimag.2020.101699 ↗
30. 10.1007/s00500-019-04383-810.1007/s00500-019-04383-8 ↗
31. Habibzadeh M, Jannesari M, Rezaei Z, et al. Automatic white blood cell classification using pre-trained deep learning models: Resnet and inception. Proc SPIE Int Soc Opt Eng. 2018;10696:1069612.
32. 10.1371/journal.pone.018925910.1371/journal.pone.0189259 ↗
33. 10.1088/1742-6596/1201/1/01204510.1088/1742-6596/1201/1/012045 ↗
34. 10.1016/j.bbe.2019.01.00510.1016/j.bbe.2019.01.005 ↗
35. 10.1002/jbio.20200019710.1002/jbio.202000197 ↗
36. 10.1016/j.optlastec.2016.05.01310.1016/j.optlastec.2016.05.013 ↗
37. 10.18280/ria.33050210.18280/ria.330502 ↗
38. Liu L Jiang H He P et al. On the variance of the adaptive learning rate and beyond. Proc Int Conf Learn Representat. Addis Ababa Ethiopia. 2019;:1–13.
39. 10.1049/iet-its.2020.021710.1049/iet-its.2020.0217 ↗
40. 10.1016/j.knosys.2019.04.02510.1016/j.knosys.2019.04.025 ↗
41. Lin M Chen Q Yan S. Network in network. Proc Int Conf Learn Representat. Banff Canada. 2014;:1–10.
42. 10.1016/j.eswa.2020.11321110.1016/j.eswa.2020.113211 ↗
43. 10.1016/j.asoc.2020.10681010.1016/j.asoc.2020.106810 ↗
44. 10.1016/j.cell.2018.02.01010.1016/j.cell.2018.02.010 ↗
45. Perez L Wang J. The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621. 2017.
46. 10.1016/j.mehy.2019.10947210.1016/j.mehy.2019.109472 ↗
47. Jung C Abuhamad M Alikhanov J et al. W-Net: A CNN-based Architecture for White Blood Cells Image Classification. arXiv preprint arXiv:1910.01091. 2019.
48. Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision. Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit. Las Vegas, USA. 2016;:2818–2826.
49. Targ S Almeida D Lyman K. Resnet in resnet: Generalizing residual architectures. Proc Int Conf Learn Representat. San Juan Puerto Rico. 2016;:1–7.