Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization
Clinically, the proportion and classification of white blood cell (WBC)s are currently established using manual methods, which rely on subjective judgment. Therefore, many studies are being conducted to automate the classification of WBC types. Several studies have employed deep learning (DL) or mac...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10849518/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576777975758848 |
|---|---|
| author | Taeyeon Gil Sukjun Lee Onseok Lee |
| author_facet | Taeyeon Gil Sukjun Lee Onseok Lee |
| author_sort | Taeyeon Gil |
| collection | DOAJ |
| description | Clinically, the proportion and classification of white blood cell (WBC)s are currently established using manual methods, which rely on subjective judgment. Therefore, many studies are being conducted to automate the classification of WBC types. Several studies have employed deep learning (DL) or machine learning (ML) methods; no significant difference in performance between the two methods has been demonstrated. However, if the feature extraction and selection processes are optimized when using ML for WBC classification, its performance is improved. Therefore, in this study, we proposed an ML-based optimization system for five normal WBC classifications. Open datasets, Raabin-WBC, and private data were used. WBCs were segmented into nucleus, cytoplasm, and cell regions using U-Net, a DL model. The nucleus showed high segmentation performance with an average accuracy of 98.58% and a Dice coefficient of 0.9233, whereas the cells achieved an average accuracy of 99.47% and a Dice coefficient of 0.9324. Among the five multiple classifiers, the support vector machine achieved the highest accuracy of 97.36% and was chosen for WBC classification. Features used for WBC classification were determined through three experiments, resulting in a final selection of 108 features combining intensity histogram, hue saturation value, and CIE La<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>b<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> features. When using the selected features, the classification accuracy was 98.22%, indicating a high performance. Segmentation and classification of WBCs were performed using a graphical user interface and required approximately 137 s. The proposed system in this study is expected to enhance the efficiency of the existing PBS tests. |
| format | Article |
| id | doaj-art-b21719002c0446e290e079a02b9f1756 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b21719002c0446e290e079a02b9f17562025-01-31T00:01:26ZengIEEEIEEE Access2169-35362025-01-0113176621767210.1109/ACCESS.2025.353271910849518Machine Learning-Based Normal White Blood Cell Multi-Classification OptimizationTaeyeon Gil0Sukjun Lee1Onseok Lee2https://orcid.org/0000-0002-3696-9353Department of Software Convergence, Graduate School, Soonchunhyang University, Asan, Chungcheongnam-do, Republic of KoreaDepartment of Biomedical Laboratory Science, College of Health and Medical Sciences, Cheongju University, Cheongju, Chungcheongbuk-do, Republic of KoreaDepartment of Software Convergence, Graduate School, Soonchunhyang University, Asan, Chungcheongnam-do, Republic of KoreaClinically, the proportion and classification of white blood cell (WBC)s are currently established using manual methods, which rely on subjective judgment. Therefore, many studies are being conducted to automate the classification of WBC types. Several studies have employed deep learning (DL) or machine learning (ML) methods; no significant difference in performance between the two methods has been demonstrated. However, if the feature extraction and selection processes are optimized when using ML for WBC classification, its performance is improved. Therefore, in this study, we proposed an ML-based optimization system for five normal WBC classifications. Open datasets, Raabin-WBC, and private data were used. WBCs were segmented into nucleus, cytoplasm, and cell regions using U-Net, a DL model. The nucleus showed high segmentation performance with an average accuracy of 98.58% and a Dice coefficient of 0.9233, whereas the cells achieved an average accuracy of 99.47% and a Dice coefficient of 0.9324. Among the five multiple classifiers, the support vector machine achieved the highest accuracy of 97.36% and was chosen for WBC classification. Features used for WBC classification were determined through three experiments, resulting in a final selection of 108 features combining intensity histogram, hue saturation value, and CIE La<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>b<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> features. When using the selected features, the classification accuracy was 98.22%, indicating a high performance. Segmentation and classification of WBCs were performed using a graphical user interface and required approximately 137 s. The proposed system in this study is expected to enhance the efficiency of the existing PBS tests.https://ieeexplore.ieee.org/document/10849518/Peripheral blood smearnormal white blood cellsfeature selectionmultiple classifiersgraphical user interface |
| spellingShingle | Taeyeon Gil Sukjun Lee Onseok Lee Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization IEEE Access Peripheral blood smear normal white blood cells feature selection multiple classifiers graphical user interface |
| title | Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization |
| title_full | Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization |
| title_fullStr | Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization |
| title_full_unstemmed | Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization |
| title_short | Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization |
| title_sort | machine learning based normal white blood cell multi classification optimization |
| topic | Peripheral blood smear normal white blood cells feature selection multiple classifiers graphical user interface |
| url | https://ieeexplore.ieee.org/document/10849518/ |
| work_keys_str_mv | AT taeyeongil machinelearningbasednormalwhitebloodcellmulticlassificationoptimization AT sukjunlee machinelearningbasednormalwhitebloodcellmulticlassificationoptimization AT onseoklee machinelearningbasednormalwhitebloodcellmulticlassificationoptimization |