IEICE TRANSACTIONS on Information
The Effectiveness of Data Augmentation for Mature White Blood Cell Image Classification in Deep Learning — Selection of an Optimal Technique for Hematological Morphology Recognition —
Summary :
The data augmentation method is known as a helpful technique to generate a dataset with a large number of images from one with a small number of images for supervised training in deep learning. However, a low validity augmentation method for image recognition was reported in a recent study on artificial intelligence (AI). This study aimed to clarify the optimal data augmentation method in deep learning model generation for the recognition of white blood cells (WBCs). Study Design: We conducted three different data augmentation methods (rotation, scaling, and distortion) on original WBC images, with each AI model for WBC recognition generated by supervised training. The subjects of the clinical assessment were 51 healthy persons. Thin-layer blood smears were prepared from peripheral blood and subjected to May-Grünwald-Giemsa staining. Results: The only significantly effective technique among the AI models for WBC recognition was data augmentation with rotation. By contrast, the effectiveness of both image distortion and image scaling was poor, and improved accuracy was limited to a specific WBC subcategory. Conclusion: Although data augmentation methods are often used for achieving high accuracy in AI generation with supervised training, we consider that it is necessary to select the optimal data augmentation method for medical AI generation based on the characteristics of medical images.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.5 pp.707-714
- Publication Date
- 2023/05/01
- Publicized
- 2022/11/22
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022DLP0066
- Type of Manuscript
- Special Section PAPER (Special Section on Deep Learning Technologies: Architecture, Optimization, Techniques, and Applications)
- Category
- Smart Healthcare
Authors
Hiroyuki NOZAKA
Hirosaki University
Kosuke KAMATA
Hirosaki University
Kazufumi YAMAGATA
Hirosaki University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hiroyuki NOZAKA, Kosuke KAMATA, Kazufumi YAMAGATA, "The Effectiveness of Data Augmentation for Mature White Blood Cell Image Classification in Deep Learning — Selection of an Optimal Technique for Hematological Morphology Recognition —" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 5, pp. 707-714, May 2023, doi: 10.1587/transinf.2022DLP0066.
Abstract: The data augmentation method is known as a helpful technique to generate a dataset with a large number of images from one with a small number of images for supervised training in deep learning. However, a low validity augmentation method for image recognition was reported in a recent study on artificial intelligence (AI). This study aimed to clarify the optimal data augmentation method in deep learning model generation for the recognition of white blood cells (WBCs). Study Design: We conducted three different data augmentation methods (rotation, scaling, and distortion) on original WBC images, with each AI model for WBC recognition generated by supervised training. The subjects of the clinical assessment were 51 healthy persons. Thin-layer blood smears were prepared from peripheral blood and subjected to May-Grünwald-Giemsa staining. Results: The only significantly effective technique among the AI models for WBC recognition was data augmentation with rotation. By contrast, the effectiveness of both image distortion and image scaling was poor, and improved accuracy was limited to a specific WBC subcategory. Conclusion: Although data augmentation methods are often used for achieving high accuracy in AI generation with supervised training, we consider that it is necessary to select the optimal data augmentation method for medical AI generation based on the characteristics of medical images.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DLP0066/_p
Copy
@ARTICLE{e106-d_5_707,
author={Hiroyuki NOZAKA, Kosuke KAMATA, Kazufumi YAMAGATA, },
journal={IEICE TRANSACTIONS on Information},
title={The Effectiveness of Data Augmentation for Mature White Blood Cell Image Classification in Deep Learning — Selection of an Optimal Technique for Hematological Morphology Recognition —},
year={2023},
volume={E106-D},
number={5},
pages={707-714},
abstract={The data augmentation method is known as a helpful technique to generate a dataset with a large number of images from one with a small number of images for supervised training in deep learning. However, a low validity augmentation method for image recognition was reported in a recent study on artificial intelligence (AI). This study aimed to clarify the optimal data augmentation method in deep learning model generation for the recognition of white blood cells (WBCs). Study Design: We conducted three different data augmentation methods (rotation, scaling, and distortion) on original WBC images, with each AI model for WBC recognition generated by supervised training. The subjects of the clinical assessment were 51 healthy persons. Thin-layer blood smears were prepared from peripheral blood and subjected to May-Grünwald-Giemsa staining. Results: The only significantly effective technique among the AI models for WBC recognition was data augmentation with rotation. By contrast, the effectiveness of both image distortion and image scaling was poor, and improved accuracy was limited to a specific WBC subcategory. Conclusion: Although data augmentation methods are often used for achieving high accuracy in AI generation with supervised training, we consider that it is necessary to select the optimal data augmentation method for medical AI generation based on the characteristics of medical images.},
keywords={},
doi={10.1587/transinf.2022DLP0066},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - The Effectiveness of Data Augmentation for Mature White Blood Cell Image Classification in Deep Learning — Selection of an Optimal Technique for Hematological Morphology Recognition —
T2 - IEICE TRANSACTIONS on Information
SP - 707
EP - 714
AU - Hiroyuki NOZAKA
AU - Kosuke KAMATA
AU - Kazufumi YAMAGATA
PY - 2023
DO - 10.1587/transinf.2022DLP0066
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - The data augmentation method is known as a helpful technique to generate a dataset with a large number of images from one with a small number of images for supervised training in deep learning. However, a low validity augmentation method for image recognition was reported in a recent study on artificial intelligence (AI). This study aimed to clarify the optimal data augmentation method in deep learning model generation for the recognition of white blood cells (WBCs). Study Design: We conducted three different data augmentation methods (rotation, scaling, and distortion) on original WBC images, with each AI model for WBC recognition generated by supervised training. The subjects of the clinical assessment were 51 healthy persons. Thin-layer blood smears were prepared from peripheral blood and subjected to May-Grünwald-Giemsa staining. Results: The only significantly effective technique among the AI models for WBC recognition was data augmentation with rotation. By contrast, the effectiveness of both image distortion and image scaling was poor, and improved accuracy was limited to a specific WBC subcategory. Conclusion: Although data augmentation methods are often used for achieving high accuracy in AI generation with supervised training, we consider that it is necessary to select the optimal data augmentation method for medical AI generation based on the characteristics of medical images.
ER -
English
