White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization
Accurate and robust human immune system assessment through white blood cell evaluation require computer-aided tools with pathologist-level accuracy. This work presents a multi-attention leukocytes subtype classification method by leveraging fine-grained and spatial locality attributes of white blood...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/6/4/122 |
| _version_ | 1797461424456335360 |
|---|---|
| author | Nasrin Bayat Diane D. Davey Melanie Coathup Joon-Hyuk Park |
| author_facet | Nasrin Bayat Diane D. Davey Melanie Coathup Joon-Hyuk Park |
| author_sort | Nasrin Bayat |
| collection | DOAJ |
| description | Accurate and robust human immune system assessment through white blood cell evaluation require computer-aided tools with pathologist-level accuracy. This work presents a multi-attention leukocytes subtype classification method by leveraging fine-grained and spatial locality attributes of white blood cell. The proposed framework comprises three main components: texture-aware/attention map generation blocks, attention regularization, and attention-based data augmentation. The developed framework is applicable to general CNN-based architectures and enhances decision making by paying specific attention to the discriminative regions of a white blood cell. The performance of the proposed method/model was evaluated through an extensive set of experiments and validation. The obtained results demonstrate the superior performance of the model achieving 99.69 % accuracy compared to other state-of-the-art approaches. The proposed model is a good alternative and complementary to existing computer diagnosis tools to assist pathologists in evaluating white blood cells from blood smear images. |
| first_indexed | 2024-03-09T17:20:10Z |
| format | Article |
| id | doaj.art-7585fb036c754a6c9b34229725bfb890 |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-09T17:20:10Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-7585fb036c754a6c9b34229725bfb8902023-11-24T13:17:40ZengMDPI AGBig Data and Cognitive Computing2504-22892022-10-016412210.3390/bdcc6040122White Blood Cell Classification Using Multi-Attention Data Augmentation and RegularizationNasrin Bayat0Diane D. Davey1Melanie Coathup2Joon-Hyuk Park3Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL 32816, USACollege of Medicine, University of Central Florida, 6850 Lake Nona Blvd, Orlando, FL 32827, USACollege of Medicine, University of Central Florida, 6850 Lake Nona Blvd, Orlando, FL 32827, USADepartment of Electrical and Computer Engineering, University of Central Florida, Orlando, FL 32816, USAAccurate and robust human immune system assessment through white blood cell evaluation require computer-aided tools with pathologist-level accuracy. This work presents a multi-attention leukocytes subtype classification method by leveraging fine-grained and spatial locality attributes of white blood cell. The proposed framework comprises three main components: texture-aware/attention map generation blocks, attention regularization, and attention-based data augmentation. The developed framework is applicable to general CNN-based architectures and enhances decision making by paying specific attention to the discriminative regions of a white blood cell. The performance of the proposed method/model was evaluated through an extensive set of experiments and validation. The obtained results demonstrate the superior performance of the model achieving 99.69 % accuracy compared to other state-of-the-art approaches. The proposed model is a good alternative and complementary to existing computer diagnosis tools to assist pathologists in evaluating white blood cells from blood smear images.https://www.mdpi.com/2504-2289/6/4/122attention mechanismmedical image analysisdeep learningblood cell detectionconvolutional neural networks |
| spellingShingle | Nasrin Bayat Diane D. Davey Melanie Coathup Joon-Hyuk Park White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization Big Data and Cognitive Computing attention mechanism medical image analysis deep learning blood cell detection convolutional neural networks |
| title | White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization |
| title_full | White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization |
| title_fullStr | White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization |
| title_full_unstemmed | White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization |
| title_short | White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization |
| title_sort | white blood cell classification using multi attention data augmentation and regularization |
| topic | attention mechanism medical image analysis deep learning blood cell detection convolutional neural networks |
| url | https://www.mdpi.com/2504-2289/6/4/122 |
| work_keys_str_mv | AT nasrinbayat whitebloodcellclassificationusingmultiattentiondataaugmentationandregularization AT dianeddavey whitebloodcellclassificationusingmultiattentiondataaugmentationandregularization AT melaniecoathup whitebloodcellclassificationusingmultiattentiondataaugmentationandregularization AT joonhyukpark whitebloodcellclassificationusingmultiattentiondataaugmentationandregularization |