Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features
White blood cells (WBCs) are one of the main components of blood produced by the bone marrow. WBCs are part of the immune system that protects the body from infectious diseases and an increase or decrease in the amount of any type that causes a particular disease. Thus, recognizing the WBC types is...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/11/1899 |
| _version_ | 1797597747098943488 |
|---|---|
| author | Fekry Olayah Ebrahim Mohammed Senan Ibrahim Abdulrab Ahmed Bakri Awaji |
| author_facet | Fekry Olayah Ebrahim Mohammed Senan Ibrahim Abdulrab Ahmed Bakri Awaji |
| author_sort | Fekry Olayah |
| collection | DOAJ |
| description | White blood cells (WBCs) are one of the main components of blood produced by the bone marrow. WBCs are part of the immune system that protects the body from infectious diseases and an increase or decrease in the amount of any type that causes a particular disease. Thus, recognizing the WBC types is essential for diagnosing the patient’s health and identifying the disease. Analyzing blood samples to determine the amount and WBC types requires experienced doctors. Artificial intelligence techniques were applied to analyze blood samples and classify their types to help doctors distinguish between types of infectious diseases due to increased or decreased WBC amounts. This study developed strategies for analyzing blood slide images to classify WBC types. The first strategy is to classify WBC types by the SVM-CNN technique. The second strategy for classifying WBC types is by SVM based on hybrid CNN features, which are called VGG19-ResNet101-SVM, ResNet101-MobileNet-SVM, and VGG19-ResNet101-MobileNet-SVM techniques. The third strategy for classifying WBC types by FFNN is based on a hybrid model of CNN and handcrafted features. With MobileNet and handcrafted features, FFNN achieved an AUC of 99.43%, accuracy of 99.80%, precision of 99.75%, specificity of 99.75%, and sensitivity of 99.68%. |
| first_indexed | 2024-03-11T03:09:51Z |
| format | Article |
| id | doaj.art-b8e8a86f286445928764e3d4a9d3071f |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T03:09:51Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-b8e8a86f286445928764e3d4a9d3071f2023-11-18T07:42:38ZengMDPI AGDiagnostics2075-44182023-05-011311189910.3390/diagnostics13111899Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted FeaturesFekry Olayah0Ebrahim Mohammed Senan1Ibrahim Abdulrab Ahmed2Bakri Awaji3Department of Information System, Faculty Computer Science and information System, Najran University, Najran 66462, Saudi ArabiaDepartment of Artificial Intelligence, Faculty of Computer Science and Information Technology, Alrazi University, Sana’a, YemenComputer Department, Applied College, Najran University, Najran 66462, Saudi ArabiaDepartment of Computer Science, Faculty of Computer Science and Information System, Najran University, Najran 66462, Saudi ArabiaWhite blood cells (WBCs) are one of the main components of blood produced by the bone marrow. WBCs are part of the immune system that protects the body from infectious diseases and an increase or decrease in the amount of any type that causes a particular disease. Thus, recognizing the WBC types is essential for diagnosing the patient’s health and identifying the disease. Analyzing blood samples to determine the amount and WBC types requires experienced doctors. Artificial intelligence techniques were applied to analyze blood samples and classify their types to help doctors distinguish between types of infectious diseases due to increased or decreased WBC amounts. This study developed strategies for analyzing blood slide images to classify WBC types. The first strategy is to classify WBC types by the SVM-CNN technique. The second strategy for classifying WBC types is by SVM based on hybrid CNN features, which are called VGG19-ResNet101-SVM, ResNet101-MobileNet-SVM, and VGG19-ResNet101-MobileNet-SVM techniques. The third strategy for classifying WBC types by FFNN is based on a hybrid model of CNN and handcrafted features. With MobileNet and handcrafted features, FFNN achieved an AUC of 99.43%, accuracy of 99.80%, precision of 99.75%, specificity of 99.75%, and sensitivity of 99.68%.https://www.mdpi.com/2075-4418/13/11/1899deep learningFFNNSVMfusion featureshandcrafted featuresWBC |
| spellingShingle | Fekry Olayah Ebrahim Mohammed Senan Ibrahim Abdulrab Ahmed Bakri Awaji Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features Diagnostics deep learning FFNN SVM fusion features handcrafted features WBC |
| title | Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features |
| title_full | Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features |
| title_fullStr | Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features |
| title_full_unstemmed | Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features |
| title_short | Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features |
| title_sort | blood slide image analysis to classify wbc types for prediction haematology based on a hybrid model of cnn and handcrafted features |
| topic | deep learning FFNN SVM fusion features handcrafted features WBC |
| url | https://www.mdpi.com/2075-4418/13/11/1899 |
| work_keys_str_mv | AT fekryolayah bloodslideimageanalysistoclassifywbctypesforpredictionhaematologybasedonahybridmodelofcnnandhandcraftedfeatures AT ebrahimmohammedsenan bloodslideimageanalysistoclassifywbctypesforpredictionhaematologybasedonahybridmodelofcnnandhandcraftedfeatures AT ibrahimabdulrabahmed bloodslideimageanalysistoclassifywbctypesforpredictionhaematologybasedonahybridmodelofcnnandhandcraftedfeatures AT bakriawaji bloodslideimageanalysistoclassifywbctypesforpredictionhaematologybasedonahybridmodelofcnnandhandcraftedfeatures |