An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques
Acute Lymphoblastic Leukemia (ALL) is a cancer that infects the blood cells causing the development of lymphocytes in large numbers. Diagnostic tests are costly and very time-consuming. It is important to diagnose ALL using Peripheral Blood Smear (PBS) images, especially in the initial screening cas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/10760 |
| _version_ | 1797469255542767616 |
|---|---|
| author | Nada M. Sallam Ahmed I. Saleh H. Arafat Ali Mohamed M. Abdelsalam |
| author_facet | Nada M. Sallam Ahmed I. Saleh H. Arafat Ali Mohamed M. Abdelsalam |
| author_sort | Nada M. Sallam |
| collection | DOAJ |
| description | Acute Lymphoblastic Leukemia (ALL) is a cancer that infects the blood cells causing the development of lymphocytes in large numbers. Diagnostic tests are costly and very time-consuming. It is important to diagnose ALL using Peripheral Blood Smear (PBS) images, especially in the initial screening cases. Several issues affect the examination process such as diagnostic error, symptoms, and nonspecific nature signs of ALL. Therefore, the objective of this study is to enforce machine-learning classifiers in the detection of Acute Lymphoblastic Leukemia as benign or malignant after using the grey wolf optimization algorithm in feature selection. The images have been enhanced by using an adaptive threshold to improve the contrast and remove errors. The model is based on grey wolf optimization technology which has been developed for feature reduction. Finally, acute lymphoblastic leukemia has been classified into benign and malignant using K-nearest neighbors (KNN), support vector machine (SVM), naïve Bayes (NB), and random forest (RF) classifiers. The best accuracy, sensitivity, and specificity of this model were 99.69%, 99.5%, and 99%, respectively, after using the grey wolf optimization algorithm in feature selection. To ensure the effectiveness of the proposed model, comparative results with other classification techniques have been included. |
| first_indexed | 2024-03-09T19:18:47Z |
| format | Article |
| id | doaj.art-196ecdab48e24a94a77b0dd3a0742785 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:18:47Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-196ecdab48e24a94a77b0dd3a07427852023-11-24T03:32:23ZengMDPI AGApplied Sciences2076-34172022-10-0112211076010.3390/app122110760An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning TechniquesNada M. Sallam0Ahmed I. Saleh1H. Arafat Ali2Mohamed M. Abdelsalam3Nile Higher Institute for Commercial Science and Computer Technology, Mansoura 35511, EgyptComputer Engineering and Control Systems Department, Faculty of Engineering, Mansoura University, Mansoura 35511, EgyptComputer Engineering and Control Systems Department, Faculty of Engineering, Mansoura University, Mansoura 35511, EgyptComputer Engineering and Control Systems Department, Faculty of Engineering, Mansoura University, Mansoura 35511, EgyptAcute Lymphoblastic Leukemia (ALL) is a cancer that infects the blood cells causing the development of lymphocytes in large numbers. Diagnostic tests are costly and very time-consuming. It is important to diagnose ALL using Peripheral Blood Smear (PBS) images, especially in the initial screening cases. Several issues affect the examination process such as diagnostic error, symptoms, and nonspecific nature signs of ALL. Therefore, the objective of this study is to enforce machine-learning classifiers in the detection of Acute Lymphoblastic Leukemia as benign or malignant after using the grey wolf optimization algorithm in feature selection. The images have been enhanced by using an adaptive threshold to improve the contrast and remove errors. The model is based on grey wolf optimization technology which has been developed for feature reduction. Finally, acute lymphoblastic leukemia has been classified into benign and malignant using K-nearest neighbors (KNN), support vector machine (SVM), naïve Bayes (NB), and random forest (RF) classifiers. The best accuracy, sensitivity, and specificity of this model were 99.69%, 99.5%, and 99%, respectively, after using the grey wolf optimization algorithm in feature selection. To ensure the effectiveness of the proposed model, comparative results with other classification techniques have been included.https://www.mdpi.com/2076-3417/12/21/10760grey wolf optimizationacute lymphoblastic leukemiasupport vector machinerandom forestnaïve bayesK nearest neighbor |
| spellingShingle | Nada M. Sallam Ahmed I. Saleh H. Arafat Ali Mohamed M. Abdelsalam An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques Applied Sciences grey wolf optimization acute lymphoblastic leukemia support vector machine random forest naïve bayes K nearest neighbor |
| title | An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques |
| title_full | An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques |
| title_fullStr | An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques |
| title_full_unstemmed | An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques |
| title_short | An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques |
| title_sort | efficient strategy for blood diseases detection based on grey wolf optimization as feature selection and machine learning techniques |
| topic | grey wolf optimization acute lymphoblastic leukemia support vector machine random forest naïve bayes K nearest neighbor |
| url | https://www.mdpi.com/2076-3417/12/21/10760 |
| work_keys_str_mv | AT nadamsallam anefficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques AT ahmedisaleh anefficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques AT harafatali anefficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques AT mohamedmabdelsalam anefficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques AT nadamsallam efficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques AT ahmedisaleh efficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques AT harafatali efficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques AT mohamedmabdelsalam efficientstrategyforblooddiseasesdetectionbasedongreywolfoptimizationasfeatureselectionandmachinelearningtechniques |