Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection
<b>Objectives</b>: Subarachnoid Hemorrhage (SAH) is a serious neurological emergency case with a higher mortality rate. An automatic SAH detection is needed to expedite and improve identification, aiding timely and efficient treatment pathways. The existence of noisy and dissimilar anato...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/14/21/2417 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173475109076992 |
|---|---|
| author | Jewel Sengupta Robertas Alzbutas Tomas Iešmantas Vytautas Petkus Alina Barkauskienė Vytenis Ratkūnas Saulius Lukoševičius Aidanas Preikšaitis Indre Lapinskienė Mindaugas Šerpytis Edgaras Misiulis Gediminas Skarbalius Robertas Navakas Algis Džiugys |
| author_facet | Jewel Sengupta Robertas Alzbutas Tomas Iešmantas Vytautas Petkus Alina Barkauskienė Vytenis Ratkūnas Saulius Lukoševičius Aidanas Preikšaitis Indre Lapinskienė Mindaugas Šerpytis Edgaras Misiulis Gediminas Skarbalius Robertas Navakas Algis Džiugys |
| author_sort | Jewel Sengupta |
| collection | DOAJ |
| description | <b>Objectives</b>: Subarachnoid Hemorrhage (SAH) is a serious neurological emergency case with a higher mortality rate. An automatic SAH detection is needed to expedite and improve identification, aiding timely and efficient treatment pathways. The existence of noisy and dissimilar anatomical structures in NCCT images, limited availability of labeled SAH data, and ineffective training causes the issues of irrelevant features, overfitting, and vanishing gradient issues that make SAH detection a challenging task. <b>Methods</b>: In this work, the water waves dynamic factor and wandering strategy-based Sand Cat Swarm Optimization, namely DWSCSO, are proposed to ensure optimum feature selection while a Parametric Rectified Linear Unit with a Stacked Convolutional Neural Network, referred to as PRSCNN, is developed for classifying grades of SAH. The DWSCSO and PRSCNN surpass current practices in SAH detection by improving feature selection and classification accuracy. DWSCSO is proposed to ensure optimum feature selection, avoiding local optima issues with higher exploration capacity and avoiding the issue of overfitting in classification. Firstly, in this work, a modified region-growing method was employed on the patient Non-Contrast Computed Tomography (NCCT) images to segment the regions affected by SAH. From the segmented regions, the wide range of patterns and irregularities, fine-grained textures and details, and complex and abstract features were extracted from pre-trained models like GoogleNet, Visual Geometry Group (VGG)-16, and ResNet50. Next, the PRSCNN was developed for classifying grades of SAH which helped to avoid the vanishing gradient issue. <b>Results</b>: The DWSCSO-PRSCNN obtained a maximum accuracy of 99.48%, which is significant compared with other models. The DWSCSO-PRSCNN provides an improved accuracy of 99.62% in CT dataset compared with the DL-ICH and GoogLeNet + (GLCM and LBP), ResNet-50 + (GLCM and LBP), and AlexNet + (GLCM and LBP), which confirms that DWSCSO-PRSCNN effectively reduces false positives and false negatives. <b>Conclusions</b>: the complexity of DWSCSO-PRSCNN was acceptable in this research, for while simpler approaches appeared preferable, they failed to address problems like overfitting and vanishing gradients. Accordingly, the DWSCSO for optimized feature selection and PRSCNN for robust classification were essential for handling these challenges and enhancing the detection in different clinical settings. |
| format | Article |
| id | doaj-art-b3e293bbcfc9454094f7d5ab28df65e7 |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-b3e293bbcfc9454094f7d5ab28df65e72024-11-08T14:34:52ZengMDPI AGDiagnostics2075-44182024-10-011421241710.3390/diagnostics14212417Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature SelectionJewel Sengupta0Robertas Alzbutas1Tomas Iešmantas2Vytautas Petkus3Alina Barkauskienė4Vytenis Ratkūnas5Saulius Lukoševičius6Aidanas Preikšaitis7Indre Lapinskienė8Mindaugas Šerpytis9Edgaras Misiulis10Gediminas Skarbalius11Robertas Navakas12Algis Džiugys13Department of Mathematics and Natural Sciences, Kaunas University of Technology, K. Donelaičio st. 73, 44249 Kaunas, LithuaniaDepartment of Mathematics and Natural Sciences, Kaunas University of Technology, K. Donelaičio st. 73, 44249 Kaunas, LithuaniaDepartment of Mathematics and Natural Sciences, Kaunas University of Technology, K. Donelaičio st. 73, 44249 Kaunas, LithuaniaHealth Telematics Science Institute, Kaunas University of Technology, K. Donelaičio st. 73, 44249 Kaunas, LithuaniaCenter for Radiology and Nuclear Medicine, Vilnius University Hospital Santaros Klinikos, Santariskiu st. 2, 08661 Vilnius, LithuaniaDepartment of Radiology, Lithuanian University of Health Sciences, Eiveniu st. 2, 50009 Kaunas, LithuaniaDepartment of Radiology, Lithuanian University of Health Sciences, Eiveniu st. 2, 50009 Kaunas, LithuaniaClinic of Neurology and Neurosurgery, Faculty of Medicine, Vilnius University, M. K. Ciurlionio st. 21, 03101 Vilnius, LithuaniaClinic of Anaesthesiology and Intensive Care, Faculty of Medicine, Vilnius University, M. K. Ciurlionio st. 21, 03101 Vilnius, LithuaniaClinic of Anaesthesiology and Intensive Care, Faculty of Medicine, Vilnius University, M. K. Ciurlionio st. 21, 03101 Vilnius, LithuaniaLaboratory of Heat-Equipment Research and Testing, Lithuanian Energy Institute, Breslaujos st. 3, 44403 Kaunas, LithuaniaLaboratory of Heat-Equipment Research and Testing, Lithuanian Energy Institute, Breslaujos st. 3, 44403 Kaunas, LithuaniaLaboratory of Heat-Equipment Research and Testing, Lithuanian Energy Institute, Breslaujos st. 3, 44403 Kaunas, LithuaniaLaboratory of Heat-Equipment Research and Testing, Lithuanian Energy Institute, Breslaujos st. 3, 44403 Kaunas, Lithuania<b>Objectives</b>: Subarachnoid Hemorrhage (SAH) is a serious neurological emergency case with a higher mortality rate. An automatic SAH detection is needed to expedite and improve identification, aiding timely and efficient treatment pathways. The existence of noisy and dissimilar anatomical structures in NCCT images, limited availability of labeled SAH data, and ineffective training causes the issues of irrelevant features, overfitting, and vanishing gradient issues that make SAH detection a challenging task. <b>Methods</b>: In this work, the water waves dynamic factor and wandering strategy-based Sand Cat Swarm Optimization, namely DWSCSO, are proposed to ensure optimum feature selection while a Parametric Rectified Linear Unit with a Stacked Convolutional Neural Network, referred to as PRSCNN, is developed for classifying grades of SAH. The DWSCSO and PRSCNN surpass current practices in SAH detection by improving feature selection and classification accuracy. DWSCSO is proposed to ensure optimum feature selection, avoiding local optima issues with higher exploration capacity and avoiding the issue of overfitting in classification. Firstly, in this work, a modified region-growing method was employed on the patient Non-Contrast Computed Tomography (NCCT) images to segment the regions affected by SAH. From the segmented regions, the wide range of patterns and irregularities, fine-grained textures and details, and complex and abstract features were extracted from pre-trained models like GoogleNet, Visual Geometry Group (VGG)-16, and ResNet50. Next, the PRSCNN was developed for classifying grades of SAH which helped to avoid the vanishing gradient issue. <b>Results</b>: The DWSCSO-PRSCNN obtained a maximum accuracy of 99.48%, which is significant compared with other models. The DWSCSO-PRSCNN provides an improved accuracy of 99.62% in CT dataset compared with the DL-ICH and GoogLeNet + (GLCM and LBP), ResNet-50 + (GLCM and LBP), and AlexNet + (GLCM and LBP), which confirms that DWSCSO-PRSCNN effectively reduces false positives and false negatives. <b>Conclusions</b>: the complexity of DWSCSO-PRSCNN was acceptable in this research, for while simpler approaches appeared preferable, they failed to address problems like overfitting and vanishing gradients. Accordingly, the DWSCSO for optimized feature selection and PRSCNN for robust classification were essential for handling these challenges and enhancing the detection in different clinical settings.https://www.mdpi.com/2075-4418/14/21/2417feature selectionparametric rectified linear unitregion-growing methodsand cat swarm optimization algorithmstacked convolutional neural networksubarachnoid hemorrhage detection |
| spellingShingle | Jewel Sengupta Robertas Alzbutas Tomas Iešmantas Vytautas Petkus Alina Barkauskienė Vytenis Ratkūnas Saulius Lukoševičius Aidanas Preikšaitis Indre Lapinskienė Mindaugas Šerpytis Edgaras Misiulis Gediminas Skarbalius Robertas Navakas Algis Džiugys Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection Diagnostics feature selection parametric rectified linear unit region-growing method sand cat swarm optimization algorithm stacked convolutional neural network subarachnoid hemorrhage detection |
| title | Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection |
| title_full | Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection |
| title_fullStr | Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection |
| title_full_unstemmed | Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection |
| title_short | Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection |
| title_sort | detection of subarachnoid hemorrhage using cnn with dynamic factor and wandering strategy based feature selection |
| topic | feature selection parametric rectified linear unit region-growing method sand cat swarm optimization algorithm stacked convolutional neural network subarachnoid hemorrhage detection |
| url | https://www.mdpi.com/2075-4418/14/21/2417 |
| work_keys_str_mv | AT jewelsengupta detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT robertasalzbutas detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT tomasiesmantas detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT vytautaspetkus detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT alinabarkauskiene detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT vytenisratkunas detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT sauliuslukosevicius detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT aidanaspreiksaitis detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT indrelapinskiene detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT mindaugasserpytis detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT edgarasmisiulis detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT gediminasskarbalius detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT robertasnavakas detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection AT algisdziugys detectionofsubarachnoidhemorrhageusingcnnwithdynamicfactorandwanderingstrategybasedfeatureselection |