Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage
<p><em>Early diagnosis of intracranial hemorrhage significantly reduces mortality. Hemorrhage is diagnosed by using various imaging methods and the most time-efficient one among them is computed tomography (CT). However, it is clear that accurate CT scans requires time, diligence, and ex...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EduSoft publishing
2021-12-01
|
| Series: | Brain: Broad Research in Artificial Intelligence and Neuroscience |
| Subjects: | |
| Online Access: | https://www.edusoft.ro/brain/index.php/brain/article/view/1185 |
| _version_ | 1797335683004628992 |
|---|---|
| author | Sezin BARIN Murat SARIBAŞ Beyza Gülizar ÇİLTAŞ Gür Emre GÜRAKSIN Utku KÖSE |
| author_facet | Sezin BARIN Murat SARIBAŞ Beyza Gülizar ÇİLTAŞ Gür Emre GÜRAKSIN Utku KÖSE |
| author_sort | Sezin BARIN |
| collection | DOAJ |
| description | <p><em>Early diagnosis of intracranial hemorrhage significantly reduces mortality. Hemorrhage is diagnosed by using various imaging methods and the most time-efficient one among them is computed tomography (CT). However, it is clear that accurate CT scans requires time, diligence, and experience. Computer-aided design methods are vital for the treatment because they facilitate early diagnosis of intracranial hemorrhage. At this point, deep learning can provide effective outcomes through an automated diagnosis way. However, as different from the known solutions, diagnosis of five different hemorrhage subtypes is a critical problem to be solved.This study focused on deep learning methods and employed cranial computed tomography scans in order to detect intracranial hemorrhage. The diagnosis approach in the study aimed to detect five subtypes of hemorrhage. In detail, EfficientNet-B3 and ResNet-Inception-V2 architectures were used for diagnosis purposes. Eventually, the study also proposed a two-architecture hybrid method for the diagnosis purpose. The obtained findings by the hybrid method were evaluated in terms of a comparative perspective.Results showed that the newly designed hybrid method was quite effective in terms of increasing classification rates of detecting intracranial hemorrhage according to the subtypes. Briefly, an accuracy of 98.5%, which is higher than those of the EfficientNet-B3 and the Inception-ResNet-V2, were obtained thanks to the developed hybrid method.</em></p> |
| first_indexed | 2024-03-08T08:41:53Z |
| format | Article |
| id | doaj.art-f87b82292ebd46b093f60ab63f1be8be |
| institution | Directory Open Access Journal |
| issn | 2067-3957 |
| language | English |
| last_indexed | 2024-03-08T08:41:53Z |
| publishDate | 2021-12-01 |
| publisher | EduSoft publishing |
| record_format | Article |
| series | Brain: Broad Research in Artificial Intelligence and Neuroscience |
| spelling | doaj.art-f87b82292ebd46b093f60ab63f1be8be2024-02-01T18:00:41ZengEduSoft publishingBrain: Broad Research in Artificial Intelligence and Neuroscience2067-39572021-12-011240127991Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial HemorrhageSezin BARIN0Murat SARIBAŞ1Beyza Gülizar ÇİLTAŞ2Gür Emre GÜRAKSIN3Utku KÖSE4Afyon Kocatepe University, Department of Biomedical Engineering, Afyonkarahisar, TurkeyAfyon Kocatepe University, Department of Biomedical Engineering, Afyonkarahisar, TurkeyAfyon Kocatepe University, Department of Biomedical Engineering, Afyonkarahisar, TurkeyAfyon Kocatepe University, Department of Computer Engineering, Afyonkarahisar, TurkeySuleyman Demirel University, Department of Computer Engineering, Isparta, Turkey<p><em>Early diagnosis of intracranial hemorrhage significantly reduces mortality. Hemorrhage is diagnosed by using various imaging methods and the most time-efficient one among them is computed tomography (CT). However, it is clear that accurate CT scans requires time, diligence, and experience. Computer-aided design methods are vital for the treatment because they facilitate early diagnosis of intracranial hemorrhage. At this point, deep learning can provide effective outcomes through an automated diagnosis way. However, as different from the known solutions, diagnosis of five different hemorrhage subtypes is a critical problem to be solved.This study focused on deep learning methods and employed cranial computed tomography scans in order to detect intracranial hemorrhage. The diagnosis approach in the study aimed to detect five subtypes of hemorrhage. In detail, EfficientNet-B3 and ResNet-Inception-V2 architectures were used for diagnosis purposes. Eventually, the study also proposed a two-architecture hybrid method for the diagnosis purpose. The obtained findings by the hybrid method were evaluated in terms of a comparative perspective.Results showed that the newly designed hybrid method was quite effective in terms of increasing classification rates of detecting intracranial hemorrhage according to the subtypes. Briefly, an accuracy of 98.5%, which is higher than those of the EfficientNet-B3 and the Inception-ResNet-V2, were obtained thanks to the developed hybrid method.</em></p>https://www.edusoft.ro/brain/index.php/brain/article/view/1185deep convolutional neural networkintracranial hemorrhagecomputer tomographyinception-resnet-v2efficientnet-b3 |
| spellingShingle | Sezin BARIN Murat SARIBAŞ Beyza Gülizar ÇİLTAŞ Gür Emre GÜRAKSIN Utku KÖSE Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage Brain: Broad Research in Artificial Intelligence and Neuroscience deep convolutional neural network intracranial hemorrhage computer tomography inception-resnet-v2 efficientnet-b3 |
| title | Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage |
| title_full | Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage |
| title_fullStr | Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage |
| title_full_unstemmed | Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage |
| title_short | Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage |
| title_sort | hybrid convolutional neural network based diagnosis system for intracranial hemorrhage |
| topic | deep convolutional neural network intracranial hemorrhage computer tomography inception-resnet-v2 efficientnet-b3 |
| url | https://www.edusoft.ro/brain/index.php/brain/article/view/1185 |
| work_keys_str_mv | AT sezinbarin hybridconvolutionalneuralnetworkbaseddiagnosissystemforintracranialhemorrhage AT muratsaribas hybridconvolutionalneuralnetworkbaseddiagnosissystemforintracranialhemorrhage AT beyzagulizarciltas hybridconvolutionalneuralnetworkbaseddiagnosissystemforintracranialhemorrhage AT guremreguraksin hybridconvolutionalneuralnetworkbaseddiagnosissystemforintracranialhemorrhage AT utkukose hybridconvolutionalneuralnetworkbaseddiagnosissystemforintracranialhemorrhage |