Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random Forest
Brain hemorrhage is a severe threat to human life, and its timely and correct diagnosis and treatment are of great importance. Multiple types of brain hemorrhage are distinguished depending on the location and character of bleeding. The main division covers five subtypes: subdural, epidural, intrave...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/21/7577 |
| _version_ | 1797549655469326336 |
|---|---|
| author | Agata Sage Pawel Badura |
| author_facet | Agata Sage Pawel Badura |
| author_sort | Agata Sage |
| collection | DOAJ |
| description | Brain hemorrhage is a severe threat to human life, and its timely and correct diagnosis and treatment are of great importance. Multiple types of brain hemorrhage are distinguished depending on the location and character of bleeding. The main division covers five subtypes: subdural, epidural, intraventricular, intraparenchymal, and subarachnoid hemorrhage. This paper presents an approach to detect these intracranial hemorrhage types in computed tomography images of the head. The model trained for each hemorrhage subtype is based on a double-branch convolutional neural network of ResNet-50 architecture. It extracts features from two chromatic representations of the input data: a concatenation of the image normalized in different intensity windows and a stack of three consecutive slices creating a 3D spatial context. The joint feature vector is passed to the classifier to produce the final decision. We tested two tools: the support vector machine and the random forest. The experiments involved 372,556 images from 11,454 CT series of 9997 patients, with each image annotated with labels related to the hemorrhage subtypes. We validated deep networks from both branches of our framework and the model with either of two classifiers under consideration. The obtained results justify the use of a combination of double-source features with the random forest classifier. The system outperforms state-of-the-art methods in terms of F1 score. The highest detection accuracy was obtained in intraventricular (96.7%) and intraparenchymal hemorrhages (93.3%). |
| first_indexed | 2024-03-10T15:17:33Z |
| format | Article |
| id | doaj.art-1e4872b41f664576b4a5f4257fe1d085 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:17:33Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1e4872b41f664576b4a5f4257fe1d0852023-11-20T18:45:47ZengMDPI AGApplied Sciences2076-34172020-10-011021757710.3390/app10217577Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random ForestAgata Sage0Pawel Badura1Faculty of Biomedical Engineering, Silesian University of Technology, Roosevelta 40, 41-800 Zabrze, PolandFaculty of Biomedical Engineering, Silesian University of Technology, Roosevelta 40, 41-800 Zabrze, PolandBrain hemorrhage is a severe threat to human life, and its timely and correct diagnosis and treatment are of great importance. Multiple types of brain hemorrhage are distinguished depending on the location and character of bleeding. The main division covers five subtypes: subdural, epidural, intraventricular, intraparenchymal, and subarachnoid hemorrhage. This paper presents an approach to detect these intracranial hemorrhage types in computed tomography images of the head. The model trained for each hemorrhage subtype is based on a double-branch convolutional neural network of ResNet-50 architecture. It extracts features from two chromatic representations of the input data: a concatenation of the image normalized in different intensity windows and a stack of three consecutive slices creating a 3D spatial context. The joint feature vector is passed to the classifier to produce the final decision. We tested two tools: the support vector machine and the random forest. The experiments involved 372,556 images from 11,454 CT series of 9997 patients, with each image annotated with labels related to the hemorrhage subtypes. We validated deep networks from both branches of our framework and the model with either of two classifiers under consideration. The obtained results justify the use of a combination of double-source features with the random forest classifier. The system outperforms state-of-the-art methods in terms of F1 score. The highest detection accuracy was obtained in intraventricular (96.7%) and intraparenchymal hemorrhages (93.3%).https://www.mdpi.com/2076-3417/10/21/7577intracranial hemorrhagecomputer-aided diagnosiscomputed tomographydeep learningrandom forest |
| spellingShingle | Agata Sage Pawel Badura Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random Forest Applied Sciences intracranial hemorrhage computer-aided diagnosis computed tomography deep learning random forest |
| title | Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random Forest |
| title_full | Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random Forest |
| title_fullStr | Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random Forest |
| title_full_unstemmed | Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random Forest |
| title_short | Intracranial Hemorrhage Detection in Head CT Using Double-Branch Convolutional Neural Network, Support Vector Machine, and Random Forest |
| title_sort | intracranial hemorrhage detection in head ct using double branch convolutional neural network support vector machine and random forest |
| topic | intracranial hemorrhage computer-aided diagnosis computed tomography deep learning random forest |
| url | https://www.mdpi.com/2076-3417/10/21/7577 |
| work_keys_str_mv | AT agatasage intracranialhemorrhagedetectioninheadctusingdoublebranchconvolutionalneuralnetworksupportvectormachineandrandomforest AT pawelbadura intracranialhemorrhagedetectioninheadctusingdoublebranchconvolutionalneuralnetworksupportvectormachineandrandomforest |