Detection of Collaterals from Cone-Beam CT Images in Stroke
Collateral vessels play an important role in the restoration of blood flow to the ischemic tissues of stroke patients, and the quality of collateral flow has major impact on reducing treatment delay and increasing the success rate of reperfusion. Due to high spatial resolution and rapid scan time, a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/8099 |
| _version_ | 1797507179808292864 |
|---|---|
| author | Azrina Abd Aziz Lila Iznita Izhar Vijanth Sagayan Asirvadam Tong Boon Tang Azimah Ajam Zaid Omar Sobri Muda |
| author_facet | Azrina Abd Aziz Lila Iznita Izhar Vijanth Sagayan Asirvadam Tong Boon Tang Azimah Ajam Zaid Omar Sobri Muda |
| author_sort | Azrina Abd Aziz |
| collection | DOAJ |
| description | Collateral vessels play an important role in the restoration of blood flow to the ischemic tissues of stroke patients, and the quality of collateral flow has major impact on reducing treatment delay and increasing the success rate of reperfusion. Due to high spatial resolution and rapid scan time, advance imaging using the cone-beam computed tomography (CBCT) is gaining more attention over the conventional angiography in acute stroke diagnosis. Detecting collateral vessels from CBCT images is a challenging task due to the presence of noises and artifacts, small-size and non-uniform structure of vessels. This paper presents a technique to objectively identify collateral vessels from non-collateral vessels. In our technique, several filters are used on the CBCT images of stroke patients to remove noises and artifacts, then multiscale top-hat transformation method is implemented on the pre-processed images to further enhance the vessels. Next, we applied three types of feature extraction methods which are gray level co-occurrence matrix (GLCM), moment invariant, and shape to explore which feature is best to classify the collateral vessels. These features are then used by the support vector machine (SVM), random forest, decision tree, and K-nearest neighbors (KNN) classifiers to classify vessels. Finally, the performance of these classifiers is evaluated in terms of accuracy, sensitivity, precision, recall, F-Measure, and area under the receiver operating characteristics curve. Our results show that all classifiers achieve promising classification accuracy above 90% and able to detect the collateral and non-collateral vessels from images. |
| first_indexed | 2024-03-10T04:44:57Z |
| format | Article |
| id | doaj.art-e7952ec6a1cc41b5931c9f2ab6752da2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:44:57Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e7952ec6a1cc41b5931c9f2ab6752da22023-11-23T03:03:57ZengMDPI AGSensors1424-82202021-12-012123809910.3390/s21238099Detection of Collaterals from Cone-Beam CT Images in StrokeAzrina Abd Aziz0Lila Iznita Izhar1Vijanth Sagayan Asirvadam2Tong Boon Tang3Azimah Ajam4Zaid Omar5Sobri Muda6Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS (UTP), Seri Iskandar 32610, MalaysiaDepartment of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS (UTP), Seri Iskandar 32610, MalaysiaDepartment of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS (UTP), Seri Iskandar 32610, MalaysiaCentre for Intelligent Signal and Imaging Research (CISIR), Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS (UTP), Seri Iskandar 32610, MalaysiaDepartment of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS (UTP), Seri Iskandar 32610, MalaysiaSchool of Electrical Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, MalaysiaDepartment of Radiology, Faculty of Medicine and Health Sciences, Hospital Pengajar Universiti Putra Malaysia, Serdang 43400, MalaysiaCollateral vessels play an important role in the restoration of blood flow to the ischemic tissues of stroke patients, and the quality of collateral flow has major impact on reducing treatment delay and increasing the success rate of reperfusion. Due to high spatial resolution and rapid scan time, advance imaging using the cone-beam computed tomography (CBCT) is gaining more attention over the conventional angiography in acute stroke diagnosis. Detecting collateral vessels from CBCT images is a challenging task due to the presence of noises and artifacts, small-size and non-uniform structure of vessels. This paper presents a technique to objectively identify collateral vessels from non-collateral vessels. In our technique, several filters are used on the CBCT images of stroke patients to remove noises and artifacts, then multiscale top-hat transformation method is implemented on the pre-processed images to further enhance the vessels. Next, we applied three types of feature extraction methods which are gray level co-occurrence matrix (GLCM), moment invariant, and shape to explore which feature is best to classify the collateral vessels. These features are then used by the support vector machine (SVM), random forest, decision tree, and K-nearest neighbors (KNN) classifiers to classify vessels. Finally, the performance of these classifiers is evaluated in terms of accuracy, sensitivity, precision, recall, F-Measure, and area under the receiver operating characteristics curve. Our results show that all classifiers achieve promising classification accuracy above 90% and able to detect the collateral and non-collateral vessels from images.https://www.mdpi.com/1424-8220/21/23/8099collateralscone-beam computed tomography (CBCT)strokesupport vector machine (SVM)K-nearest neighbors (KNN) |
| spellingShingle | Azrina Abd Aziz Lila Iznita Izhar Vijanth Sagayan Asirvadam Tong Boon Tang Azimah Ajam Zaid Omar Sobri Muda Detection of Collaterals from Cone-Beam CT Images in Stroke Sensors collaterals cone-beam computed tomography (CBCT) stroke support vector machine (SVM) K-nearest neighbors (KNN) |
| title | Detection of Collaterals from Cone-Beam CT Images in Stroke |
| title_full | Detection of Collaterals from Cone-Beam CT Images in Stroke |
| title_fullStr | Detection of Collaterals from Cone-Beam CT Images in Stroke |
| title_full_unstemmed | Detection of Collaterals from Cone-Beam CT Images in Stroke |
| title_short | Detection of Collaterals from Cone-Beam CT Images in Stroke |
| title_sort | detection of collaterals from cone beam ct images in stroke |
| topic | collaterals cone-beam computed tomography (CBCT) stroke support vector machine (SVM) K-nearest neighbors (KNN) |
| url | https://www.mdpi.com/1424-8220/21/23/8099 |
| work_keys_str_mv | AT azrinaabdaziz detectionofcollateralsfromconebeamctimagesinstroke AT lilaiznitaizhar detectionofcollateralsfromconebeamctimagesinstroke AT vijanthsagayanasirvadam detectionofcollateralsfromconebeamctimagesinstroke AT tongboontang detectionofcollateralsfromconebeamctimagesinstroke AT azimahajam detectionofcollateralsfromconebeamctimagesinstroke AT zaidomar detectionofcollateralsfromconebeamctimagesinstroke AT sobrimuda detectionofcollateralsfromconebeamctimagesinstroke |