|
Automated classification of childhood brain tumoursbased on texture feature |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Daisy Das 2. Lipi B. Mahanta 3. Shabnam Ahmed 4. Basanta Kr. Baishya 5. Inamul Haque |
| Title | Automated classification of childhood brain tumoursbased on texture feature |
| Publisher | Research and Development Office, Prince of Songkla University |
| Publication Year | 2562 |
| Journal Title | Songklanakarin Journal of Science and Technology |
| Journal Vol. | 41 |
| Journal No. | 5 |
| Page no. | 1014-1020 |
| Keyword | CNS tumours, medulloblastoma, biopsy, classification, texture feature |
| URL Website | http://rdo.psu.ac.th/sjstweb/index.php |
| ISSN | 0125-3395 |
| Abstract | We propose a framework for automated classification between normal and abnormal biopsy samples of childhood braintumour with emphasis on childhood medulloblastoma, a most common childhood brain tumour, using texture features. Texture isa measure to analyze the variation of intensity of surface of an image and the connection of pixels satisfying a repeated grey levelproperty. The feature set consisted of a total of 172 features belonging to five texture features, GLCM, GRLN, HOG, Tamura andLBP. The performance of each feature set was evaluated both individually and in group, using six different classifiers, LinearDiscriminant, Quadratic Discriminant, Logistic Regression, Support Vector Machine and K-Nearest Neighbour algorithms. Here,feature of tamura, global low order histogram and local second order GLCM outperforms the local texture measure of LBP andGRLN. Using 80 normal and malignant images of 10x magnification we obtained an optimal accuracy of 100% by combining allfive textural features. |
