Automated classification of childhood brain tumours based on texture feature
We propose a framework for automated classification between normal and abnormal biopsy samples of childhood brain tumour with emphasis on childhood medulloblastoma, a most common childhood brain tumour, using texture features. Texture is a measure to analyze the variation of intensity of surface o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Prince of Songkla University
2019-10-01
|
| Series: | Songklanakarin Journal of Science and Technology (SJST) |
| Subjects: | |
| Online Access: | https://rdo.psu.ac.th/sjstweb/journal/41-5/8.pdf |
| _version_ | 1811249326863679488 |
|---|---|
| author | Daisy Das Lipi B. Mahanta Shabnam Ahmed Basanta Kr. Baishya Inamul Haque |
| author_facet | Daisy Das Lipi B. Mahanta Shabnam Ahmed Basanta Kr. Baishya Inamul Haque |
| author_sort | Daisy Das |
| collection | DOAJ |
| description | We propose a framework for automated classification between normal and abnormal biopsy samples of childhood brain
tumour with emphasis on childhood medulloblastoma, a most common childhood brain tumour, using texture features. Texture is
a measure to analyze the variation of intensity of surface of an image and the connection of pixels satisfying a repeated grey level
property. The feature set consisted of a total of 172 features belonging to five texture features, GLCM, GRLN, HOG, Tamura and
LBP. The performance of each feature set was evaluated both individually and in group, using six different classifiers, Linear
Discriminant, 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 and
GRLN. Using 80 normal and malignant images of 10x magnification we obtained an optimal accuracy of 100% by combining all
five textural features. |
| first_indexed | 2024-04-12T15:44:34Z |
| format | Article |
| id | doaj.art-a9c549e19d1b4a078157af5cd5212974 |
| institution | Directory Open Access Journal |
| issn | 0125-3395 |
| language | English |
| last_indexed | 2024-04-12T15:44:34Z |
| publishDate | 2019-10-01 |
| publisher | Prince of Songkla University |
| record_format | Article |
| series | Songklanakarin Journal of Science and Technology (SJST) |
| spelling | doaj.art-a9c549e19d1b4a078157af5cd52129742022-12-22T03:26:42ZengPrince of Songkla UniversitySongklanakarin Journal of Science and Technology (SJST)0125-33952019-10-014151014102010.14456/sjst-psu.2019.128Automated classification of childhood brain tumours based on texture featureDaisy Das0Lipi B. Mahanta1Shabnam Ahmed2Basanta Kr. Baishya3Inamul Haque4Central Computational and Numerical Sciences Division, Institute of Advanced Study in Science and Technology, Guwahati, 781035 IndiaCentral Computational and Numerical Sciences Division, Institute of Advanced Study in Science and Technology, Guwahati, 781035 IndiaDepartment of Pathology, Guwahati Neurological Research Centre, Sixmile, Guwahati, 781006 IndiaDepartment of Neurosurgery, Gauhati Medical College, Guwahati, 781032 IndiaDepartment of Neurosurgery, Gauhati Medical College, Guwahati, 781032 IndiaWe propose a framework for automated classification between normal and abnormal biopsy samples of childhood brain tumour with emphasis on childhood medulloblastoma, a most common childhood brain tumour, using texture features. Texture is a measure to analyze the variation of intensity of surface of an image and the connection of pixels satisfying a repeated grey level property. The feature set consisted of a total of 172 features belonging to five texture features, GLCM, GRLN, HOG, Tamura and LBP. The performance of each feature set was evaluated both individually and in group, using six different classifiers, Linear Discriminant, 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 and GRLN. Using 80 normal and malignant images of 10x magnification we obtained an optimal accuracy of 100% by combining all five textural features.https://rdo.psu.ac.th/sjstweb/journal/41-5/8.pdfcns tumoursmedulloblastomabiopsyclassificationtexture feature |
| spellingShingle | Daisy Das Lipi B. Mahanta Shabnam Ahmed Basanta Kr. Baishya Inamul Haque Automated classification of childhood brain tumours based on texture feature Songklanakarin Journal of Science and Technology (SJST) cns tumours medulloblastoma biopsy classification texture feature |
| title | Automated classification of childhood brain tumours based on texture feature |
| title_full | Automated classification of childhood brain tumours based on texture feature |
| title_fullStr | Automated classification of childhood brain tumours based on texture feature |
| title_full_unstemmed | Automated classification of childhood brain tumours based on texture feature |
| title_short | Automated classification of childhood brain tumours based on texture feature |
| title_sort | automated classification of childhood brain tumours based on texture feature |
| topic | cns tumours medulloblastoma biopsy classification texture feature |
| url | https://rdo.psu.ac.th/sjstweb/journal/41-5/8.pdf |
| work_keys_str_mv | AT daisydas automatedclassificationofchildhoodbraintumoursbasedontexturefeature AT lipibmahanta automatedclassificationofchildhoodbraintumoursbasedontexturefeature AT shabnamahmed automatedclassificationofchildhoodbraintumoursbasedontexturefeature AT basantakrbaishya automatedclassificationofchildhoodbraintumoursbasedontexturefeature AT inamulhaque automatedclassificationofchildhoodbraintumoursbasedontexturefeature |