封面圖片

Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency

MRI which stands for Magnetic Resonance Imaging is commonly used to capture images of internal body organs, functionality and structure. Manual analysis is usually performed by Radiologists on a large set of MR images in order to detect brain tumor. Aims: This research aims to improve automated bra...

全面介紹

Saved in:
書目詳細資料
Main Authors: Ghazanfar, Latif, Dayang Nur Fatimah, Binti Awg Iskandar, Jaafar, Alghazo, Arfan, Jaffar
格式: Article
語言:English
出版: Bentham Science Publishers 2018
主題:
R Medicine (General)
在線閱讀:http://ir.unimas.my/id/eprint/21721/1/Improving%20Brain%20MR%20Image%20Classification%20for%20Tumor%20Segmentation%20using%20Phase%20Congruency%20%20%28abstract%29.pdf
http://ir.unimas.my/id/eprint/21721/
http://www.eurekaselect.com/node/160931/article/improving-brain-mr-image-classification-for-tumor-segmentation-using-phase-congruency
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
id my.unimas.ir.21721
record_format eprints
spelling my.unimas.ir.217212022-09-29T02:40:08Z http://ir.unimas.my/id/eprint/21721/ Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency Ghazanfar, Latif Dayang Nur Fatimah, Binti Awg Iskandar Jaafar, Alghazo Arfan, Jaffar R Medicine (General) MRI which stands for Magnetic Resonance Imaging is commonly used to capture images of internal body organs, functionality and structure. Manual analysis is usually performed by Radiologists on a large set of MR images in order to detect brain tumor. Aims: This research aims to improve automated brain MR image classification and tumor segmentation using phase congruency. Methods: The skull part is removed from brain MR image by applying converging square algorithm and phase congruency based edge detection method. Features are then extracted from the segmented brain portion using discrete wavelet transforms. In order to minimize the extracted feature set, we applied the principal Component Analysis algorithm. The MR images are classified into tumorous and non-tumorous using Multilayer perceptron and compared with other classifiers such as K-Nearest Neighbor, Naïve Bayes, and Support Vector Machines (SVM) along with discrete cosine and discrete cosine transform features. The tumor is segmented using Fuzzy C-mean and reconstructed tumor 3D model to measure the volume, location and shape accurately. Results & conclusions: Experimental results are obtained by testing the proposed method on a dataset of 19 patients with a total number of 2920 brain MR images. The proposed method achieved an accuracy of 99.43% for classification which is higher as compared to other current studies. Keywords: Brain MRI, phase congruency, segmentation, tumor analysis, feature extraction, tumor classification Bentham Science Publishers 2018 Article PeerReviewed text en http://ir.unimas.my/id/eprint/21721/1/Improving%20Brain%20MR%20Image%20Classification%20for%20Tumor%20Segmentation%20using%20Phase%20Congruency%20%20%28abstract%29.pdf Ghazanfar, Latif and Dayang Nur Fatimah, Binti Awg Iskandar and Jaafar, Alghazo and Arfan, Jaffar (2018) Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency. Current Medical Imaging Reviews, 14. pp. 1-10. ISSN 1875-6603 http://www.eurekaselect.com/node/160931/article/improving-brain-mr-image-classification-for-tumor-segmentation-using-phase-congruency DOI: 10.2174/1573405614666180402150218
institution Universiti Malaysia Sarawak
building Centre for Academic Information Services (CAIS)
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Sarawak
content_source UNIMAS Institutional Repository
url_provider http://ir.unimas.my/
language English
topic R Medicine (General)
spellingShingle R Medicine (General)
Ghazanfar, Latif
Dayang Nur Fatimah, Binti Awg Iskandar
Jaafar, Alghazo
Arfan, Jaffar
Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency
description MRI which stands for Magnetic Resonance Imaging is commonly used to capture images of internal body organs, functionality and structure. Manual analysis is usually performed by Radiologists on a large set of MR images in order to detect brain tumor. Aims: This research aims to improve automated brain MR image classification and tumor segmentation using phase congruency. Methods: The skull part is removed from brain MR image by applying converging square algorithm and phase congruency based edge detection method. Features are then extracted from the segmented brain portion using discrete wavelet transforms. In order to minimize the extracted feature set, we applied the principal Component Analysis algorithm. The MR images are classified into tumorous and non-tumorous using Multilayer perceptron and compared with other classifiers such as K-Nearest Neighbor, Naïve Bayes, and Support Vector Machines (SVM) along with discrete cosine and discrete cosine transform features. The tumor is segmented using Fuzzy C-mean and reconstructed tumor 3D model to measure the volume, location and shape accurately. Results & conclusions: Experimental results are obtained by testing the proposed method on a dataset of 19 patients with a total number of 2920 brain MR images. The proposed method achieved an accuracy of 99.43% for classification which is higher as compared to other current studies. Keywords: Brain MRI, phase congruency, segmentation, tumor analysis, feature extraction, tumor classification
format Article
author Ghazanfar, Latif
Dayang Nur Fatimah, Binti Awg Iskandar
Jaafar, Alghazo
Arfan, Jaffar
author_facet Ghazanfar, Latif
Dayang Nur Fatimah, Binti Awg Iskandar
Jaafar, Alghazo
Arfan, Jaffar
author_sort Ghazanfar, Latif
title Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency
title_short Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency
title_full Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency
title_fullStr Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency
title_full_unstemmed Improving Brain MR Image Classification for Tumor Segmentation using Phase Congruency
title_sort improving brain mr image classification for tumor segmentation using phase congruency
publisher Bentham Science Publishers
publishDate 2018
url http://ir.unimas.my/id/eprint/21721/1/Improving%20Brain%20MR%20Image%20Classification%20for%20Tumor%20Segmentation%20using%20Phase%20Congruency%20%20%28abstract%29.pdf
http://ir.unimas.my/id/eprint/21721/
http://www.eurekaselect.com/node/160931/article/improving-brain-mr-image-classification-for-tumor-segmentation-using-phase-congruency
_version_ 1745566040577802240
score 13.251813

相似書籍