- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
Shape Model Construction for MRI Brain Tumor Detection | ||
| Journal of College of Education | ||
| Article 1, Volume 0, Issue 5, 2017, Pages 229-238 | ||
| Author | ||
| Amal AbbasKhadhim | ||
| Abstract | ||
| In this paper, a construction of shape model for interest region is submitted to achieve an efficient and automatic detection for brain tumorlocationin MRI images. The proposed approach composed of two major modes; training mode and testing mode. In the training mode, a manual detection of interest regions is implemented on theinfected training image in order to extract diagnostic region only. Then, an extraction of histogram bins, texture and statistical features is carried out to generate feature vector for each infected region. Finally, the raw feature vectors are passes to linear discriminate analysis method for the purpose of generating features space of the infected regions. In the testing mode, the texture and statistical features are extracted to perform the detection of region of interest. Subsequently, determining the infected regions in MRI image based on linear discriminant analysis method. Thus, the final decision of tumor diagnosis is given based on the comparison process with the ground truth of the brain tumors to detect the tumor brain through Hausdorff distance measure. The experimental results have been illustrated the effectiveness of the proposed detection approach. | ||
| Keywords | ||
| tumor brain detection; LDA; shape model | ||
|
Statistics Article View: 41 PDF Download: 24 |
||