|
Vol.11, No.2, May 2022. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Brain Tumor Segmentation from Magnetic Resonance Image using Optimized Thresholded Difference Algorithm and Rough Set
Dalia Mohammad Toufiq, Ali Makki Sagheer, Hadi Veisi
© 2022 Dalia Mohammad Toufiq, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 11, Issue 2, Pages 631-638, ISSN 2217-8309, DOI: 10.18421/TEM112-17, May 2022.
Received: 16 January 2022. Revised: 24 March 2022.
Abstract:
This research presents an effective method for automatically segmenting brain tumors using the proposed Optimized Thresholded Difference (OTD) and Rough Set Theory (RST). The tumor area is determined using the proposed two-level segmentation algorithm. The first level i.e., an overlay image is created, which is the intensity average of all the pixels of the brain area that were segmented in the initial stage. Then the second level, in which the process of the thresholded difference is applied between the brain area and the overlay image depending on the specified threshold. Features are extracted from the segmented images using the Gray-Level Co-occurrence Matrix (GLCM). To improve performance, an RST is employed with the extracted features. The completely automated methodology is validated using Figshare open dataset.
Keywords –Brain tumor segmentation, OTD, GLCM, RST, ID3. |
|
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |