Automated segmentation and detection of T1-weighted magnetic resonance imaging brain images of glioma brain tumor

• Published in: Bulletin of Electrical Engineering and Informatics
• Main Author: Zaihani N.H.I.M.; Roslan R.; Ibrahim Z.; Samah K.A.F.A.
• Format: Article
• Language: English
• Published: Institute of Advanced Engineering and Science 2020
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85083096108&doi=10.11591%2feei.v9i3.2079&partnerID=40&md5=6376fbbcf89173dc9c4f29a2d601605f

There are numerous studies on brain imaging applications. The statistics in Malaysia showed that glioma is one of the most common type disease in brain tumor. Glioma brain tumor is an abnormal growth of glial cells inside the brain tissues which known as cerebral tissues. Radiologist commonly used magnetic resonance imaging (MRI) image sequences to diagnose the brain tumor. However, manual examination of the brain tumor diagnosis by radiologist is difficult and time-consuming task as tumors are occurred in variability of shape and appearance. They will also inject a gadolinium contrast agent to enhance the image modality which will give the side effects to the patients. Therefore, this paper presents an automated segmentation and detection of MRI brain images using Sobel edge detection and mathematical morphology operations. The total of 30 glioma T1-weighted MRI brain images are obtained from brain tumor image segmentation benchmark (BRATS). The results of segmentation and detection are quantitatively evaluated by using Area Overlap which produced the accuracy rate of 80.2% and shows that the presented methods are promising. © 2020, Institute of Advanced Engineering and Science. All rights reserved.