Two-step verification of brain tumor segmentation using watershed-matching algorithm

• Published in: Brain informatics Vol. 5; no. 2; pp. 8 - 11
• Main Authors: Hasan, S. M. Kamrul, Ahmad, Mohiudding
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 14.08.2018; Springer; Springer Nature B.V; SpringerOpen
• Subjects: Algorithms; Applied research; Artificial Intelligence; Brain; Brain cancer; Brain tumor segmentation; Brain tumors; Cognitive Psychology; Computation by Abstract Devices; Computer Science; Diagnosis; Diagnostic errors; Diagnostic imaging; Error detection; Ground truth; Health Informatics; Image detection; Image segmentation; Magnetic resonance imaging; Matching; Median filter; Medical imaging; Medical research; Methods; Neurosciences; Prevention; Review; SIFT algorithm; Soft tissues; Status checking; Topology; Tumors; SIFT algorithm; Magnetic resonance imaging; Watershed-matching algorithm; Brain tumor segmentation; Status checking; Topology; Median filter
• ISSN: 2198-4018; 2198-4026; 2198-4026
• DOI: 10.1186/s40708-018-0086-x

Though the modern medical imaging research is advancing at a booming rate, it is still a very challenging task to detect brain tumor perfectly. Medical imaging unlike other imaging system has highest penalty for a minimal error. So, the detection of tumor should be accurate to minimize the error. Past researchers used biopsy to detect the tumor tissue from the other soft tissues in the brain which is time-consuming and may have errors. We outlined a two-stage verification-based tumor segmentation that makes the detection more accurate. We segmented the tumor area from the MR image and then used another algorithm to match the segmented portion with the ground truth image. We named this new algorithm as watershed-matching algorithm. The most promising part of our model is the status checking of the tumor by finding the area of the tumor. Our proposed model works better than other state-of-the art works on BRATS 2017 dataset.