No Detail Found!

Morphological and marker-based watershed method for detection and segmentation of brain tumor regions

Author(s)
Faisal Hafeez Faculty of Computing and Information Technology, Deparmtent of Computer Science, University of Punjab,Lahore,Pakistan
Zobia Suhail Faculty of Computing and Information Technology, Deparmtent of Computer Science, University of Punjab,Lahore,Pakistan
Reyer Zwiggelaar Department of Computer Science, Aberyswyth University,,UK
Abstract
Brain tumor detection is a complex problem in medical image analysis. Brain tumor is an abnormal growth of brain cells that is usually detected by Magnetic Resonance Imaging (MRI) brain images. In this paper, we propose an efficient algorithm for detecting brain tumors using MRI images without skull removal. After applying basic image preprocessing techniques, morphological operations are used to detect the boundaries and sharpen the regions. Subsequently, segmentation is performed using Otsu thresholding and then a marker watershed technique is used for final brain tumor segmentation. The proposed approach is evaluated on 3000 images from Brain Tumor Detection 2020 dataset (Br35H). Experiments showed that with appropriate preprocessing and appropriate thresholding, good segmentation results can be achieved to segment brain tumor.
Publication Details
Page(s) 108-113
DOI 10.24949/njes.v16i2.759
Published Journal: NUST Journal of Engineering Sciences, Volume: 16, Issue: 2, Year: 2023

Request the full text from PASTIC

Keywords
image segmentation, Medical Image Analysis, BRATS Dataset, Morphological operation, Marker-Based Watershed Method, Otsu Threshold, Brain Tumor Detection
More from NUST Journal of Engineering Sciences
0

Citations

0

Downloads

30

Views

Copyright ©  PASTIC National Center, Islamabad www.pastic.gov.pk