Abstract
In this paper, we propose a minimum spanning tree-based method for segmenting brain tumors. The proposed method performs interactive segmentation based on the minimum spanning tree without tuning parameters. The steps involve preprocessing, making a graph, constructing a minimum spanning tree, and a newly implemented way of interactively segmenting the region of interest. In the preprocessing step, a Gaussian filter is applied to 2D images to remove the noise. Then, the pixel neighbor graph is weighted by intensity differences and the corresponding minimum spanning tree is constructed. The image is loaded in an interactive window for segmenting the tumor. The region of interest and the background are selected by clicking to split the minimum spanning tree into two trees. One of these trees represents the region of interest and the other represents the background. Finally, the segmentation given by the two trees is visualized. The proposed method was tested by segmenting two different 2D brain T1-weighted magnetic resonance image data sets. The comparison between our results and the gold standard segmentation confirmed the validity of the minimum spanning tree approach. The proposed method is simple to implement and the results indicate that it is accurate and efficient.
Highlights
A brain tumor is a collection of abnormal cells in the brain: they may be malignant or benign and can be categorized as primary or secondary
Images from the first data set were used to evaluate the minimum spanning tree (MST) approach when segmenting region of interest (ROI) loosely connected to the background (Figure 3)
In the instances/cases where the ROIs are loosely connected to the background, a sigma value of 0.1 is used in the preprocessing step to obtain the segmentation
Summary
A brain tumor is a collection of abnormal cells in the brain: they may be malignant (cancerous) or benign (noncancerous) and can be categorized as primary or secondary. Primary brain tumors originate in the brain and are either glial or non-glial. Non-glial tumors may originate from any other tissue in the brain, such as meninges, neurons, blood vessels, and glands. Primary tumors can be malignant (cancerous) or benign. Secondary brain tumors develop in another part of the body and metastasize to the brain. Segmenting brain tumors using automatic techniques is challenging because of factors that cause complexity during segmentation. These factors include the location in the brain, irregular shapes, different sizes, types of tumors, blurred boundaries, and noise
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
