ROI Segmentation from Brain MR Images with a Fast Multilevel Thresholding
A novel region of interest (ROI) segmentation for detection of Glioblastoma multiforme (GBM) tumor in magnetic resonance (MR) images of the brain is proposed using a two-stage thresholding method. We have defined multiple intervals for multilevel threshol
- PDF / 557,386 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 59 Downloads / 240 Views
Abstract A novel region of interest (ROI) segmentation for detection of Glioblastoma multiforme (GBM) tumor in magnetic resonance (MR) images of the brain is proposed using a two-stage thresholding method. We have defined multiple intervals for multilevel thresholding using a novel meta-heuristic optimization technique called Discrete Curve Evolution. In each of these intervals, a threshold is selected by bi-level Otsu’s method. Then the ROI is extracted from only a single seed initialization, on the ROI, by the user. The proposed segmentation technique is more accurate as compared to the existing methods. Also the time complexity of our method is very low. The experimental evaluation is provided on contrast-enhanced T1-weighted MRI slices of three patients, having the corresponding ground truth of the tumor regions. The performance measure, based on Jaccard and Dice indices, of the segmented ROI demonstrated higher accuracy than existing methods. Keywords Segmentation ⋅ Discrete curve evolution ⋅ Delineation ⋅ MRI ⋅ GBM ⋅ Thresholding
1 Introduction Image segmentation is ubiquitous in any image analysis system. In the medical image analysis, we need to perform segmentation accurately and efficiently since errors occurring in this step are usually carried over to subsequent processing phases. Accurate segmentation facilitates computerized visualization, feature extraction, and S. Banerjee (✉) ⋅ S. Mitra ⋅ B. Uma Shankar Machine Intelligence Unit, Indian Statistical Institute, 203 B. T Road, Kolkata 700108, India e-mail: [email protected] S. Mitra e-mail: [email protected] B. Uma Shankar e-mail: [email protected] © Springer Science+Business Media Singapore 2017 B. Raman et al. (eds.), Proceedings of International Conference on Computer Vision and Image Processing, Advances in Intelligent Systems and Computing 459, DOI 10.1007/978-981-10-2104-6_23
249
250
S. Banerjee et al.
analysis of the region of interest (ROI). Image segmentation entails pixel wise labeling of the image regions according to similarity in terms of visual characteristics. The segmentation of the ROI is an important step in computer-aided detection and diagnosis (CAD) systems assisting medical practitioners and radiologists in the process of interpreting medical images [14, 20]. Detection of tumors, anomalies, organs of specific interest or any other features in a medical image requires considerable amount of experience and knowledge about visual characteristics of the anatomical features. Image segmentation and detection of such different region of interests (ROIs) is typically performed manually by expert radiologists as part of the whole treatment process. The increasing amount of available data and the complexity of the features of interest made us think differently. It is almost necessary and becoming essential to develop automated delineation system to assist and advance image understanding to allow for reproducible results which are quantifiable for further analysis and inference [3]. Besides this, the existence of inter and intra observe
Data Loading...
