Comparative Study of K-means, Gaussian Mixture Model, Fuzzy C-means algorithms for Brain Tumor Segmentation
- U. Baid, S. Talbar, S. Talbar
- Corresponding Author
- U. Baid
Available Online December 2016.
- https://doi.org/10.2991/iccasp-16.2017.85How to use a DOI?
- Brain Tumor Segmentation · K-means clustering · Gaussian Mixture Model · Fuzzy C-means clustering
- Magnetic Resonance Imaging (MRI) is one of the widely used imaging modality for visualizing and assessing the brain anatomy and its functions in non-invasive manner. The most challenging task in analysis of brain MRI images is image segmentation. Automatic and accurate detection of brain tumor is one of the major areas of research in medical image processing. Accurate segmentation of brain tumor helps radiologists for precise treatment planning. In this paper results of one hard clustering algorithm i.e. K-means clustering and two soft clustering algorithm, Gaussian Mixture Model (GMM) and Fuzzy C-means (FCM) clustering are compared. These algorithms are tested on BRATS 2012 training database of High Grade and Low Grade Glioma tumors. Various evaluation parameters like Dice index, Jaccard index, Sensitivity, Specificity are calculated for all the algorithms and comparative analysis is carried out. Experimental results state that Fuzzy C-means clustering outperforms K-means and Gaussian Mixture Model algorithm for brain tumor segmentation problem.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - U. Baid AU - S. Talbar AU - S. Talbar PY - 2016/12 DA - 2016/12 TI - Comparative Study of K-means, Gaussian Mixture Model, Fuzzy C-means algorithms for Brain Tumor Segmentation BT - International Conference on Communication and Signal Processing 2016 (ICCASP 2016) PB - Atlantis Press UR - https://doi.org/10.2991/iccasp-16.2017.85 DO - https://doi.org/10.2991/iccasp-16.2017.85 ID - Baid2016/12 ER -