Automated Segmentation of Brain Tumors in MRI Using Force Data Clustering Algorithm

Authors:
Masoumeh Kalantari Khandani;Ruzena Bajcsy;Yaser P. Fallah
Affiliations:
School of Engineering Science, Simon Fraser University, Canada;Electrical Engineering and Computer Sciences, University of California, Berkeley, USA;Electrical Engineering and Computer Sciences, University of California, Berkeley, USA and Institute of Transportation Studies, University of California, Berkeley, USA
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Year:
2009

Citing 5
Cited 0

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing Deviations from Normalcy for Brain Tumor Segmentation

MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
Atlas-Based Segmentation of Pathological Brains Using a Model of Tumor Growth

MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
Segmentation of Meningiomas and Low Grade Gliomas in MRI

MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Brain Tumor Detection Using Color-Based K-Means Clustering Segmentation

IIH-MSP '07 Proceedings of the Third International Conference on International Information Hiding and Multimedia Signal Processing (IIH-MSP 2007) - Volume 02

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a novel automated method for detecting tumor location in brain magnetic resonance (MR) images, and identifying the tumor boundary. This method employs an unsupervised learning algorithm called Force for coarse detection of the tumor region. Once tumor area is identified, further processing is done in the local neighborhood of the tumor to determine its boundary. The Force method, which is based on the rules of electrostatics, is used for finding spatial clusters of high intensity in the 2D space of MR image. Further analysis of the identified clusters is performed to select the cluster that contains the tumor. This method outperforms many existing methods due to its accuracy and speed. The performance of the proposed method has been verified by examining MR images of different patients.