Ladan Aminia - Elec. and Comp. Eng. Dept., Faculty of Eng., Univ. of Tehran, Tehran, Iran
Hamid Soltanian-Zadeh - aElec. and Comp. Eng. Dept., Faculty of Eng., Univ. of Tehran, Tehran, Iran bInstitute for Studies in Theoretical Physics and Mathematics, Tehran, Iran
Caro Lucasa - bInstitute for Studies in Theoretical Physics and Mathematics, Tehran, Iran

Based on a discrete dynamic contour model, a method for segmentation of brain structures like thalamus from magnetic resonance images (MRI) is developed. A new method for solving common problems in extracting the discontinuous boundary of a structure from a low contrast image is presented. External and internal forces deform the dynamic contour model. Internal forces are obtained from local geometry of the contour, which consist of vertices and edges, connecting adjacent vertices. The image data and desired image features such as image energy are utilized to obtain external forces. The problem of low contrast image data and unclear edges in the image energy is overcome by a new algorithm that uses several methods like thresholding, unsupervised clustering methods such as fuzzy C-means (FCM), edge-finding filters like Prewitt, and morphological operations. We also present a method for generating an initial contour for the model from the image data automatically. Evaluation and validation of the methods are conducted by comparing automatic and radiologist segmentation results, which confirms good performance of the new method

Dynamic contours; Clustering; Segmentation; Image processing; Thalamus; MRI