Locating the eyes in CT brain scan data
Kostis Kaggelides, R. B. Fisher, Peter J. Elliott · 1993
In this document, a technique for locating the eyes in Computed Tomography brain scan data, is described. The objective is to automatically localise the eyes for protection during radiotherapy planning. The image feature that is exploited is the circularity of the eyes. After data preprocessing to remove parts of the CT machinery, signature analysis is performed to locate areas of interest. By applying Canny's edge detector to these areas, data is further reduced to the signicant edge fragments. The Hough Transform is then applied. The Converging Squares algorithm is used as an ecient and robust method to search the parameter space. The results are processed by the hypothesis generation stage which clusters them according with the x; y; z coordinates of the suggested centres. The ISODATA algorithm is used for clustering. The hypotheses are assessed and sorted. The most valid hypothesis is selected and rened using a second Hough Transform, this time considering spheres. After the rejection of the invalid members of the hypothesis cluster, an ellipsoid is tted to the new cluster centre and the results are drawn on the data. The method is fast and robust. The method was tested using ve dierent data sets and it performed well on all of them. 1