Interactive region and volume growing for segmenting volumes in MR and CT images

In radiation treatment planning it is necessary to mark out selected parts of CT or MR images which are clinically relevant before designing the treatment plan. This process is usually done manually with a mouse, and for a typical data set of some 40 slices it can be a time-consuming and tedious process. We report on a system for interactive region and volume growing that assists the clinical user in outlining relevant volumes. The algorithm detects regions of interest grown from a seed selected interactively by a user. The regions consist of connected areas or volumes having similar pixel intensity values. Threshold parameters for controlling the algorithm can be set interactively, or may be determined automatically from a sample region. Region growth can be successively extended into adjacent slices so building up a three-dimensional (3D volume. Direct 3D volume growth from a seed voxel is also possible. The algorithm has been integrated into one of the pilot systems developed as part of COVIRA, project A2003 in the EC's AIM programme.