The authors report the first highly automated CT image segmentation and interpolation scheme applied to model patient-specific EM hyperthermia. This novel system is based on sophisticated tools from the artificial intelligence, computer vision, and computer graphics disciplines. It permits CT-based patient-specific hyperthermia models to be constructed without tedious manual contouring on digitizing pads or CRT screens. The system permits in principle near-real-time assistance in hyperthermia treatment planning. The authors apply this system to interpret actual patient CT data, reconstructing a 3-D model of the human thigh from a collection of 29 serial CT images at 10 mm intervals. Then, using the finite-difference-time-domain (FD-TD) method, they obtain 2-D and 3-D models of EM hyperthermia of this thigh due to a waveguide applicator. They find that different results are obtained from the 2-D and 3-D models, and they conclude that full 3-D tissue models are required for future clinical usage.