AUTOMATED PLANNING TARGET VOLUME GENERATION - AN EVALUATION FITTING ACOMPUTER-BASED TOOL AGAINST HUMAN EXPERTS

Purpose: Software tools are seeing increased use in three-dimensional treatment planning, However, the development of these tools frequently omits careful evaluation before placing them in clinical use, This st udy demonstrates the application of a rigorous evaluation methodology using blinded peer review to an automated software tool that produces ICRU-50 planning target volumes (PTVs). Methods and Materials: Seven p hysicians from three different institutions involved in three-dimensio nal treatment planning participated in the evaluation, Four physicians drew partial PTVs on nine test cases, consisting of four nasopharynx and five lung primaries, Using the same information provided to the hu man experts, the computer tool generated PTVs for comparison, The rema ining three physicians, designated evaluators, individually reviewed t he PTVs for acceptability, To exclude bias, the evaluators were blinde d to the source (human or computer) of the PTVs they reviewed. Their s corings of the PTVs were statistically examined to determine if the co mputer tool performed as well as the human experts. Results: The compu ter tool was as successful as the human experts in generating PTVs, Fa ilures were primarily attributable to insufficient margins around the clinical target volume and to encroachment upon critical structures. I n a qualitative analysis, the human and computer experts displayed sim ilar types and distributions of errors. Conclusions: Rigorous evaluati on of computer-based radiotherapy tools requires comparison to current practice and can reveal areas for improvement before the tool enters clinical practice. (C) 1997 Elsevier Science Inc.