Feasibility study of a new platform based on the Case-Based Reasoning principles to efficiently search and store voxel phantoms
Résumé
In case of accidental exposure to radiation, it is necessary to establish as soon as possible a dosimetry report for each victim. In most cases, this report is based on medical images of the victim, enabling the construction of a personalized realistic numerical model, also called a voxel phantom. Unfortunately it is not always possible to perform the medical imaging of the victim since the technology may be unavailable or to avoid additional exposure to radiation. In such cases, the commonly used method is to represent the victim with a numerical model like the "Reference Man", a voxelized phantom representative of the average male individual. The treatment accuracy depends on the diagnosis precision and, consequently, on the similarity of the phantom and/to the victim. A precise dosimetry evaluation requires a personalised and realistic phantom whose biometric characteristics match the victim; such model is often unavailable. The Case-Based Reasoning (CBR) is a problem solving method for the conception of intelligent systems. It imitates the analysis, understanding and reconstruction of the human intelligence. The ReEPh project (Research of Equivalent Phantom) proposes to use the CBR principles to retrieve from a set of phantoms, the most adapted one to the irradiated victim. For this study, the ReEPh platform retrieves, stores and compares existing phantoms to a victim. A graphic interface enables the user to compare victim's characteristics to the ones of the most similar phantoms available in the database. This defines a similarity index presenting the equivalence between the victim and the suggested phantom. Moreover, a confidence index is also assessed to define the uncertainty implied by the RaPC choice procedure. © EDP Sciences, 2010.