Published online by Cambridge University Press: 08 March 2010
In case of accidental exposure to radiation, it is necessary to establish as soon aspossible a dosimetry report for each victim. In most cases, this report is based onmedical images of the victim, enabling the construction of a personalized realisticnumerical model, also called a voxel phantom. Unfortunately it is not always possible toperform the medical imaging of the victim since the technology may be unavailable or toavoid additional exposure to radiation. In such cases, the commonly used method is torepresent the victim with a numerical model like the “Reference Man”, a voxelized phantomrepresentative of the average male individual. The treatment accuracy depends on thediagnosis precision and, consequently, on the similarity of the phantom and/to the victim.A precise dosimetry evaluation requires a personalised and realistic phantom whosebiometric characteristics match the victim; such model is often unavailable. TheCase-Based Reasoning (CBR) is a problem solving method for the conception of intelligentsystems. It imitates the analysis, understanding and reconstruction of the humanintelligence. The ReEPh project (Research of Equivalent Phantom) proposes to use the CBRprinciples to retrieve from a set of phantoms, the most adapted one to the irradiatedvictim. For this study, the ReEPh platform retrieves, stores and compares existingphantoms to a victim. A graphic interface enables the user to compare victim’scharacteristics to the ones of the most similar phantoms available in the database. Thisdefines a similarity index presenting the equivalence between the victim and the suggestedphantom. Moreover, a confidence index is also assessed to define the uncertainty impliedby the RaPC choice procedure.