Abstract

This paper describes works carried out in the Virtual Imaging Platform (VIP) project to create a comprehensive conceptualization of object models used in medical image simulation and suitable for the major imaging modalities and simulators. The goal is to create an application ontology that can be used to annotate the models in the VIP platform's model repository, to facilitate their sharing and reuse. Such annotations allow making the anatomical, physiological and pathophysiological content of the object models explicit.

Highlights

  • Medical imaging has become a very rich source of information which plays a major role in diagnosis, therapy and patient follow-up

  • This paper describes the design methodology and the implementation of an ontology for medical image simulation models, tailored to the needs of integrating the SINDBAD, SIMRI, SORTEO and FIELD-II simulators in the Virtual Imaging Platform (VIP) platform, but extensible to address the needs of other simulators in the future

  • Ontology of Medical image simulation object models The ontology of medical image simulation object models5 allows precise semantics to be associated to the data files that compose a model

Read more

Summary

Introduction

Medical imaging has become a very rich source of information which plays a major role in diagnosis, therapy and patient follow-up. The progress of medical imaging will certainly continue and one can foresee that all this imaging data will be used in the future to build some sort of digital patient avatars (i.e. virtual representation) composed of a set of personalized and integrated models representing anatomical, physiological and pathophysiological aspects of the organism Such avatars could be used to test and compare various therapeutic approaches, to predict their outcome, and contribute to decision making. Prerequisites for this to materialize are: (1) that such models are developed, something that initiatives like the Virtual Physiological Human (VPH) strongly support [1,2], and (2) that appropriate model identification methods are developed, whose function is to estimate the various model parameters from the specific patient multimodal image data. One can compare the result of a segmentation algorithm with the actual definition of the imaged object

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call