Brain

The applications of magnetic resonance imaging (MRI) has undergone since the last decades an unstopped development. Large datasets containing thousands of medical images are currently available to supply clinical diagnosis and this is particularly true for brain diseases. At the same time more and more sophisticated software and computationally intensive algorithms have been implemented to extract useful information from medical images. As a consequence many medical image processing applications would greatly take advantage from grids: run-time reduction, sharing of data collections and platform-hardware independent congurations are simple examples. With this goal we implement some methods to exploit Grid or more in general distributed computing infrastructures; within the services produced there is a feasibility study for inter-subjects multimodal registration and a segmentation algorithm workflow dedicated to the Hippocampus. The workflow allows the end user to upload MRIs which are registered with several ICBM templates and to segment them with a classier. The proposed approach can be useful even for large-scale studies or clinical trials.