Researchers at Siemens Corporate Technology are developing a platform known as Medico that brings together all the available medical imaging data for a specific patient, while also incorporating information from other patients with similar conditions.

Medico will combine medical knowledge for the first time with new image-processing methods, knowledge-based information processing techniques, and machine learning technologies. The system will thus be able to autonomously interpret images of anatomical structures such as bones, blood vessels, and organs, and also recognize any abnormal changes to them. The data will then be automatically catalogued and linked with reference images and treatment reports from several databases. Siemens experts are focusing initially on 3D data sets from tomography devices (CT/MR) in order to close the existing semantic gap in a predefined area between unstructured image data and medical terminology. “Semantic” refers in this context to the ability of a computer program to understand image content. An initial series of tests for the Medico prototype is planned for 2009 at Erlangen University Hospital.

Medico is one of six application scenarios in Theseus, a program launched by Germany’s Ministry of Economics and Technology that focuses on Web 3.0, which makes information content available and understandable to computers. The program’s objective is to work with unstructured data to develop a general method that ensures order and hierarchy in systems like Medico. Siemens’ partners in the Medico project include the German Research Center for Artificial Intelligence, the Fraunhofer Institute for Computer Graphics Research, and Ludwig Maximilian University in Munich.