CADIA advances in the creation of tools for the analysis of image and artificial intelligence

The CADIA project, which aims to create an image analysis system based on state-of-the-art artificial intelligence techniques, is evolving by creating the necessary annotation tools with which clinicians label images.

After long sessions of gathering requirements and specifications, as well as training and annotation tests, 2400 pathological anatomy samples have been digitized, creating a database of anonymized dicom images, and the necessary radiology images from the SERGAS PACS have been selected and anonymized. The first AI models from public digital radiology and pathology databases have been trained.

Two challenges can be highlighted in radiology, designing a CAD system that is capable of detecting masses in mammography and digital tomosynthesis images acquired with all the equipment available in SERGAS, so that all patients have access to the system; the other, for pathology, with a more novel scenario, since it requires the jump to digital pathology and the analysis of these digitized images for the diagnosis of the type of lesion and its degree.

Our role leading the UTE, consists of the coordination and collection of requirements and specifications in addition to the development of AI algorithms and the necessary infrastructure for the creation of models. Much of the database creation has also been carried out, including the development of annotation tools.

The project is being developed by the joint venture formed by the Vicomtech Foundation and the company Inycom. The present Innovative Public Procurement project is framed within the health innovation plan Code 100 executed in the framework of a collaboration agreement between the Galician Health Service and the Ministry of Science and Innovation, financed in an 80% by the ERDF in the framework of the Spanish Multiregional Operational Programme (POPE) 2014-202.

More information: https://bit.ly/3eIE9bP