Cloud-based Medical Image Collection Database with Automated Annotation

Abstract

Typical medical image annotation systems use manual annotation or complex proprietary software such as computer-assisted-diagnosis. A more objective approach is required to achieve generalised Content Based Image Retrieval (CBIR) functionality. The Automated Medical Image Collection Annotation (AMICA) toolkit described here addresses this need. A range of content analysis functions are provided to tag images and image regions. The user uploads a DICOM file to an online portal and the software finds and displays images that have similar characteristics. AMICA has been developed to run in the Microsoft cloud environment using the Windows Azure platform, to cater for the storage requirements of typical large medical image databases.