The caBIG® Annotation and Image Markup (AIM) Version 4.0 and AIM Template Enterprise Service (ATES) for Annotating Images

Thursday, October 11, 2012 — Poster Session III
10:00 a.m. – Noon	Natcher Conference Center, Building 45	NCI	IMAG-21

Authors

• P. Mongkolwat
• D. Rubin
• V. Kleper
• S Talbot
• J. Chen
• N. Knight
• E. Siegel

Abstract

AIM 4.0 provides a standard information model used to store annotated information of any type of image. It captures the descriptive information of an image as coded terms with user-generated graphical drawings placed on the image and calculation results that may or may not be related to the drawings into a single common information source. The model explicitly captures relationships (called AIM statements that consist of a subject-predicate-object) between things found, described, drawn on an image, calculated and concluded. Image findings are captured using any standard vocabularies such as RadLex, SNOMED CT, DICOM, ICD-10 and user-defined terminology. These vocabularies contain thousands of terms that make it difficult for users to search and select criteria for inclusion as an AIM annotation. Typical image interpreters desire to select simple and constrained annotations. ATES allows an imaging expert to create and share a set of controlled questions and answers as a template for a particular imaging study without extensive knowledge of the AIM model. A template allows imaging interpreters to select appropriate semantic image content in a standardized format. AIM stores collected information as XML, HL7 CDA or DICOM SR. This structured information can be searched and filtered by a computer program.

back to top