Imaging Ontology 101: The Lego Approach

Discover the benefits of having a common ontology for all patient images. This will broadly be divided into the following categories:

• Clinical care: While radiology images have the benefit of having common standards like Radlex, other patient images like photos, ophthalmology images, endoscopy images etc, do not have the benefit of any common standard or an ontology i.e. a common language which would enable indexing, archiving and retrieval of images in a standard manner. Lack of common ontology means that the images could be lost in a haystack (like bunch of Legos from different sources in a box) and might not be easily retrievable at the point of care by caregivers. This is a barrier for patient care as caregivers might not get a holistic view of the patient’s image data and hence might not be able to provide appropriate care affecting patient outcomes.
• Research: Standard ontologies enable multidisciplinary research such that patient images from different sources can be analyzed together. For example a photo of melanoma can be compared to the pathology slides for the same melanoma
• AI/ML: For AI and ML to reach its full potential in enhancing patient care the algorithms need clean and labelled data. Unless there is a common ontology it might be very challenging to provide an algorithm with clean training data which will obviously have a negative impact on the accuracy of such algorithms. For example – having a common ontology would enable radiomics and pathomics to work together for the same patient.
• HIMSS-SIIM collaboration to develop common ontology.

Objectives

• Describe some commonly available radiology ontologies
• Discuss the benefits of a common Ontology in clinical care
• Understand the benefits of standard ontology in research and AI/ML

Resources

Body Part Standardized Imaging Terminology (BPSITE)

Adoption of standard medical terminology for clinical systems is critical to improve interoperability, patient safety, and clinical outcomes and will allow medical practitioners to leverage the promises of precision medicine.

We want to hear from you! Take the Survey

CE Credit

SIIM has approved this activity for 1.0 hours of SIIM IIP Credits towards certification and re-certification by the American Board of Imaging Informatics (ABII).