A new strategy for image retrieval that combines a central database with a distributed system architecture promises to make content-based programs the preferred method for handling large data sets efficiently.
A new strategy for image retrieval that combines a central database with a distributed system architecture promises to make content-based programs the preferred method for handling large data sets efficiently.
Researchers from the Institut fur Medizinische Informatik in Aachen, Germany, described an approach called content-based image retrieval for medical applications, or IRMA. Its distributed system architecture is suitable for large image databases such as those housed within a PACS (Methods Inf Med 2004;43:354-361).
When a radiologist detects an abnormal pattern in an image but finds pathological diagnosis difficult, IRMA presents images showing similar patterns and offers direct access to the corresponding patient records.
For teaching purposes, radiologists can select and retrieve images that demonstrate particular artifacts or pathologies by means of a particular pattern rather than textual description.
Considering Breast- and Lesion-Level Assessments with Mammography AI: What New Research Reveals
June 27th 2025While there was a decline of AUC for mammography AI software from breast-level assessments to lesion-level evaluation, the authors of a new study, involving 1,200 women, found that AI offered over a seven percent higher AUC for lesion-level interpretation in comparison to unassisted expert readers.