PACS vendors typically use proprietary formats to embed lesion measurement data on imaging studies, creating a challenge for big-data endeavors that involve quantitative imaging assessment, according to presenter Dr. Nathaniel Swinburne, a neuroradiology fellow at the Icahn School of Medicine at Mount Sinai in New York City.
"This limits the ability to perform aggregation of lesion data essential for various purposes, such as quantifying tumor response to therapy in clinical trials," Swinburne said.
The Annotation and Image Markup (AIM) format was created to standardize the reporting of both quantitative and qualitative imaging data to facilitate such initiatives, but there's still a need to automatically convert existing proprietary image markup data to the AIM standard, he said.
To address this problem, the researchers created a software tool to automate the conversion of line measurement annotations that were created and stored in their Centricity PACS software (GE Healthcare). This demonstrated that vendor-specific data can be "unlocked," enabling interoperability of annotation data from multiple PACS sources, Swinburne said.
"This work could be extended to convert additional commercial PACS formats to AIM," he told AuntMinnie.com.
Get all of the details by sitting in on this Tuesday presentation.
