Researchers from the Fraunhofer Institute for Medical Image Computing, Germany willl soon be showing off a new deep learning software that is able to measure the size of tumors undergoing treatment and detect new metastases that may otherwise be overlooked.
What’s particularly interesting here is not how it outlines tumors, but that it improves its accuracy the more patient CT and MRI scans that it sees. In a test of the software using 149 scans of patient livers, the software kept getting better at outlining the relevant features.
“Our program package increases confidence during tumor measurement and follow-up,” said Mark Schenk from the Fraunhofer Institute for Medical Image Computing in a published statement. “The software can, for example, determine how the volume of a tumor changes over time and supports the detection of new tumors.”
The details of the research will be presented at the RSNA 2016 annual meeting at the end of November in Chicago, Illinois.