DICOM Structured Reporting (SR) is an expressive vehicle, enabling text reports and other clinical data to be stored and transmitted in imaging domains. But it would benefit from methods of defining, creating, and decoding DICOM SR objects using
DICOM Structured Reporting (SR) is an expressive vehicle, enabling text reports and other clinical data to be stored and transmitted in imaging domains. But it would benefit from methods of defining, creating, and decoding DICOM SR objects using inexpensive and widely available tools such as those based on extensible markup language (XML), according to an infoRAD exhibit.
A set of XML schemas and conversion programs developed in the National Digital Mammography Archive (NDMA) project enable the import of text and structured mammography reports, as well as other clinical data items, in the form of DICOM SR information objects.
"What we did was to define an XML equivalent form of DICOM Structured Reports," said Fred Behlen, Ph.D., president of LAI Technology, Homewood, IL.
Just about everyone who generates structured reports internally uses some kind of XML form. But they all use different ones, creating much duplication of effort among implementors, Behlen said.
"We thought it would be useful to have a set of reversible tools for converting from an XML to a DICOM form for structured reporting," he said. "Part of the NDMA project is the ability to collect report data. Sometimes you find you actually have to get down under the hood and work on the tools. That's what I ended up doing here on these XML tools."
The tools provide XML schema definitions of all DICOM Elements, Context Groups, and Templates. A pair of programs converts the XML documents to and from DICOM binary objects. The programs and XML schemas make the creation and interpretation of DICOM SR more accessible to persons with general information technology skills rather than specific DICOM experience.
The exhibit demonstrates the use of these tools in creating schemas for specific reports and the conversion of DICOM SR reports for rendering on Web browsers.
As soon as he obtains signoff for intellectual license, Behlen intends to post and publish the schemas free as part of the archive project by the end of this year.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.