A multipronged effort is under way to standardize and thereby improve the quality of digital images. The first results of this effort could be in hand very soon.
A multipronged effort is under way to standardize and thereby improve the quality of digital images. The first results of this effort could be in hand very soon.
Two new families of CT and MR objects designed for DICOM are scheduled for release within days. Their development has been driven by the Society for Computer Applications in Radiology and the National Electrical Manufacturers Association working with vendors. Together they have come up with tools and an infrastructure for developing, testing, validating, and demonstrating the new objects. Those test tools and sample images, along with open source code not yet publicly accessible, are scheduled to be available after the SCAR meeting, which ended June 5.
"The key goal (behind these developments) has been to organize CT and MR images to enable greater interoperability of the application," said David Clunie, chief technology officer of RadPharm and a member of the industry development team responsible for enhancing DICOM.
RadPharm is a full-service imaging core lab that specializes in managing the imaging segment of global clinical trials.
Others in industry and academia are looking at digital imaging as a whole. They hope to identify opportunities for improving digital image quality in general, but particularly in evolving areas. Image quality is especially vulnerable in areas such as digital mammography, where the standards have been achieved with film.
The American College of Radiology, SCAR, RSNA, and American Association of Physicists in Medicine are coming together with manufacturers, regulators, and users to form a panel of experts to discuss relevant topics. They plan to publish a white paper and open it up to feedback within the next three to five months, according to SCAR chair Dr. J. Anthony Seibert. The effort is aimed at closing gaps that have opened between what digital technologies are capable of and what they actually deliver.
The most immediate impact on image quality will likely come from efforts to enhance DICOM for CT and MR. Enhanced DICOM standards for these two modalities are urgently needed, Clunie said.
Speaking at the SCAR meeting in Orlando, he noted that DICOM CT and MR image objects are more than 10 years old and have become outdated by the rapidly advancing technologies. Much of the important information needed to support advanced applications, therefore, is not represented in standard attributes of DICOM-encoded CT and MR images. This dearth of information compromises the ability to connect equipment from different vendors.
The new CT object is expected to have 41 attributes, 39 of them mandatory, and 86 terms, 18 of them "enumerated," according to Clunie. Enumerated terms require compliance from all vendors. The enhanced DICOM MR object includes 103 attributes, 94 of them mandatory, and 228 terms, 47 enumerated, Clunie said.
Can Emerging AI Software Offer Detection of CAD on CCTA on Par with Radiologists?
May 14th 2025In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.
Study Examines CT-Based AI Detection of Incidental Abdominal Aortic Aneurysms
April 29th 2025The AI software Viz AAA offered a sensitivity of 87.5 percent in detecting abdominal aortic aneurysms on contrast-enhanced CT, according to new retrospective research presented at the American Roentgen Ray Society (ARRS) conference.