Digital radiography extension nears inclusion in DICOMDICOM Committee members are currently voting on a proposed extension to the DICOM standard that would add support for images and information generated by digital radiography systems. With
DICOM Committee members are currently voting on a proposed extension to the DICOM standard that would add support for images and information generated by digital radiography systems. With commercial availability of systems from companies such as Sterling Diagnostic Imaging forthcoming in the next several months
(
PNN
7/98), the committee's timing couldn't be better.
The new proposal differs in a number of ways from the DICOM computer radiography (CR) image definition. For example, specific attributes unique to digital radiography systems, such as detector characteristics, were included.
In addition, the DICOM working group that developed the digital x-ray extension (DX) raised the bar significantly in comparison with other modality image objects already in the standard. Specifically, the group mandated the inclusion of information supporting hanging protocols, which define how a radiologist may prefer to look at an image set, or how a technologist might hang the films on an alternator.
By accommodating hanging protocols in the digital radiography image object, radiologists will not have to flip or rotate the images, invert the gray scale, or perform other operations to make the displayed image conform to their preferences in viewing studies. All attributes that allow a software application at a workstation to support this protocol must be included in the image object, and manufacturers adhering to the standard will not be able to get away with leaving this information out.
In addition to general x-ray uses, the digital x-ray extension also supports other radiographic applications such as digital mammography and intra-oral and panoramic dental x-ray imaging.
The extension offers another improvement over the CR image object. Typically, vendors exchange CR images in one of three ways: as raw unprocessed data, as raw data with look-up tables that enable the image to be viewed correctly at a workstation, or as processed data. Unfortunately, the CR image object doesn't include a mechanism to alert the user or the workstation as to which of the three kinds of data to expect.
The digital x-ray extension resolves this problem by providing the capability for explicit exchanges such as raw data, "for processing" data, or "for presentation" data. This allows institutions to look at the raw image data for quality assurance purposes, or, if they wish, to apply their own image-processing algorithms.
With the new extension accommodating direct digital capture, the DICOM standard will allow these new images to be encoded in a standard manner. By supporting the hanging protocol as well, the extension enables radiology departments to improve their work flow and increase their efficiency.
-Herman Oosterwijk, president, OTech Inc. (herman@otechimg.com)
Can MRI-Based AI Enhance Pre-Op Prediction of Tumor Deposits in Patients with Rectal Cancer?
October 31st 2024For patients with rectal cancer, an emerging nomogram that combines deep learning and clinical factors had greater than 16 percent and 23 percent increases in accuracy and specificity, respectively, for pre-op prediction of tumor deposits in comparison to clinical factors alone.