DICOM Update: DICOM accommodates new technologyBy Herman Oosterwijk, President, OTech Inc.Every year, PACS vendors present new technological applications, advances, and extensions to existing imaging
By Herman Oosterwijk, President, OTech Inc.
Every year, PACS vendors present new technological applications, advances, and extensions to existing imaging applications. In response to some of these product additions, the DICOM Committee has begun to incorporate new sections to the standard.
Computer-aided detection (CAD) is a new medical imaging application that shows a lot of promise, especially in mammography. When a mammography image that uses CAD is sent to a workstation, however, no standardized way exists to communicate the area of concern highlighted by the CAD software.
A proposal has been presented to make use of the American College of Radiologys BI-RADS mammography reporting and terminology standard in combination with the recently proposed DICOM structured reporting supplement. Sources knowledgeable about the standard believe that the proposal to extend the standard will be adopted soon, based on the momentum being generated in the mammography CAD arena.
In media exchange developments, a proposal has been generated by a DICOM working group to perform experimental work using existing digital video disk (DVD) technology. Further standardization efforts will occur when the optical media industry agrees on a single standard that guarantees interoperability among the different types of DVD media, such as DVD-R and DVD-RAM. When that takes place, a final DICOM DVD media exchange standard will be submitted for approval.
In addition to developing new technologies, medical imaging vendors are extending the capabilities of traditional modalities, such as adding three-dimensional visualization of ultrasound images. When the DICOM standard was first defined in the early 1990s, image acquisition was standardized on an image by image basis. Images were typically neatly spaced and related in a manner that was easily described (for example, as orthogonal or parallel image planes). Even if represented as separate image planes, the relationship among the individual images acquired by these new 3-D acquisition techniques cannot be described as easily. The ultrasound 3-D data set can be acquired by a technologist using a probe and making a freehand sweep, after which the individual slices no longer have a straightforward relationship.
To avoid independent and divergent efforts in multiple working groups, the DICOM Committee set up Working Group 17 to develop a common framework for multidimensional data sets, applicable to any modality and clinical specialty. The mission of this working group is to facilitate the support of dimensions of any type, including space, time, or spectral. This would include native modality objects (raw data), re-sampled objects such as 3-D reconstructed volumes, and derived presentation objects (two-dimensional images or slices rendered from 3-D objects).
The group will also study related data sets within multidimensional objects, such as a 3-D volume data set that has a time relationship resulting in four dimensions. Additional dimensions include space, time, physiological phase, detector energy, or other acquisition-defined dimensions. The groups activity will likely affect all existing specialties and working groups. New image objects will be defined, especially in modalities like MRI and ultrasound, where technological developments continue at a rapid rate.
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.