A client-server model for advanced image postprocessing techniques is unshackling radiologists at the University of Texas M.D. Anderson Cancer Center from their PACS workstations. By distributing advanced postprocessing capabilities to computers
A client-server model for advanced image postprocessing techniques is unshackling radiologists at the University of Texas M.D. Anderson Cancer Center from their PACS workstations. By distributing advanced postprocessing capabilities to computers throughout the enterprise, it allows radiologists to do volume rendering and multiplanar reformations anywhere they are needed.
The client-server model uses server hardware and software to perform advanced postprocessing in real-time. Users interact with the server via a thin client that can be downloaded using a Web browser.
"The development of systems that can distribute the ability to do advanced postprocessing to wherever the radiologist may be working is significant," said Dr. Eric P. Tamm, an assistant professor of radiology at M.D. Anderson.
Until the development of these systems, radiologists had to move to an advanced workstation to do postprocessing.
"The traditional paradigm has been the review of axial images on PACS workstations. The construction of postprocessed images required advanced workstations that have typically been in different locations," Tamm said.
While several manufacturers have begun to incorporate entire postprocessing programs into PACS workstations to eliminate this physical separation, this approach demands major hardware upgrades at a high cost to permit this capability for every workstation.
Now, with the client-server model, radiologists can more freely use such capabilities wherever they need them: at a PACS reading station, in a consultation area meeting with clinicians, in a case management conference, or even in their own offices for academic purposes, he said.
Tamm found that the thin client is capable of running simultaneously on the same computer platform as that running the PACS without modification of hardware.
Radiologists working from the PACS workstation can now direct the PACS archive to push images to the server, which is made by TeraRecon. They can then interactively direct the server to create and view complex 3D volume-rendered images and finally push selected images back to the PACS archive for distribution to clinicians via M.D. Anderson's self-developed Clinicstation, Tamm said.
"We are also able to use the thin client on radiologists' office computers and conference room computers with LCD projectors," he said.
Using this approach, it has been possible to routinely create complex postprocessed images on office computers for clinical and academic purposes.
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.