Radiology is generally concerned with the study of images in the diagnosis of pathology. A paper presented at the RSNA meeting this morning described a methodology designed to give radiologists a better way to examine the operation of their own hospital
Radiology is generally concerned with the study of images in the diagnosis of pathology. A paper presented at the RSNA meeting this morning described a methodology designed to give radiologists a better way to examine the operation of their own hospital diagnostic imaging departments.
The system generates a series of diagrams. It determines departmental workflow and identifies any existing problem areas. The principal benefit of the system, however, is its ability to provide building blocks to create a software prototype that can be extended to automate these workflows and help eliminate departmental problems identified during the analysis.
The methodology, presented by Dr. Sergio Camorlinga, a radiologist at the University of Manitoba, make use of four fundamental tools in the pursuit of interviews, participant observation, diagrams, and other documents:
"UML, a modeling tool used for analysis and design of software engineering projects, combined with a new application of the IHE model, was used as a basis for our diagrams," Camorlinga said.
Software prototypes are a speedy and cost-effective way to capture user requirements, according to Camorlinga.
"The diagrams that are produced with this methodology are a variation of the ones used in UML and have proven to be very useful in this context," he said.
The utility of the diagrams became apparent in communication with the people being interviewed and in identifying areas where the analysis was lacking. This methodology has been applied successfully in three hospitals and has been an excellent tool in the discovery of departmental problems and limitations in services provided, according to Camorlinga.
"The big advantage of this methodology is that it is easy for the user to understand, and it can be used to consolidate ideas and analyze results," he said."It's particularly useful as a foundation for a PACS installation."
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.