Not all CR images are suitable for interpretation, which not only inhibits workflow but may cause misdiagnosis. Once an unsuitable image is registered in the database, correction adjustments must be made on every subsequent observation. A scientific
Not all CR images are suitable for interpretation, which not only inhibits workflow but may cause misdiagnosis.
Once an unsuitable image is registered in the database, correction adjustments must be made on every subsequent observation.
A scientific poster from the RSNA conference offered a solution to this problem in the form of a cost-effective manual CR inspection system, called CRIS, designed to guarantee that images are analyzed before they are registered in the PACS database.
The CRIS system consists of a high-definition monochrome monitor equal to or better than what radiologists use at workstations. A senior radiology technologist has the responsibility to confirm and adjust CR images as necessary before image registration.
As a result, all images are available for interpretation immediately, which is not always the case otherwise.
The poster reported benefits from the use of the CRIS system at Showa University Northern Yokohama Hospital in Japan between May 2001 and June 2002.
During that period, 29,013 of 125,885 images (23%) were processed by CRIS. Faulty marking or flipping, either of which could affect image interpretation, was found on 19,436 (15%)of the images.
The principal benefit of the system, aside from ensuring diagnostic quality, was the time saved by radiologists who normally must confirm questionable CR images by telephone.
According to lead author Dr. Hiroki Takenaka, if radiologists had to use the telephone to confirm the images salvaged by CRIS and had to make the adjustments themselves (assuming two to six minutes per inquiry), 1.3 to 3.9 hours per day could potentially be lost.
While CRIS requires the addition of a senior technologist FTE, the authors consider the expense reasonable when weighed against benefit.
Average image process time by technologists was found to be about 50 seconds per image, fast enough not to compromise rapid image delivery.
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.