Compression offerings should find solid niche Compression offerings should find solid nicheThe use of lossy compression technologies in medical imaging remains a controversial subject, despite its widely touted benefits. The American College
Compression offerings should find solid niche
Compression offerings should find solid niche
The use of lossy compression technologies in medical imaging remains a controversial subject, despite its widely touted benefits. The American College of Radiology and the Food and Drug Administration have offered little in the way of useful guidance on this matter, and many conservative physicians remain unconvinced about lossy compression sche-mes, although several clinical studies have found no negative effects on the diagnostic content of images.
A breakthrough could be on the horizon, however, thanks to several interesting new applications of wavelet compression technology. At the 1998 RSNA meeting, the introduction of dynamic transfer syntax from a University of Pittsburgh team was the talk of the infoRAD area and exhibit halls (PNN 1/99). Another interesting wavelet- compressed image communication offering, called MrSID, was debuted by LizardTech at this year's SCAR meeting (see story, page 4).
The era of enterprise-wide PACS and Web-based image distribution requires rapid dissemination of large image files. Technologies such as DTS and MrSID, which use wavelet schemes to allow users to initially receive lower resolution images and access additional resolution or pixels on demand, offer the promise of dramatic performance improvements for these kinds of networks. Advances in networking technology will undoubtedly also help in this regard, but PACS users would be well served by overcoming any doubts they might have about employing lossy compression. The success of their large-scale PACS implementation may depend on it.
--Erik L. Ridley, Editor
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.