A San Francisco company has developed a software package that “stitches” digital radiographs together in the same way a series of photographs are combined to create a panorama.Several original equipment manufacturers and distributors are
A San Francisco company has developed a software package that “stitches” digital radiographs together in the same way a series of photographs are combined to create a panorama.
Several original equipment manufacturers and distributors are evaluating the AccuStitch package, developed by AccuImage. The company hopes to begin marketing the product once the distribution methodology has been finalized, probably this month. Because the original images are bundled with the stitched image, no FDA action is required before the company can begin selling the product, said Leon Kaufman, Ph.D., AccuImage CEO.
”We’ve been around the imaging business a long time, and it didn’t seem too difficult to create a package that was very specific to this need and would allow users not only to do this easily and accurately, but also to validate that they were doing it properly,” Kaufman said.
The company has filed for a patent covering the technology. A firm price for the product has not been set, Kaufman said. It could find a place in angiography, but it might be particularly useful in orthopedic applications, in which long portions of the body, such as bones or the spinal column, are imaged, he said.
Because most radiography systems cover only a limited area of the body, images of these long segments must be combined. Until now, that was usually done by placing the images side by side on a viewbox or by using photographic software that was not specific for medical applications.
With AccuStitch, landmarks are created on each image, which are either acquired digitally or digitized after film capture. The program matches the landmarks to line up the images lengthwise, laterally, and rotationally. The software also gives users flexibility in adjusting and blending the images.
”Stitching now is very crude,” Kaufman said. “What’s been available in this market has not been very creative.”
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.