The process to link two data sets acquired from different modalities or with the same modality at different times must now be done manually on the Carestream PACS. By early next year, these PACS users will be able to skip this time-consuming step using an automatic registration feature previewed at the Society for Imaging Informatics in Medicine meeting.
The process to link two data sets acquired from different modalities or with the same modality at different times must now be done manually on the Carestream PACS. By early next year, these PACS users will be able to skip this time-consuming step using an automatic registration feature previewed at the Society for Imaging Informatics in Medicine meeting.
Carestream luminaries will begin testing the capability in early fall. General release is expected early next year.
Radiologists today may spend several minutes per case registering data sets, a time expenditure whose significance increases with increasing throughtput. When autoregistration becomes available onboard Version 11 of the Carestream PACS, the computer will do the work.
Users will pick a point in one data set, seen on a slice depicting a lesion, for example. The registration function will then automatically find the same point in one or more other data sets, presenting in split screen these data sets in the same format as the first.
"Autoregistration will physically register the data in the same way," said Eddie Moore, senior sales engineer at Carestream.
The data may be presented in axial or even oblique slices, he said.
Registration may be needed simply because the patient was scanned in a slightly different position from previous scans, he said. Or the data may be fundamentally different, as occurs when comparing CT and MR results, an increasingly common practice after cancer treatment as oncologists try to reduce patient exposure to ionizing radiation.
Reformatting of the data can be particularly helpful when looking at vasculature, according to Moore.
"We are able to look at the oblique view of vessels and see the actual diameter of the vessel," he said.
Deep Learning Detection of Mammography Abnormalities: What a New Study Reveals
June 19th 2023In multiple mammography datasets with the original radiologist-detected abnormality removed, deep learning detection of breast cancer had an average area under the curve (AUC) of 87 percent and an accuracy rate of 83 percent, according to research presented at the recent Society for Imaging Informatics in Medicine (SIIM) conference.
Detecting Intracranial Hemorrhages: Can an Emerging AI Advance Have an Impact?
June 9th 2022A 3D whole brain convolutional neural network could provide enhanced sensitivity and specificity for diagnosing intracranial hemorrhages on computed tomography, according to new research presented at the Society for Imaging Informatics in Medicine (SIIM) conference in Kissimmee, Fla.