- AI
- Molecular Imaging
- CT
- X-Ray
- Ultrasound
- MRI
- Facility Management
- Mammography
Motion-induced images may help diagnosis
Introducing motion into the display of static images could improve detection performance and efficiency, according to a paper presented Friday at the Society for Imaging Informatics in Medicine meeting.
Introducing motion into the display of static images could improve detection performance and efficiency, according to a paper presented Friday at the Society for Imaging Informatics in Medicine meeting.
Human visual perception can better detect some types of objects and structures if motion is added, said presenter Elizabeth Krupinski, Ph.D., of the University of Arizona. Typically, multiple image studies and 3D reconstructions are well suited to utilization of pseudomotion, but static images are not.
In the pilot study, Krupinski used z-axis kinematic motion (ZAK), a surface rendering technology, to make a static radiographic image appear to be rotating in the display plane. A test set of 10 static and ZAK-processed angiographic images containing 27 stenotic locations were reviewed by five radiologists in two sessions, one to view static images and the other to view motion-induced images.
With viewing the motion-induced images, three of the five readers experienced a statistically significant reduction in viewing time. One radiologist reported no change. For the remaining radiologist, evaluating the motion images took longer than the static images.
Residents benefited most from seeing the motion-induced images, Krupinski said, but could not speculate on the reason why due to the limited nature of the study.
The technology may prove valuable in evaluating mammograms, breast MRI, and bone fractures, Krupinski 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.
