Skoltech researchers have trained a neural network to search for lung pathologies on X-ray images and come up with brief verbal descriptions to accompany them. This task is currently performed by physicians, and it takes several minutes to complete.
According to study published in the American Journal of Roentgenology (AJR), MRI-based surveillance after surgical treatment of musculoskeletal soft-tissue sarcomas (STS) shows utility for detecting clinically occult local recurrences (LRs), potentially improving patient outcomes.
The researchers found that for the test set, the 3-D CNN reached a sensitivity and specificity of 83.3 and 86.6 percent, respectively, compared with the mean reader sensitivity and specificity of 77.6 and 81.6 percent, respectively. There was significant improvement for the combined group of readers with AI support, from a sensitivity of 77.6 to 85.6 percent and from a specificity of 81.6 to 91.3 percent. The number of false-negative and false-positive findings were also reduced with AI support.
The automated AI body composition tools had high technical adequacy rates in a heterogeneous sample of external CT examinations, supporting the tools' generalizability and potential for broad use," concluded head researcher B. Dustin Pooler, MD, from the University of Wisconsin School of Medicine & Public Health in Madison.
The Ohio State University Wexner Medical Center is the first in the United States to install this recently FDA-approved full body MRI for patient care. The technology uses a lower magnetic field to open up new possibilities for imaging the lungs and patients with implanted devices and will potentially support new interventional procedures that could result in less radiation exposure.
