Journal highlights
The following are highlights from the current issues of RSNA’s peer-reviewed journals.
Precision Screening of Osteoporosis
Osteoporosis affects approximately 200 million women globally, with an estimated increase of 9 million individuals each year. Because it rarely presents with symptoms, osteoporosis is difficult to diagnose, making it important to provide screening for high-risk populations.
Opportunistic screening using AI may be useful for patients who are asymptomatic and do not otherwise meet the formal criteria for bone density testing with dual-energy X-ray absorptiometry (DXA).
Chin Lin, PhD, National Defense Medical Center in Taipei, Taiwan, and colleagues sought to evaluate the effectiveness of DXA screening in high-risk patients with osteoporosis identified by an AI model using chest radiographs. The results were published in an article in Radiology.
“Providing DXA screening to a high-risk group identified with AI-enabled chest radiographs can effectively diagnose more patients with osteoporosis,” the authors conclude.
Read the full article, “Osteoporotic Precise Screening Using Chest Radiography and Artificial Neural Network: The OPSCAN Randomized Controlled Trial.”
Follow the Radiology editor on X @RadiologyEditor.
Images demonstrate how artificial intelligence (AI) using chest radiographs makes decisions. Left: Original chest radiographs in posterior-anterior view. Right: Class activation maps generated by overlays (colored probability maps) onto the original image.
Complete legend details can be found at https://doi.org/10.1148/radiol.231936 ©RSNA 2024.
Vascular Pathologic Conditions In and Around the Spinal Cord
The diagnosis and differentiation of spinal vascular pathologic conditions are challenging and are further complicated by small structures, long imaging times and overlapping imaging features. However, radiologists can learn to spot subtle findings and employ useful protocols to help narrow the differential diagnosis.
In an article published in RadioGraphics, Jennifer McCarty, MD, University of Texas Health in Houston, and colleagues seek to aid in the accurate and timely diagnosis of spinal vascular pathologic conditions in and around the spinal cord. They highlight spinal vascular anatomy, imaging strategies and three broad categories of abnormalities that include infarcts, anomalies and tumors.
“Radiologists armed with a solid foundation of knowledge, specific spine imaging protocols, and a high level of suspicion can aid in the accurate and timely diagnosis of spinal vascular pathologic conditions,” the authors conclude.
Read the full article, “Vascular Pathologic Conditions in and around the Spinal Cord,” at RSNA.org/RadioGraphics. This article is also available for CME on EdCentral or at RSNA.org/Learning-Center. Follow the RadioGraphics editor on X @RadG_Editor.
Patient with both cerebral and spinal cord cavernous malformations. (A) Axial T2-weighted MR image shows an intra-axial heterogeneous left anterior temporal lobe lesion with small central hyperintense foci and a peripheral hypointense halo of hemosiderin (arrow), with the typical appearance of chocolate-covered popcorn. (B) Sagittal T2-weighted MR image of the cervical spine also shows an intramedullary lesion with the same imaging characteristics (arrowhead).
https://doi.org/10.1148/rg.240055 ©RSNA 2024
Extracting Information from Free-Text Radiology Reports
CT-based coronary artery calcium scoring (CACS) is a known predictor of major adverse cardiac events. As a guide for clinical decision-making, it can be used to reclassify patients with intermediate cardiovascular risk and some individuals who have borderline cardiovascular risk.
Nicola Fink, MD, Medical University of South Carolina, Charleston, and colleagues investigated the impact of plaque size and density on virtual noncontrast (VNC)-based CACS using photon-counting detector CT.
They also sought to provide safety net reconstructions for improved detection of subtle plaques in patients whose VNC-based CACS might otherwise be missed when compared with true noncontrast (TNC)–based CACS. Their research was published in Radiology: Cardiothoracic Imaging.
Compared with TNC-based calcium scoring, “VNC–based calcium scoring was limited for small and low-density plaques but improved using safety net reconstructions, which may be particularly useful in patients with low calcium scores who would otherwise be treated based on potentially false-negative results,” the authors conclude.
Read the full article, “Improved Detection of Small and Low-Density Plaques in Virtual Noncontrast Imaging–based Calcium Scoring at Photon-Counting Detector CT.” Follow the Radiology: Cardiothoracic Imaging editor on X @RadiologyCTI.
Explore the Vasty Deep
Hear from some of the most engaged minds in medical imaging AI as they present The Vasty Deep, a podcast series developed by the editorial board of Radiology: Artificial Intelligence. Top experts in medical imaging AI discuss hot topics in AI science, engage in discussions with leading researchers in the field, and hold thoughtful discussions about future directions in AI. New episodes are featured monthly, and past episodes are available now.