Placenta accreta spectrum (PAS) disease is described as improper adhesion or invasion of trophoblast tissue to the myometrium and serosa, which is a form of disease that is extremely damaging to pregnant women in clinical practice [1]. Risk factors for PAS include placenta previa, multiple deliveries, advanced maternal age, and cesarean sections, with the latter having the most impact and raising the risk with the number of prior cesarean sections [1,2]. The incidence of PAS has been steadily ri…
We scan the top radiology sources so you don’t have to.
From AI breakthroughs to imaging trends, we serve up real-time radiology insights.
-
Performance of large language models for CAD-RADS 2.0 classification derived from cardiac CT reports
This study evaluates the performance of seven large language models (LLMs) in generating CAD-RADS 2.0 scores from cardiac CT reports, including all modifiers. The models, comprising both cloud-based and locally hosted solutions, were assessed for their ability to handle the complexity of CAD-RADS 2.0 classification, which includes plaque burden, high-risk plaque features, and ischemia. GPT-4o and Llama 3 70B demonstrated high accuracy (93 % and 92.5 %, respectively), while open-source models a…
-
Application of the Socioecological Model to Address Recruitment, Promotion, and Leadership Development of Women in Radiology
Women, who represent nearly 50% of medical school graduates, consistently comprise approximately 25% of radiology residency spots. Recruitment, promotion, and leadership development of radiologists from diverse backgrounds is important for continued growth of the field. Despite major radiological societies and journals championing this cause across all practice levels, efforts to improve diversity in the field have been limited. The socioecological model (SEM) has been used to address challenges…
-
Keeping AI on Track: Regular monitoring of algorithmic updates in mammography
Artificial intelligence (AI) algorithms interpreting screening mammography exhibit diagnostic performance that can match or supersede human performance [1]. Unlike traditional medical products, AI is more fluid and can change overtime [2]. Although seen as a fundamental advantage of machine learning, this fluidity carries inherent risks. Prospective clinical trials are essential to understand the impact of AI on screening workflows before their implementation [3]. However, once implemented into …
-
Diagnostic management pathways for workup of abnormal screening with digital mammography versus digital breast tomosynthesis
To assess the transition from digital mammography (DM) to digital breast tomosynthesis (DBT) screening, we compared diagnostic work-up type and frequency, work-up pathways, and time to resolution of abnormal screening DBT versus DM.
-
World's Largest Class Single Crystal Diamond Radiation Detector Opens New Possibilities for …
Orbray Co., Ltd. has developed a cutting-edge radiation detector based on its proprietary high-quality, large-diameter single-crystal diamond technology.
-
Mammography Study Reveals Mixed Results with Standalone AI Assessment for Post-Mastectomy Surveillance
While standalone AI interpretation offered over 10 percent higher sensitivity than radiologists for patients undergoing post-mastectomy surveillance mammography, it missed over 30 percent of breast cancers.
-
Brainomix stroke software granted FDA clearance
The U.S. FDA has granted 510(k) clearance to Brainomix for a feature of its 360 Stroke software.