Large Language Models (LLMs) are increasingly being evaluated for their ability to answer official radiology board-style examination questions. Understanding their accuracy, limitations, and potential applications in education is essential for assessing their utility in the field.
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.
-
Ultrasound dactylitis predicts bone erosion in early psoriatic arthritis: A longitudinal cohort study
Psoriatic arthritis (PsA) is a chronic progressive disease in which bone erosion is recognized as a hallmark destructive feature. Its exact prevalence is unknown, but estimates vary from 0.3 % to 1 % of the population. Previous studies have demonstrated that approximately 47 % of patients exhibit erosions within 2 years of diagnosis [1]. 87.6 % of PsA patients develop bone erosions within a decade of initial diagnosis, with a mean onset time of 6.8 ± 6.1 years [2]. The presence of bone erosions …
-
Prognostic value of functional MRI and liver function synergy in hepatocellular carcinoma patients receiving combined locoregional-systemic therapy: A multicenter scoring model
To develop and validate a prognostic model integrating pretreatment MRI features and clinical characteristics for hepatocellular carcinoma (HCC) patients undergoing transarterial chemoembolization (TACE) and hepatic arterial infusion chemotherapy (HAIC) combined targeted immunotherapy (TII). A weighted scoring system was developed to improve the model’s clinical utility.
-
Pelvic floor dysfunction: Anatomical characterization and functional imaging with MRI defecography
Pelvic floor dysfunction (PFD) is a common condition, affecting about 50 % of women in Western countries [1,2]. Clinical symptoms, including urinary and fecal incontinence and pelvic organ prolapse (POP), considerably impair quality of life [3]. The Pelvic Organ Prolapse Quantification (POP-Q) system provides a methodical framework for evaluating pelvic organ support and is endorsed by leading global organizations [4,5].
-
Comparison of central FLAIR hypointensity and central vein sign on FLAIR* in a diagnostic cohort
The central vein sign (CVS) is a neuroimaging biomarker in multiple sclerosis (MS) reflecting perivenular demyelination on pathology [1,2]. When standard T2-weighted (T2w) sequences are combined with susceptibility-sensitive MRI techniques, it is possible to visualize both the central vein and the T2w hyperintense lesions characteristic for MS. Techniques such as the FLAIR* enable concurrent visualization of the T2w hyperintense lesions and veins employing 3D T2w FLAIR and T2*-weighted (T2*w) 3D…
-
Image quality comparison between low-dose thin-slice deep-learning reconstruction and standard-dose thick-slice hybrid iterative reconstruction in pediatric abdominal CT
With technological advancements over the past decades, CT has become an indispensable tool for diagnosing and managing diverse diseases. Despite its tremendous contribution to modern medical practice, the widespread use of CT has raised concerns about the potential adverse effects of ionizing radiation exposure in the radiosensitive children [1], making it imperative to optimize radiation dosesin pediatric CT. Additionally, reducing slice thickness is necessary for detailed evaluations of small …
-
A CT-based radiomics model for classification of chronic pancreatitis: new biomarkers for diagnosis and severity staging
Chronic pancreatitis (CP) is an inflammatory disease characterized by progressive and irreversible damage to the pancreas. It imposes a significant burden on patients and healthcare systems due to severe complications, including persistent abdominal pain, diabetes, and exocrine pancreatic insufficiency (EPI) [1,2]. Modern pathophysiology models, especially mechanistic framework suggested by Whitcomb et al., depict CP as a dynamic continuum that starts with a single episode of acute pancreatitis,…
-
Automated 3D body composition analysis on chest CT scans for survival prediction in high-grade extremity soft tissue sarcomas
High-grade soft tissue sarcomas (STShg) of the extremities are rare cancers with a poor prognosis. Accurate staging at initial evaluation is crucial for determining optimal treatment. Current guidelines recommend systematic chest computed tomography (CT) scans during initial assessment. Recent advances in artificial intelligence (AI)-based imaging software now enable automatic, rapid volumetric assessment of body composition from CT scans. Our study aims to evaluate the predictive role of body c…