To develop and test machine learning (ML) models using computed tomography angiography to identify the intracranial aneurysm (IA) responsible for subarachnoid hemorrhage (SAH) accurately in patients with multiple saccular IAs and to determine whether these models outperform traditional predictive markers.
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.
-
Transformer-based multimodal fusion model predicts early hematoma expansion in spontaneous cerebral hemorrhage: A multicenter study
Spontaneous intracerebral hemorrhage (sICH) represents around 10–15 % of all strokes. Approximately 25 % of patients show an increase in hematoma volume during follow-up non-contrast computed tomography (NCCT) performed 6–24 h after the initial scan, a phenomenon known as early hematoma expansion (EHE) [1–3]. This phenomenon significantly increases the rates of disability and mortality in patients. Although treatment strategies such as intensified blood pressure management, hemostatic agents, an…
-
Multiparametric breast MRI to problem-solve mammographically detected suspicious calcifications
Mammographic calcifications account for 31 % of recalled lesions in digital screening mammography, representing 0.4–2 % of all women undergoing mammographic screening[1,2]. However, approximately 50–80 % of these lesions are benign [2,3]. When malignant, about 66 % are confirmed as ductal carcinoma in situ (DCIS) [4]. As such, mammographic calcifications account for about 80 % of DCIS diagnoses [5,6]. DCIS is the most controversial breast malignancy diagnosed in women, as pure DCIS is non-lethal…
-
Machine learning outperforms deep learning in adhesive capsulitis diagnosis: a clinical-radiomics model bridging PD-T2 MRI and multimodal data fusion
Adhesive Capsulitis of the Shoulder (ACS) is a chronic inflammatory condition characterized by capsular fibrosis, thickening, and restricted mobility. Early diagnosis remains challenging due to the limited sensitivity of traditional imaging and symptom-based methods.
-
Real-life performance of AI-aided radiologists, emergency physicians and two AI solutions for diagnosing bone fractures in appendicular skeletal trauma
Appendicular skeletal trauma is the most frequent reason for admission to emergency departments, and X-ray is the first imaging modality [1–4]. Artificial intelligence (AI) holds potential to improve patient management throughout their journey in emergency departments [5]. Notably, the development of AI solutions based on deep convolutional neural networks (DCNNs) for detecting bone fractures has attracted considerable attention given the prevalence of appendicular skeletal trauma. However, AI c…
-
Erratum to “Value of rectal MRI prior to endoscopic submucosal dissection (ESD): An exploratory study” [Eur. J. Radiol. 192C (2025) 112400]
The publisher regrets that the printed version of the above article contained a number of errors. The correct and final version follows. The publisher would like to apologise for any inconvenience caused.
-
Prognostic value of coronary CTA-based AI plaque quantification in patients undergoing transcatheter aortic valve implantation
Coronary artery disease can be concomitantly evaluated as part of the pre-transcatheter aortic valve implantation (TAVI) CT angiography (CTA). More recently it has been possible to perform quantitative plaque analysis on coronary CT angiography (CCTA). In this study, we aimed to assess the prognostic value of quantitative plaque volumes using Artificial Intelligence Quantified Coronary Plaque Analysis (AI-QCPA) on pre-TAVI CTA.
-
Deep learning and transformer-based feature fusion of conventional MRI for differentiating spinal osteolytic bone metastases and multiple myeloma
To develop a deep learning model utilizing conventional MRI sequences integrated with Transformer-based feature fusion to differentiate spinal osteolytic bone metastases (OBM) from multiple myeloma (MM).
-
Corrigendum to “Keeping AI on Track: Regular monitoring of algorithmic updates in mammography” [Eur. J. Radiol. 187 (2025) 112100]
The authors regret two errors in the published version of this article.