Latest AI and machine learning research in radiology for healthcare professionals.
OBJECTIVE: Parkinson's disease (PD) is a progressive neurodegenerative disorder characterized by tremor, rigidity and bradykinesia. Although central nervous system pathology has been extensively studied, peripheral musculoskeletal manifestations in PD remain comparatively understudied. METHODS: In this exploratory study, the characteristics of the gastrocnemius muscle were assessed using B-mode ul...
OBJECTIVE: To develop and evaluate a deep learning model capable of detecting ventriculomegaly on prenatal ultrasound images using a foundation model pre-trained specifically on ultrasound data. METHODS: A vision transformer-based ultrasound self-supervised foundation model with masked autoencoding (USF-MAE) was fine-tuned for binary classification of fetal brain ultrasound images as normal or ven...
The multi-scale organization of chromatin underlies gene regulation and cell identity, yet how nuclear architecture remodels during cell state transit...
Accurate brain parcellation in diffusion MRI (dMRI) space is essential for advanced neuroimaging analyses. However, most existing approaches rely on a...
BACKGROUND: Lumbar disc herniation (LDH) is a major cause of low back pain and radicular leg pain. Percutaneous endoscopic lumbar discectomy (PELD) is...
This review explores the application and limitations of ultrasound elastography (USE) in the pediatric population, addressing its diagnostic value acr...
BACKGROUND: Accurate segmentation of acute ischemic stroke (AIS) lesions on neuroimaging is essential for diagnosis, treatment decision-making, and pr...
Body composition (BC) is a key determinant of metabolic risk, treatment tolerance, and long-term outcomes. The distribution of skeletal muscle, viscer...
Predicting pathological complete response (pCR) to neoadjuvant immunochemotherapy in non-small cell lung cancer (NSCLC) is clinically important yet re...
BACKGROUND: Conventional clinical scoring systems and contrast-enhanced computed tomography (CECT) interpretation provide limited accuracy in predicti...
OBJECTIVES: To evaluate the diagnostic performance of the large language model (LLM) Gemini 2.5 for cholesteatoma detection using histopathology as th...
BACKGROUND: Artificial intelligence (AI) detection tools for intracranial hemorrhage (ICH) are increasingly integrated into radiology workflows. In re...
BACKGROUND: Large language models (LLMs) require specialized methodologies to quantify model confidence for safe deployment in health care systems; ho...
Low-Dose Computed Tomography (LDCT) is a widely used imaging modality to perform CT examinations with a reduced radiation exposure to patients, but it...
BACKGROUND: Accurate diagnosis of lacunar stroke in the acute setting is challenging and often depends on MRI or clinical suspicion. CT perfusion (CTP...
RATIONALE AND OBJECTIVES: Thyroid cancer, the fastest-growing endocrine malignancy, is shifting from morphological evaluation to molecular-functional ...
Automated segmentation of cardiac magnetic resonance (CMR) imaging is integrated into clinical workflows, yet comparative performance across vendor AI...
PURPOSE: Blood clot volume (BCV), defined as the total three-dimensional (3D) volume of the thrombus on computed tomography angiography (CTA), is an o...
BACKGROUND: Deep learning integrated with ultrasound systems may assist in predicting difficult airway, a life-threatening complication in anesthesia....
OBJECTIVES: To develop a nomogram model combining ultrasound radiomics and clinical features and to evaluate its predictive value for pathological inv...