The Liver Imaging Reporting and Data System standardises acquisition, interpretation, reporting, and data collection for imaging examination in patients at risk of developing hepatocellular carcinoma. Although many studies have validated its use, showing its excellent diagnostic performance and reliability, its adoption is not universal[1,2]. Many radiologists still prefer free-text reporting and have cited unfamiliarity, lack of routine use by referring clinicians, perceived complexity, and per…
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.
-
Synovitis mediates the association between medial meniscal extrusion and subchondral bone denudation in knee osteoarthritis: Data from the FNIH OA biomarkers consortium
Knee osteoarthritis (KOA) remains one of the most prevalent musculoskeletal disorders worldwide, representing a primary cause of chronic pain and long-term disability among middle-aged and older adult populations [1]. Current epidemiological projections indicate a concerning rise in the global burden of KOA, with an estimated increase of 74.9 % (range: 59.4 %–89.9 %) by 2050, compared to 2020 figures [2]. Beyond its clinical impact, KOA constitutes a substantial driver of healthcare expenditures…
-
Development and validation of a radiomics model for lactate metabolism genes-based stratification and prognostic prediction in head and neck squamous cell carcinoma
Head and Neck Squamous Cell Carcinoma (HNSCC) represents a notably diverse group of malignant neoplasms that arise from the mucosal epithelium found in the oral cavity, pharynx, and larynx. This type of carcinoma accounts for nearly 90 % of all tumors located in the head and neck region [1]. Globally, there are over 830,000 new cases of HNSCC each year and 430,000 deaths; the 5-year survival rate has long hovered around 40 %-60 % [2]. Current standard treatment regimens primarily involve surgica…
-
Spectral CT-Based habitat imaging for the prediction of occult lymph node metastasis in resectable pancreatic ductal Adenocarcinoma: Pathological validation via collagen ratio
Pancreatic ductal adenocarcinoma (PDAC) is recognized as one of the most aggressive malignancies, with a dismal 5-year survival rate nearing 13% [1]. Early lymph node metastasis (LNM), along with aggressive tumor growth, represents a defining biological characteristic of PDAC and serves as a strong independent predictor of poor clinical outcomes [2]. Notably, N0 patients exhibit a significantly higher 5-year survival rate compared to N1/2 patients (57.1% vs. 25.0%) [3]. Neoadjuvant therapy is re…
-
Utilizing baseline multiregional MRI radiomics for prediction of tumor deposition and prognosis following neoadjuvant therapy in resectable rectal cancer
Colorectal cancer (CRC) is one of the most common cancers worldwide, with its incidence and mortality rates ranking the third and second among all malignant tumors in the world [1]. Epidemiological data indicate that distant recurrence constitutes the primary cause of mortality in rectal cancer cases [2]. Therefore, precise risk stratification for recurrence is crucial for enhancing survival outcomes. Tumor deposit (TD) refers to a nodule devoid of identifiable lymph node tissue or vascular/neur…
-
Relationship between resource utilization and diagnostic accuracy of large language models for efficient multimodal reasoning in radiologic image interpretation
Large language models (LLMs), exemplified by generative pre-trained transformers (GPT) such as ChatGPT (OpenAI) [1], have marked a significant advancement in artificial intelligence by demonstrating exceptional capabilities in natural language processing tasks [2–4]. These models have generated considerable interest due to their potential to transform medical practice [1,5]. Recent developments have introduced multimodal-LLMs that extend beyond text analysis [6–8].
-
Association between cognitive status and structural brain changes in Alzheimer’s disease: Clinical implication of lightweight deep learning-aided diagnosis
The complex brain changes involved in Alzheimer’s disease (AD) development constitute a high-dimensional nonlinear feature space where deep learning (DL) classification/diagnosis may be advantageous over classical non-learning methods. However, the practicality of DL remains under debate among healthcare professionals, largely because many models are computationally expensive and operate without explicit interpretability. This study aimed to construct a lightweight DL model to disclose the assoc…
-
Performance analysis of liver segmentation using nn-UNet TotalSegmentator: Focus on atypical livers, pathologies, and variants
Several diseases and treatments affect the liver and its volume, such as cirrhosis, hepatitis, liver metastases, hepatocellular carcinoma, and chemotherapy. Most abdominal CT examinations cover the entire liver volume, which could be used as a diagnostic imaging biomarker. However, traditional manual estimation is time-consuming and subject to errors and interobserver variability, which fosters the development of automatic segmentation solutions [1,2].
-
Ultrashort echo time MRI radiomics as a predictor of clinical outcomes in patellar tendinopathy: Insights from a large prospective clinical trial
To evaluate the predictive utility of radiomic features extracted from ultrashort echo time (UTE) MRI in comparison to conventional proton density (PD) sequences for short-term (24-week) and long-term (5-year) clinical outcomes in patients with patellar tendinopathy (PT) receiving exercise therapy.
-
Artificial intelligence-assisted CCTA for coronary stenosis detection: Diagnostic promise, methodological nuances, and directions for clinical translation
We read with great interest the recent meta-analysis by Yan et al., which comprehensively evaluates the diagnostic performance of coronary computed tomography angiography (CCTA)–based artificial intelligence (AI) systems for detecting ≥ 50 % coronary stenosis at both patient and vessel levels [1]. By rigorously adhering to PRISMA-DTA standards and disentangling patient-level from vessel-level evidence, the authors address a critical methodological limitation present in prior meta-analyses and pr…