Articles tagged with Radiology
A specialized AI model, AMIR-GPT, has been developed to improve radiology guideline alignment, outperforming general purpose models in 33.3% of test responses. However, the model's performance varied across performance bands, and qualitative review revealed limitations, such as omissions and deviations from standard recommendations.
A Chinese study reports a 100% technical and clinical success rate for robot-assisted brain angiography, with median procedure times 11 minutes shorter than manual angiography. No added radiation or complications were observed, showcasing the feasibility and safety of the YDHB-NS01 system
Researchers developed predictive AI models that identified patients at risk of intimate partner violence from their medical records, years before they enrolled in care. The models achieved high accuracy and could detect IPV up to four years before patients sought care.
The NRG-LU005 trial found that immunotherapy atezolizumab did not improve survival for patients with limited-stage small cell lung cancer when added to chemoradiation. Twice-daily radiation therapy, however, was associated with improved survival in this population.
A Chinese Neurosurgical Journal study developed a radiomics-based machine learning model to identify high-risk patients with traumatic brain injury who require emergency decompressive surgery. The model accurately distinguished patients who later required secondary surgery, suggesting its potential to complement clinical judgment.
A study found that radiologists who reviewed imaging tests twice after AI flagged them as abnormal were 53% less likely to be held liable in court compared to those who reviewed once. This suggests that changes to radiologist workflow could reduce legal risk, but may also come with increased costs.
Artificial intelligence can complement human expertise to improve radiology workflows and patient care. The JACR Focus Issue on AI in Workflow Optimization explores the integration of AI technology to enhance efficiency and deliver better care.
The Society of Interventional Radiology has published new practice guidance for treating chronic pelvic pain in women with venous-origin disorders, emphasizing interventional radiology's role in care. The guidance provides evidence-based recommendations on diagnosis, treatment options, and imaging.
The two organizations are expanding their collaboration to improve care for neurodegenerative disease, prostate cancer, and metastatic liver tumors through enhanced imaging and interventional technologies. This expanded partnership aims to bring more precise, less invasive, and personalized treatment approaches to patients.
A new JACR focus issue explores alternative approaches to resident education, radiology residency applications, and investing in pre-clinical medical education. The study aims to spark meaningful dialogue around how radiology education is valued, supported, and delivered amidst economic challenges.
A study published in Radiology found that photon-counting CT reduced radiation exposure by 66.34% and improved image quality compared to conventional CT in lung cancer patients. The technology also showed fewer adverse reactions, including contrast-induced acute kidney injury.
Researchers provide radiation oncologists with practical guidance to identify and protect female sexual organs during pelvic cancer treatment. The study establishes a shared, standardized approach to identifying the bulboclitoris, enabling clinicians to measure radiation dose to these tissues.
A new study discovered two previously unidentified fat distribution types associated with extensive gray matter atrophy and accelerated brain aging in men and women. Individuals with 'pancreatic-predominant' and 'skinny fat' profiles showed increased risk of neurological diseases, cognitive decline, and brain health issues.
A new oral contrast agent significantly improves visualization of inflammatory bowel disease (IBD) or cancer within the abdomen, according to clinical trial data. The dark borosilicate agent reveals previously impossible-to-detect findings, including small bowel tumors and subtle inflammatory conditions.
The Society of Interventional Radiology's Annual Scientific Meeting will showcase nearly 400 oral presentations and 120 poster presentations highlighting transformative advancements in minimally invasive medicine. SIR 2026 aims to improve patient care through innovative image-guided therapies.
NEJM Clinician curates highly relevant clinical insights from over 150 peer-reviewed journals to give physicians clear guidance without the noise. The weekly publication delivers summaries and commentary in a concise, 30-minute read, helping healthcare providers stay informed and confident in their decisions.
A new AI model can accurately identify brain abnormalities in MRI scans for various conditions, including stroke, multiple sclerosis, and brain tumors. The model can also triage scans, increase reporting speeds, and support clinical decision-making by suggesting findings to radiologists.
A special issue of the Journal of the American College of Radiology highlights the transformation of lung cancer from a feared and stigmatized disease to one that is increasingly understood as chronic and treatable. Advances in screening, therapeutics, and survivorship have improved outcomes for patients.
The 9th IOF Asia-Pacific Bone Health Conference will bring together healthcare professionals, researchers, and policymakers to exchange knowledge and shape the future of bone health across the region. The conference will feature keynote lectures, sponsored sessions, and a launch of the IOF Asia-Pacific Regional Audit 2025.
Researchers developed a deep learning model to measure adrenal gland volume on existing CT scans, identifying the first imaging biomarker of chronic stress. The AI-derived biomarker correlates with validated stress questionnaires, cortisol levels, and future cardiovascular outcomes.
The new system can reveal early cancers, lung disease, hidden material defects and changes in porosity without multiple exposures or complex mechanical movement. This method produces low-dose and faster images, lowering patients' radiation dose and making clinical translation feasible.
Researchers at UCSF found distinctive brain patterns in children with sensory processing disorder, which could help clinicians refine treatments for tantrums and emotional volatility. The study suggests that over-responsive children's brains dial up inward-focused networks to gain self-control.
Researchers developed an AI model that outperforms radiologists in detecting hidden objects on chest scans, particularly for cases of foreign body aspiration. The model achieves high precision and recall rates, helping doctors diagnose complex conditions more reliably.
Researchers have developed a low-cost approach, called ComSLI, that can visualize the orientation and organization of tissue fibers at micrometer resolution. This enables detailed mapping of neural pathways and fiber appearances in various tissues, including brain samples from patients with neurological disorders like Alzheimer's disease.
The Center for Computational and AI-enabled Imaging Sciences brings together experts to develop AI-powered medical imaging applications that integrate information from different imaging types. This may include identifying previously unknown early indicators of disease onset.
Researchers at Stanford Medicine have created a new cell-sorting device that uses electromagnetic levitation to separate different types of cells, including cancer cells and live cells from dead cells. The device can precisely direct the movement of cells without attaching fluorescent labels or exposing them to harsh chemicals.
Researchers are building an AI-powered database of MRI and CT images to track disease progression and measure patient response to treatments. The database will provide a standardized toolkit for extracting precise imaging biomarkers, enhancing the accuracy of organ measurements and improving treatment choices.
The collaboration aims to deliver high-quality, timely care by leveraging the latest imaging systems and AI tools. This will enable more precise diagnoses with shorter wait times, driving effective treatment across all service lines.
A new study examines the radiology department's experience during a mass casualty terror attack in southern Israel. Researchers found that rapid staff mobilization, versatile imaging resources management, and AI-enabled safety checks were crucial in guiding clinical decisions.
Researchers at Sylvester Comprehensive Cancer Center are pioneering innovative approaches to treating complex movement disorders with advanced imaging and radiosurgery techniques. The new era of functional radiosurgery enables precise treatment without invasive procedures.
Researchers from University of Miami Miller School of Medicine will showcase their study results at the annual conference. The presentation focuses on advancements in cancer treatment and patient care.
The PRISM trial will examine the impact of AI on mammogram accuracy and patient experience, with hundreds of thousands of mammograms analyzed. The study aims to understand whether AI enhances cancer detection by radiologists or leads to more false alarms.
A study by Columbia University researchers found that soccer heading causes damage to the brain's cerebral cortex, leading to cognitive deficits. The study used a new imaging technique to identify areas most damaged by repeated impacts from heading a soccer ball.
The Society of Interventional Radiology has published new practice guidance for creating percutaneous arteriovenous fistulas for dialysis access. The guidance emphasizes the importance of interventional radiologists in providing durable hemodialysis access to improve patient outcomes.
A new study from Mizzou's College of Veterinary Medicine analyzed the effects of radioactive iodine therapy on thyroid cancer in dogs. The research found that tailoring the dose of radiation more precisely for each dog could improve outcomes and potentially lead to more targeted care.
Dr. Wendaline M. VanBuren has been awarded a grant to develop an AI-powered model for diagnosing and treating adenomyosis and endometriosis. The study aims to enhance detection, treatment planning, and patient outcomes.
A global study surveyed 14,000 patients across 43 countries, finding that those in poorer health were more likely to reject AI. Patients preferred explainable AI and wanted clinicians to make final decisions.
Researchers are using total-body PET imaging to investigate the relationship between long COVID symptoms and activated immune T cells, as well as blood vessel damage. The goal is to gain a better understanding of how these processes are related and how they contribute to long COVID symptoms.
Dr. Catheryn Yashar, a renowned radiation oncologist, has been appointed president-elect of the American Society for Radiation Oncology (ASTRO). She will champion innovative radiation therapies and advance health policy reform to improve cancer care outcomes.
Mount Sinai will provide orthopedics, sports medicine, emergency medicine, and musculoskeletal radiology services to world's top tennis stars. The institution has partnered with the USTA for 13 years, promoting health and wellness, preventing injuries, and catering to diverse populations.
A new minimally invasive procedure, genicular artery embolization, has been shown to relieve chronic knee pain caused by osteoarthritis in over 60% of patients. The procedure reduces inflammation and blood flow to joints, providing significant improvements in knee pain and stiffness.
A new study suggests that subtly adjusting the angle of the foot during walking can reduce knee pain caused by osteoarthritis and slow its progression. By tailoring each patient's foot angle to their unique walking pattern, experts believe an easy and fairly inexpensive way to address early-stage osteoarthritis may be found.
Scientists investigated how Pr content impacts perovskite oxide crystal structure and oxygen exchange. Higher Pr content led to disorder phase transition and improved orbital hybridization, accelerating oxygen exchange. The discovery provides guidance for designing high-performance SOEC anodes.
Experts suggest a clear separation of roles between AI systems and radiologists to overcome challenges such as cognitive biases and misaligned incentives. A framework for role separation is proposed, including three models that can be adapted to specific needs, enabling institutions to implement hybrid approaches.
The tripartite agreement has driven $100M in NIH funding, 217 invention disclosures, 136 U.S. patents, and 31 international patents, accelerating MRI technology adoption and improving patient care. Technologies developed through this collaboration have shaped multiple FDA-approved products used worldwide.
The International radiology consensus outlines best practices for post-COVID CT imaging, including standardized terminology and low-dose protocols. The guidelines aim to standardize the indications for chest CT and improve patient management.
Researchers found Galectin-1, a sugar-binding protein, plays a critical role in helping hepatocellular carcinoma cells resist thermal ablation and thrive after being treated with high heat. Blocking Gal-1 can make thermal ablation more effective and reduce the risk of recurrence.
A new study demonstrates that retrieval-augmented generation can eliminate hallucinations in clinical LLMs while protecting patient privacy. The RAG-enhanced model responds significantly faster than cloud-based systems, delivering safer results without compromising data security.
Researchers at the University of Illinois Urbana-Champaign have developed a new non-invasive MRI approach that visualizes brain metabolism and detects metabolic alterations associated with brain diseases. The technique uses magnetic resonance spectroscopic imaging to provide insights into brain function and disease processes.
A new survey conducted by Ohio State University Wexner Medical Center found that only 1% of men are concerned about bone density, with cancer and heart disease being top concerns. Men can build back bone density through exercise, nutrition, and lifestyle changes, and early intervention can prevent deadly fractures.
A landmark review highlights how diabetes alters bone microarchitecture and increases fracture risk in people with type 2 diabetes, despite normal or elevated bone mineral density. The authors advocate for updated diagnostic tools, including a revised TBS algorithm, to more accurately reflect bone quality in individuals with central ob...
A study published in Radiology found that CT colonography is more effective and cost-effective than stool DNA testing for colorectal cancer screening, reducing incidence by 70-75% compared to 59%. CT colonography is also a cost-saving option with an estimated cost of $9,000 per QALY gained.
A new AI system has been developed that improves radiology productivity and accuracy, offering a breakthrough solution to the global radiologist shortage. The tool boosts efficiency by up to 40% without compromising accuracy and flags life-threatening conditions in real-time.
A new quality initiative at Mass General Brigham improved radiologists' follow-up imaging recommendations, reducing diagnostic errors and potential harm. The initiative resulted in a 44% reduction in imaging recommendations and increased actionability of recommendations, leading to better patient outcomes.
Patients with breast cancer detected through routine screening mammography have improved clinical outcomes, including lower odds of advanced stage breast cancer and death. In contrast, symptom-detected cases were more frequent in older women and had higher mortality rates.
A new study reveals that fine-tuned large language models (LLMs) greatly improve error detection in radiology reports, outperforming other NLP tools. The LLMs successfully identify various types of errors, including transcription and directional mistakes, providing a promising solution for medical proofreading.
A new study published in Radiology found that abbreviated breast MRI is an effective screening method for women with extremely dense breasts, detecting cancer while reducing scan times by up to 80%. The abbreviated protocol retains a high level of diagnostic accuracy comparable to the full protocol MRI.
A new AI system, MedGaze, is designed to emulate how radiologists visually interpret chest X-rays. By replicating expert attention, it helps train future specialists and improve the efficiency of hospitals through better workflow management.
Dr. Tarek Hanna joins UMSOM from Emory University School of Medicine with expertise in emergency and trauma imaging, clinical operations optimization, and faculty development. He will advance clinical excellence and expand radiology services across central Maryland.
Researchers at the University of Chicago Medicine discovered a new phenomenon where high doses of radiation cause growth in existing metastatic tumors. The 'badscopal effect' is attributed to increased production of amphiregulin, which weakens the immune system and makes cancer cells more resistant.