Articles tagged with Radiology
Researchers found that a mobile interventional stroke team treated patients faster and with better outcomes than standard care. Patients treated by the MIST team were more likely to be functionally independent at 90 days post-stroke.
A retrospective study of over 3,900 patients found that warming iohexol 350 contrast media did not significantly reduce adverse reactions or extravasations. The results suggest that maintaining the agent at room temperature is non-inferior to warming it to body temperature before injection.
King's College London researchers have automated brain MRI image labelling by leveraging radiology reports, enabling the labelling of over 100,000 exams in less than half an hour. This breakthrough tackles a bottleneck in deep learning image recognition tasks for complex datasets like MRI.
A new AI algorithm developed by TUM and Imperial College London can detect pneumonia in pediatric x-ray images while maintaining patient privacy. The algorithm uses federated learning, secure aggregation, and differential privacy to keep data onsite and prevent individual identification.
A new AI algorithm accurately predicts lung cancer risk from low-dose CT scans, outperforming established models and human clinicians. The algorithm may aid in optimizing follow-up recommendations for lung cancer screening participants.
A retrospective study found that CT features can help select patients with stage IA non-small cell lung cancer for sublobar resection. Peritumoral interstitial thickening and pleural contact were independently associated with pathologic lymphovascular invasion, predicting recurrence-free survival after the procedure.
A new AI tool developed by NYU Langone Health can accurately predict which COVID-19 patients are most likely to develop life-threatening complications within four days, using chest X-ray images and other clinical data. The tool achieved an 80% accuracy rate in predicting patients who required intensive care or died from their infections.
The American Roentgen Ray Society (ARRS) honors all members with the 2021 ARRS Gold Medal for their selfless service on the frontlines of the COVID-19 pandemic. The award recognizes their distinguished contributions to radiology and its impact on patient care.
A study found that a chest x-ray scoring system can predict patient outcomes, including death, intubation, and chronic renal replacement therapy, in COVID-19 patients with high pretest probability or rapid test results. The scoring system was accurate and reliable, even among junior residents.
A study found that radiology residency program directors will likely rely on USMLE Step 2 Clinical Knowledge scores as an objective metric for applicant screening. Program directors are unsure whether to require Step 2 CK scores at application or before interviewing applicants.
A large randomized controlled trial found that low-dose IV contrast-enhanced 2-millisievert CT is comparable to conventional-dose CT for diagnosing right colonic diverticulitis. The study included 3,074 patients and demonstrated similar diagnostic performance between the two groups.
A study published in Radiology found that chest CT scans can assess body composition and predict mortality risk in people with chronic obstructive pulmonary disease (COPD). Higher intermuscular fat was linked to higher mortality rates, while subcutaneous adipose tissue was associated with lower risks.
The COVID-19 'Safer at Home' order led to a 40% decline in total radiology orders, with outpatient volumes decreasing by 67% and ED volumes declining by 21%. Subspecialty imaging saw significant declines, especially in dexa and breast imaging.
A study reviewed 286 patients who underwent ICD implantation between 2013 and 2016, assessing appropriateness based on AUC. The results showed a high rate of appropriate ICD implantations and very low prevalence of rarely appropriate implantations.
A large-scale study found that the introduction of RADLogics' AI-Powered solution into radiology workflow reduced report turnaround time by an average of 30 percent, equivalent to 7 minutes per case. The study also showed a significant improvement in productivity and report accuracy.
Researchers found that people searching for objects in 3D image stacks are less successful than those searching for the same in single 2D images. This is due to a bottleneck in human vision and cognition, where humans under-explore 3D search areas and rely on peripheral visual processing.
Genicular artery embolization (GAE) significantly reduces inflammation, improving quality of life for people with moderate to severe knee pain. The procedure provides long-term, safe pain relief, with benefits seen as early as three days post-treatment and lasting up to one year.
A new study found that hysterectomies are used more frequently to treat significant postpartum bleeding than uterine artery embolization, a minimally invasive procedure. The procedure resulted in longer hospital stays and higher costs.
Researchers have developed Immuno-PET, a technique that visualizes changes in different cancer receptors within tumors during targeted therapies, enabling early evaluation of treatment effectiveness and prediction of response. This can help physicians select the most effective treatment for patients with cancer.
A new study published in the American Journal of Roentgenology found that CT colonography with a 10 mm threshold is the most effective and efficient non-invasive screening test for colorectal cancer prevention and detection. This method targets advanced neoplasia while reducing unnecessary colonoscopies compared to other tests.
Swollen lymph nodes after COVID-19 vaccination can be managed with proper documentation and follow-up care. Imaging centers should document vaccination information to avoid unnecessary biopsies.
A machine learning algorithm helps differentiate between benign and premalignant polyps in CT colonography data, with a sensitivity of 82% and specificity of 85%. The findings suggest a role for machine learning-derived algorithms in boosting the effectiveness of CT colonography as a screening tool for colorectal cancer.
Radiological images confirm that COVID-19 can trigger autoimmune reactions leading to rheumatoid arthritis flares and other musculoskeletal disorders. Imaging helps explain prolonged symptoms and directs patients to the right physician for treatment.
Sanjeev Bhalla, MD, has been recognized as the 2021 ARRS Distinguished Educator for his proven record of improving radiological education. He is a dedicated teacher and innovator in medical imaging.
Research suggests that radiologists' diagnoses of lumbar spine pain generators are highly accurate when using patient-reported symptom information from brief questionnaires. The study found almost perfect agreement between radiologists' diagnoses using symptom information and those without it, improving diagnostic certainty levels.
Radiologists question the status quo to spark positive dialog and improve patient care. Featured articles debate the use of physician extenders and incorporation of AI algorithms into daily practice.
Drs. Kelil and Jaimes will investigate personalized breast cancer risk assessment and fetal diffusion tensor imaging to improve conventional risk prediction models and characterize normal brain development in fetuses with congenital heart disease. Their studies aim to harness cutting-edge MRI processing tools to correct for fetal motion.
A review article highlights the need for improved understanding and prevention of adverse events in interventional radiology. Most procedures are successful, but complications can lead to significant morbidity and increased risk of harm.
Research suggests that up to one-third of adult women with forearm fractures, particularly non-displaced ulnar fractures, may be victims of intimate partner violence. The study's findings highlight the need for radiologists to screen for intimate partner violence in these cases.
A new AI algorithm, DeepCOVID-XR, has been developed to detect COVID-19 on chest X-ray images. It outperformed thoracic radiologists in accuracy and speed, analyzing images 10 times faster and with a 1-6% higher accuracy rate.
A study by University of Utah researchers found that experienced radiologists can miss clear abnormalities when looking for one specific issue, highlighting the limits of human cognition. The experiment demonstrates that years of experience don't guarantee detection of critical findings.
A review of academic studies found that nearly 20% of COVID-19 patients exhibit only gastrointestinal symptoms. Radiologists should be aware of signs such as bowel inflammation and air within the bowel wall, which could indicate advanced disease or COVID-19 infection.
A deep learning system has been developed to detect cerebral aneurysms with a sensitivity of 97.5%. The algorithm detected 633 of the 649 cerebral aneurysms and found eight new aneurysms overlooked by human readers.
A panel of experts recommends imaging for hip and knee steroid injections to mitigate joint collapse and total replacement risks. Current evidence is insufficient to draw a definitive conclusion, highlighting the need for further research.
Researchers found in situ pulmonary artery thrombosis associated with radiation therapy has unique imaging characteristics and does not typically embolize. The study identified 27 patients with PAT after RT, highlighting the importance of radiologist awareness for accurate diagnosis and management.
Dual-energy CT enhances radiologist confidence in emergency department imaging studies, leading to reduced downstream imaging and associated costs. This technology resulted in a decrease of recommended follow-up imaging examinations totaling $52,991.53-61,598.44.
A new AI algorithm developed by researchers at the University of Central Florida can accurately diagnose COVID-19 pneumonia in lung CT scans with up to 90% accuracy. The algorithm also distinguishes COVID-19 cases from influenza and other diseases, overcoming current testing challenges.
A deep learning model can quickly identify large vessel occlusions, which account for a significant proportion of ischemic strokes. The algorithm's sensitivity was found to be 100%, outperforming single-phase CTA in detecting these critical blockages.
Patients with COVID-19 show a higher prevalence of thromboembolism and solid-organ infarction compared to those without the disease. Hypercoagulability is suggested by increased findings in abdominal and extremity macrothrombi, necessitating radiologists to consider COVID-19 diagnosis.
The American Roentgen Ray Society will convene its 2021 Annual Meeting as an all-virtual event from April 18-22, 2021. The meeting will offer world-class educational activities led by experts in radiology across various subspecialties.
A study found that minimally invasive ultrasound-guided carpal tunnel release improves hand function and reduces discomfort in patients with carpal tunnel syndrome. The procedure demonstrated a safe, effective, and less invasive alternative to traditional open or endoscopic surgery.
Researchers used modest data and basic engineering AI to solve complex MRI appointment no-shows. The study found a 17.2% improvement in no-show rates after implementing phone call reminders for high-risk patients.
UT Dallas researchers developed a proof-of-concept model that quantifies thermal characteristics of breast cancer, detecting temperature differences and increased blood flow. The study aims to improve digital infrared thermal imaging for monitoring breast cancer and its treatment.
A new study shows that the Ellipsys Vascular Access System reduces the time before patients with kidney failure can start lifesaving dialysis treatments, while requiring fewer secondary procedures. The technology uses a small needle puncture and catheter to create an endovascular AVF, reducing the average time from fistula creation to ...
Despite significant increases in radiology research funding since 1994, citation rates have remained unchanged, with no association found between funding and citations. Funding sources, including federal sponsorship and nonprofit foundations, were primarily utilized.
Researchers at Karolinska Institutet have found that one AI algorithm is as accurate as the average radiologist in identifying breast cancer from mammograms. The study compared three AI algorithms and showed significant differences between them, with one outperforming others and rivaling human detection accuracy.
A study found that electronic consultations between primary providers and radiologists improved patient care by reducing unnecessary imaging tests. The platform provided a secure method for PCPs to ask specialist questions, promoting collaboration and improving outcomes.
A new study published in Radiology found an alarming rise in intimate partner violence (IPV) during the COVID-19 pandemic, with a significant increase in physical injuries and severe signs of abuse. The study suggests that victims may have delayed seeking care due to fear of COVID-19.
A study found that 11.4% of second-opinion radiology reports were ignored by clinicians, with sonography and pediatrics having the highest rates. The cost of these ignored reports could be substantial, estimated at €53,700 or approximately $63,427.
A new study found a significant increase in domestic violence injuries during the COVID-19 pandemic, with more severe injuries reported despite fewer patients seeking help. The study suggests that fear of contracting infection and limited access to ambulatory sites may be preventing victims from reporting abuse.
A pilot study found that Snapchat improves diagnostic performance among radiology residents, who performed better on the platform than with traditional classroom screens. The results suggest a promising novel training method to enhance recognition of life-threatening imaging diagnoses.
The COVID-19 pandemic has had a substantial impact on private radiology practices, with examination volumes decreasing by 40%-90%. To mitigate losses, practices are adjusting service availability, staffing, compensation, and seeking additional revenues.
A study found that non-white patients with COVID-19 have more severe disease on chest X-rays, increasing the likelihood of adverse outcomes. Limited English proficiency and socioeconomic factors contribute to these disparities.
The study found that focusing on subjects less likely to remain in the program, such as smokers and those with negative low-dose CT exams, improves cost-effectiveness and maximizes societal benefits. Adherence increased progressively with higher Lung-RADS categories, and having smoked previously was a significant predictor of adherence.
A study found that cardiac CT exams can effectively screen for osteoporosis by measuring thoracic spine bone mineral density, which is strongly associated with fracture risk. This non-invasive method can guide preventive measures and treatment decisions without adding time or radiation to the exam.
The study highlights social media's benefits in Radiology, including educational content dissemination, professional networking, and collaboration. However, it also warns of challenges, such as maintaining patient privacy and avoiding e-professionalism.
The American Journal of Roentgenology is implementing an author-centered peer-review system to streamline the submission process and provide rapid initial decisions. The journal is also rapidly publishing accepted manuscripts as Online First, expediting timely research for radiologists and allied scientists.
A recent study published in Radiology found that prostate MRI quality is highly variable across institutions, with a significant impact on cancer detection and treatment outcomes. The study's findings suggest that improved standardization and training are needed to ensure consistent imaging results and better patient care.
A new case series published in Radiology examines the spectrum of imaging findings in children with Multisystem Inflammatory Syndrome in Children (MIS-C) associated with prior exposure or infection to SARS-CoV-2. The study identified a pattern of imaging findings including airway inflammation and pulmonary edema.
A new multi-institutional study found patterns of abnormal brain MRI findings in patients with severe COVID-19, including signal abnormalities in the medial temporal lobe and non-confluent multifocal white matter hyperintense lesions. The study suggests that imaging and neurological follow-up are crucial to evaluate prognosis.