A large-scale study found that patient pain upon arrival and placement in hallway beds are associated with poorer patient experience in EDs. On the other hand, receiving radiology studies generates more positive experience scores. Understanding these underlying factors can help improve patient outcomes and experiences.
A new radiology screening tool can help detect intimate partner violence (IPV) in patients, enabling healthcare providers to identify victims earlier. The study found that imaging studies and injury patterns differ between women who have reported IPV and those who have not.
A new study uses advanced lung MRI to detect regional blood flow abnormalities in children and adolescents with long COVID, which may explain persistent symptoms. The researchers found reduced blood flow patterns that correlated with fatigue symptom severity, suggesting a possible biological basis for ongoing symptoms.
A study found significant racial disparities in who received same-day diagnostic services and biopsies after abnormal mammogram findings, with Black women being less likely to receive same-day biopsies. Rural-resident patients were more likely to receive same-day diagnostic services than urban residents.
Researchers developed a robust AI model that automates segmenting of MRI images, reducing radiologist workload and improving consistency. The TotalSegmentator MRI model achieved high performance on various anatomical structures, with a Dice score of 0.839.
A study found racial and ethnic minorities are less likely to receive standard-of-care diagnostic imaging after abnormal screening mammograms compared to white patients. Minority groups were also less likely to have access to same-day biopsy services, despite similar availability of most diagnostic services.
Mayo Clinic is developing foundation models with Microsoft Research and Cerebras Systems to personalize patient care, accelerating diagnostic time and improving accuracy. These multimodal models integrate radiology images and genomic sequencing data to transform clinical diagnosis and treatment.
A Northwestern Polytechnical University team evaluated the performance of Gemini and GPT-series models across various medical tasks, finding strengths in report generation and lesion detection. The study highlights the potential of multimodal LLMs in alleviating clinician burden and integrating AI into clinical practice.
The study found a significant increase in late-stage breast cancer diagnoses among U.S. women, with annual percentage increases of up to 2.9% between 2004 and 2021. The researchers attribute the trend to factors such as lack of national screening programs, inconsistent guidelines, and increasing obesity rates.
Researchers found structural and functional alterations in specific brain regions of individuals with opioid use disorder, including increased global connectivity. Women in the group had smaller medial prefrontal cortex volume compared to men.
Priscilla Slanetz, a breast radiologist and professor at Boston University School of Medicine, has received the 2024 Marie Sklodowska-Curie Award for her outstanding contributions to advancing women in radiology. She is recognized for her clinical research, educational efforts, and leadership in promoting diversity and inclusion.
Researchers at the University of Bonn are developing an AI foundation model to improve radiology and detect Parkinson's disease earlier. The 'Re-Start PD' project aims to identify the condition before symptoms appear, with potential applications in diagnosis, treatment, and prevention.
A seminal life cycle assessment (LCA) study found that diagnostic services generate the equivalent of nearly 1,100 gas-powered cars annually, with CT scans accounting for the majority of GHG emissions. The team identified areas to reduce energy consumption and greenhouse gas emissions without compromising patient care.
Researchers introduce persistence barcodes, a tool that reduces diagnostic bias and uncovers subtle details in medical images. The method preserves key structural details, enabling clearer insights into the data.
A study published in Radiology found that radiologists and physicians who received local explanations from artificial intelligence (AI) systems performed better and made faster diagnoses than those who received global explanations. The researchers also found that AI advice was trusted more quickly when it provided local explanations.
A new approach using topological data analysis (TDA) enhances the reliability and reduces bias in AI systems used for medical diagnosis in radiology. TDA captures intricate features and provides a holistic view of medical images, leading to more accurate diagnoses and equitable patient care.
The Healthcare AI Challenge enables healthcare professionals to evaluate and compare AI solutions for their effectiveness in various clinical situations. By crowdsourcing input from experts, the challenge aims to create continuous and reliable expert evaluations of AI technologies in medicine.
Radiologists who had access to questionnaire information during MRI interpretation achieved a near statistically perfect agreement with spine specialists. This improved diagnostic accuracy and confidence, avoiding diagnostic discrepancies between radiologists and spine specialists.
Researchers analyzed 48 studies on AI's effect on medical imaging workflows and found no significant efficiency gains. The success of implementation depends heavily on specific conditions and processes on site.
A new study published in the Journal of Vascular and Interventional Radiology found that genicular artery embolization (GAE) provides durable benefit to patients with osteoarthritis in the knees for at least 2 years. The procedure targets abnormal blood flow to reduce inflammation, quickly improving patients' pain.
A new study published in Radiology journal reveals that advanced 3D mammography detects breast cancer earlier and less often results in false positives compared to traditional digital mammography. This improved detection rate has significant implications for breast cancer diagnosis and treatment.
The study found that ChatGPT-4 Vision performed well on text-based radiology exam questions but struggled with image-related questions, achieving an accuracy of 65.3%. The model's performance varied across subspecialties and images, with limitations in interpreting certain types of radiologic images.
A uniform lexicon has been developed and endorsed by a multi-medical society panel to describe observations on ultrasound during the first trimester of pregnancy. The new terms aim to minimize bias, clarify findings, and respect patient preferences.
Researchers at Osaka Metropolitan University found that AI model GPT-4 outperformed a weaker version of the model and was on par with radiology residents in diagnosing musculoskeletal conditions. However, it struggled to match the accuracy of board-certified radiologists.
A commercial AI tool was effective in excluding pathology and had lower rates of critical misses on chest X-rays compared to radiologists. The study found that the AI tool could autonomously report more than half of all normal chest X-rays without decreasing standard of care.
A recent study published in Radiology found that solid lung nodules were present in approximately 42% of non-smoking adults, with prevalence increasing with age. The study suggests that current nodule follow-up guidelines may lead to unnecessary follow-up examinations for low-risk individuals.
A new deep learning model detects clinically significant prostate cancer on MRI with performance comparable to experienced abdominal radiologists. The model's prediction can be used as an adjunct to improve diagnostic performance and reduce false positives.
Despite progress, radiology's gender gap persists due to structural biases. RSNA's efforts have increased female representation in faculty and leadership positions.
The Special Report explores expert perspectives on deploying AI in radiology, emphasizing the need for trust, reproducibility, explainability, and accountability. Radiologists must be able to trust in AI systems' design and receive adequate training, while establishing clear guidelines regarding clinical accountability.
Children and young people are generally positive about AI's role in healthcare, with many believing it can improve their care and outcomes. However, they also emphasize the importance of human oversight, particularly when it comes to empathy and ethical decision-making.
The policy statement offers guidelines for institutions and medical professionals to weigh benefits and risks of imaging in emergency departments. It includes recommendations for deferring imaging in children transferred to pediatric referral centers and using shared decision-making strategies when multiple reasonable choices exist. Th...
A study published in Radiology found that brain connectivity on MRI scans can predict the progression of brain atrophy in patients with mild Parkinson's disease. The researchers used MRI data to generate a map of the brain's neural connections, which showed potential in predicting gray matter atrophy accumulation over time.
A study published in Radiology found that AI significantly improved breast cancer detection and reduced false-positive findings. The AI system detected more cancers while lowering the rate of unnecessary recalls, reducing radiologist workload by 33.4%.
A study published in Radiology found that low-level light therapy increased resting-state functional connectivity in patients with moderate traumatic brain injuries. The treatment showed improved brain connectivity within the first two weeks, but its long-term effects are still unclear.
A new study found that GPT-4 and Google Gemini performed poorly in breast imaging classification, with a high percentage of discordant assignments that could impact patient management. The researchers emphasize the need for regulation of these large language models in high-level medical scenarios.
Radiologists are proposing actions to reduce their department's greenhouse gas emissions and become more resilient to the effects of climate change. They suggest implementing a coordinated approach, establishing sustainability teams, and optimizing scanner usage to reduce emissions by up to 33% for MRI and CT scans.
A study found that GPT-4 matched the performance of radiologists in detecting errors in radiology reports, with an accuracy rate of 82.7%. The use of GPT-4 resulted in lower mean correction cost per report than the most cost-efficient radiologist.
Researchers developed an AI algorithm to identify normal mammograms and ran a simulation on patient data, revealing that AI can reduce unnecessary testing while maintaining cancer detection rates. The study suggests that AI can help doctors focus on more questionable scans, reducing false positives and improving workflows.
Researchers found that doctors can confidently skip 50% of biopsies by combining MRI-based prostate imaging reporting and data system scores with prostate-specific antigen density testing. The study suggests that this approach can decrease patient harm and healthcare costs associated with unnecessary biopsies.
Researchers have developed a new AI model, AsymMirai, to predict 5-year breast cancer risk from mammograms. The model performs almost as well as the state-of-the-art Mirai, but with an interpretable reasoning process, making it a valuable adjunct to human radiologists.
A new study published in Radiology found that coronary artery calcium scoring can identify patients with a low risk of heart attacks or strokes. Patients with a zero coronary artery calcium score showed very low risk of major adverse cardiovascular events, suggesting they may not require invasive coronary angiography.
Researchers warn that AI tools used in radiology contribute to greenhouse gas emissions through energy consumption and data storage. To minimize these impacts, experts recommend sharing resources, selecting sustainable hardware, and using data compression techniques.
A new study published in Radiology found that ultrahigh-spatial-resolution photon-counting detector CT improved the assessment of coronary artery disease, allowing for reclassification to a lower disease category in 54% of patients. This technology has the potential to improve patient management and reduce unnecessary interventions.
A new study published in Radiology found that annual breast cancer screening beginning at age 40 and continuing until 79 results in the highest mortality reduction. The study analyzed Cancer Intervention and Surveillance Modeling Network (CISNET) estimates and showed that annual screening reduces breast cancer deaths by 41.7%.
The American College of Radiology has issued a joint statement with four other radiology societies to address the development and use of AI tools in radiology. The statement emphasizes the need for increased monitoring of AI utility and safety, advocating for collaboration among developers, clinicians, purchasers, and regulators.
Experts recommend increasing the use of intravascular ultrasound (IVUS) in lower extremity revascularization procedures to optimize outcomes and reduce complications. The technique provides detailed information about vessel walls, plaque composition, and blood flow characteristics, enabling more accurate diagnosis and treatment planning.
A new article in Radiology discusses AI applications for musculoskeletal radiology, highlighting its potential to improve complex tasks like disease prognostication and prediction of clinical outcomes. However, challenges such as data quality and multi-institutional collaboration need to be overcome for successful implementation.
A large-scale study found that low-dose CT screening increases the 20-year survival rate of lung cancer patients from 18.6% to 81%, with Stage I cancers having an even higher long-term survival rate of 95%. Early detection through annual screening can effectively cure lung cancer in the long term.
A new study published in Radiology shows that patients diagnosed with lung cancer via CT screening have a 20-year survival rate of 81 percent, significantly higher than the average five-year survival rate for all lung cancer patients. Early detection through routine screening can lead to a cure if found early.
Researchers tested the feasibility of using locally run LLMs like Vicuna-13B to label key findings in chest X-ray reports while preserving patient privacy. The results showed moderate to substantial agreement with non-LLM computer programs, suggesting that these models can be a viable option for AI research.
A new AI model integrates imaging and non-imaging patient data for improved diagnostic performance on chest X-rays. The multimodal model outperformed other models for diagnosing up to 25 conditions, showing potential as an aid to clinicians in high-pressure diagnoses.
A study comparing radiologist and AI performance in interpreting 2,000 chest X-rays found that AI tools achieved moderate sensitivity but high false-positive rates. Radiologists outperformed AI in detecting the absence of disease, especially for complex cases.
A study published in Radiology found that combining short- and long-term breast cancer risk models using artificial intelligence can improve cancer risk assessment. The combined model showed an overall improved risk assessment for both interval and long-term cancer detection, identifying women at high risk for breast cancer.
A machine learning model found that background parenchymal enhancement (BPE) on breast MRI is an indicator of breast cancer risk in women with extremely dense breasts. Women with dense breasts are at a higher risk of developing breast cancer compared to those with fatty breasts.
A new study by Harvard Medical School researchers found that automated scoring systems for AI-generated radiology reports fail to reliably identify clinical errors. The team designed a new method and composite evaluation tool to better evaluate the performance of AI tools in generating clinically useful and trustworthy reports.
A new study published in Radiology found that AI can use data from low-dose CT scans of the lungs to improve risk prediction for death from various causes. The study used data from over 20,000 individuals and found that body composition measurements derived from lung screening LDCT were strong predictors of mortality.
A study published in Radiology found that AI algorithms with high diagnostic accuracy improved radiologists' detection of lung cancers on chest X-rays. High-accuracy AI led to more frequent changes in reader determinations, suggesting increased human trust in AI.
Helen Nadel, MD, FRCPC, has been named SNMMI President, aiming to raise awareness of and access to nuclear medicine, molecular imaging, and theranostics. She will focus on precision health, standardization, diversity, and increasing qualified professionals in the field.
Dmitry Beyder has been elected as the president of the SNMMI-TS for 2023-24, aiming to increase technologists' roles in providing theranostics and nuclear medicine therapy. He brings extensive experience from various positions in the field.
A new ultra-high-resolution CT technology has been developed to detect coronary artery disease in high-risk patients, providing a potentially significant benefit for people previously ineligible for noninvasive screening. The technology delivers excellent image quality and accurate diagnosis with high sensitivity and specificity.