Latest news with #radiologists
Yahoo
7 days ago
- Business
- Yahoo
GE HealthCare launches new advanced digital X-ray system to enable access and increase efficiency in high throughput settings
Definium™ Pace Select ET, a new floor-mounted digital X-ray system, enables access to affordable, high-quality medical imaging technology while easing workflow burdens in high-volume environments This new X-ray system, designed to act as a personal assistant for technologists, provides automation of in-room workflows and motorization of manual, repetitive tasks to increase throughput and reduce technologist learning curve CHICAGO, July 24, 2025--(BUSINESS WIRE)--GE HealthCare (Nasdaq: GEHC), today announced commercial availability of an advanced floor-mounted digital X-ray system, Definium™ Pace Select ET1, designed to deliver high-image quality and optimize efficiency in highly demanding environments while enhancing access and affordability. X-ray exams often serve as the entry point to diagnostic imaging, accounting for 60% of all imaging studies conducted, resulting in an ever-increasing workload for radiologists and technologists2 3. This increased demand, combined with acute staffing challenges where 80% of healthcare organizations are short-staffed and radiology technologists have the highest vacancies3, high burnout levels and work-related injuries, creates critical barriers to providing timely, effective diagnostic imaging for patients in need of X-ray imaging. GE HealthCare's new Definium Pace Select ET solves for many of these challenges by automating manual, repetitive steps and helping to reduce physical strain. The system leverages AI to ensure accurate patient positioning and consistent image quality across various clinical conditions while streamlining the technologist workflow to maximize the patient experience and throughput. "Burdened with the stress and pressure to keep radiology departments running smoothly and profitably, we aim to empower technologists with a system that consistently makes the first image count," said Sharad Sharma, Global General Manager, X-ray, at GE HealthCare. "With its advanced digital capabilities and automation, Definium Pace Select ET allows technologists of all experience levels to deliver consistent high-quality images to serve the full range of anatomies and patient populations." Easy-to-use features allow technologists to focus on patient care Building on the trusted Definium platform from GE HealthCare, the Definium Pace Select ET system brings advanced automation and workflow features to a flexible, floor-mounted system with elevating table, in-room exam control, and common user interface to assist technologists. "This launch reinforces our commitment to provide accessible, efficient, and high-quality care for patients, while alleviating stress from the technologist's workday by minimizing repetitive tasks and automating steps," said Jyoti Gupta, PhD, President & CEO of Women's Health and X-ray at GE HealthCare. "We remain dedicated to advancing our technology through transformative digital and AI-enabled capabilities that will remove barriers to timely and effective diagnostic imaging for any patient in need of X-ray imaging." The Definium Pace Select ET system brings the same high image quality typically seen in more expensive overhead tube suspension (OTS) systems to the affordability focused floor-mounted market. Designed and developed with extensive customer feedback, the system brings: Advanced automation to reduce workflow steps and physically demanding movements for technologists, potentially minimizing work-related injuries. Image variability reduction through the AI-enabled Helix™ Advanced Image Processing to provide consistent high-quality images. Prevention of errors before they occur through automated positioning, protocol selection, patient size (body habitus), and collimation via the Intelligent Workflow Suite, and a quality check prior to radiation exposure. To learn more about the new X-ray system, visit About GE HealthCare Technologies Inc. GE HealthCare is a trusted partner and leading global healthcare solutions provider, innovating medical technology, pharmaceutical diagnostics, and integrated, cloud-first AI-enabled solutions, services and data analytics. We aim to make hospitals and health systems more efficient, clinicians more effective, therapies more precise, and patients healthier and happier. Serving patients and providers for more than 125 years, GE HealthCare is advancing personalized, connected and compassionate care, while simplifying the patient's journey across care pathways. Together, our Imaging, Advanced Visualization Solutions, Patient Care Solutions and Pharmaceutical Diagnostics businesses help improve patient care from screening and diagnosis to therapy and monitoring. We are a $19.7 billion business with approximately 53,000 colleagues working to create a world where healthcare has no limits. GE HealthCare is proud to be among 2025 Fortune World's Most Admired Companies™. Follow us on LinkedIn, X, Facebook, Instagram, and Insights for the latest news, or visit our website for more information. _______________________________ 1 510(k) cleared. Not CE marked. Cannot be placed on the market or put into service or used with human beings until it has been made to comply with CE marking and/or regulatory approval. Not all features available in all markets. 2 MV 2019 X-ray CR / DR Market Outlook Report) page 9, 37 3 Pearson, Dave. "Radiology techs in especially high demand as 85% of hospitals seek 'allied' health workers", 23 Oct. 22. View source version on Contacts GE HealthCare Media Contact: Katie ScrivanoM +1 Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Medscape
18-07-2025
- Health
- Medscape
Does AI Aid Rare Bone Fracture Detection in Children?
TOPLINE: In patients with osteogenesis imperfecta, artificial intelligence (AI) assistance improved the fracture detection accuracy of radiologists from 83.4% to 90.7%. However, radiologists performed better than AI when their standalone performance was considered. METHODOLOGY: In this study, researchers analysed 336 appendicular and pelvic radiographs of 48 children (mean age, 12 years) with genetically confirmed osteogenesis imperfecta. The ground truth was determined by a consensus opinion of two consultant paediatric radiologists who labelled acute and healing fractures with bounding boxes. Seven radiologists independently evaluated anonymised images in two rounds — the first round without AI and the second round with AI assistance. The AI tool provided bounding boxes for suspected fractures but did not distinguish acute from healing fractures. After both rounds were completed, the results from radiologists without AI assistance, radiologists with AI assistance, and the AI alone were compared against the ground truth by calculating the intersection between the bounding boxes. TAKEAWAY: AI demonstrated a per-examination accuracy of 74.8% (95% CI, 65.4%-82.7%), compared with the average radiologist performance of 83.4% (95% CI, 75.2%-89.8%). Radiologists using AI assistance improved their average accuracy per examination to 90.7% (95% CI, 83.5%-95.4%). AI support increased average radiologist per-image accuracy by 7.0% (from 84.6% to 91.6%) and per-fracture accuracy by 3.7% (from 76.3% to 80.0%). Per fracture, AI assistance lowered true and false positives while raising true and false negatives, boosting the accuracy by 3.7%, specificity by 10.0%, and positive predictive value by 7.2%. On average, radiologists changed their per-fracture decisions in 72 instances; 69% of those changes matched the AI's suggestion, and 64% improved accuracy. IN PRACTICE: "In conclusion, the results of this study suggest that AI assistance improves radiologists' performance in diagnosing fractures in children with OI [osteogenesis imperfecta], even if it is not specifically trained for this population," the authors of the study wrote. "Nevertheless, compared to radiologists, the standalone AI performance was worse, thus highlighting potential dangers of implementing the AI tool in an autonomous manner," they added. SOURCE: This study was led by Cato Pauling, University College London, London, England. It was published online on July 07, 2025, in European Radiology. LIMITATIONS: Researchers included repeat examinations from some patients over the study period, which may have introduced bias due to similarities in appearances. This study used only one commercially available AI model, despite multiple products being available in the market. Additionally, the lack of a control group of patients without bone fragility disorder made it challenging to objectively evaluate whether the AI tool performed less accurately in children with osteogenesis imperfecta. DISCLOSURES: This study received funding support from the National Institute for Health and Care Research. The authors declared having no conflicts of interest. This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication.
Irish Times
13-07-2025
- Health
- Irish Times
The Irish Times view on cancer treatment: unacceptable delays
The Irish Cancer Society's pre-budget submission makes for alarming reading. It reveals unacceptable delays in access to essential cancer diagnostics and treatments – surgery, chemotherapy, radiotherapy, and urgent tests for breast and prostate cancer– in several parts of the country. These regional variations aren't just unfair; they are life-threatening. Outcomes from cancer are strongly tied to the speed of diagnosis and treatment. Patients treated at Stage 1 are up to four times more likely to survive than those treated at Stage 4. Yet despite targets set by the National Cancer Strategy, many public cancer centres outside of Dublin are consistently failing to deliver timely care due to shortages in staff, space, and essential equipment. The result is a cancer postcode lottery where the speed of diagnosis and treatment hinges on where patients live. In Galway patients are reportedly waiting up to eight weeks for chemotherapy– far exceeding the recommended 15-day window. International research shows that every four-week delay in treatment increases mortality risk by 10 per cent. Key diagnostic tools like PET scanners are still unavailable in public cancer centres in Galway, Waterford, and Limerick. And essential radiotherapy machines are remaining in use years beyond their recommended lifespan. Staffing shortages are also critical. GPs, radiologists, oncology nurses and radiation therapists are in short supply, resulting in cancelled appointments and essential equipment remaining idle. The system is overstretched and many patients are being let down. READ MORE The highlighted failings in our cancer services are indefensible in a first-world country with a record €26 billion overall healthcare budget. The Irish Cancer Society, backed by professional oncology groups, is calling for significantly increased cancer service investment in Budget 2026 –particularly in staffing, infrastructure, and equipment– to ensure national waiting time targets are met. Also vital is ensuring that cash that is spent actually translates to improved services.
Medical News Today
11-07-2025
- Health
- Medical News Today
Can AI help detect breast cancer, and is it accurate?
Artificial intelligence (AI) may help detect breast cancer earlier and more accurately than traditional methods alone. It may also help predict a person's risk of developing breast professionals use imaging scans like mammograms and breast ultrasounds to screen people for breast cancer, which can help with early detection. They may also assess a person's family history, genetics, and other factors to help determine their risk of developing the studies suggest that AI could help health professionals detect breast cancer more quickly and accurately than with traditional screening methods alone. The technology may also help predict a person's risk of breast cancer with greater precision. How does AI help with breast cancer detection?AI developers can train computer systems to recognize, interpret, and analyze patterns in breast cancer detection, AI technicians input information gathered from large data sets of mammograms for the systems to learn AI software uses the data to create an algorithm that outlines the characteristics of mammograms with and without cancer. The system can then compare new images to the algorithm to help identify accurate is AI in detecting breast cancer?Research has found that AI could help detect breast cancer with similar or greater accuracy than radiologists a recent Swedish study, AI-supported screening detected cancer in 244 women after analyzing 39,996 mammograms. In a separate group, two radiologists each used traditional screening methods to analyze a different set of 40,024 mammograms, from which they were able to detect cancer in 203 false positive rate was 1.5% in both groups, which means AI and radiologists both mistakenly detected breast cancer in 1.5% of the mammograms they the detection rates were similar between both groups, the AI screening method reduced the workload for radiologists and allowed them to spend 44% less time reading screens.A 2025 meta-analysis of eight studies indicated that AI techniques could detect breast cancer with better overall accuracy than the researchers also highlighted the current limitations of AI screening. These included the technology sometimes failing to identify visible lesions or interpret ambiguous results like radiologists researchers suggest that AI and traditional radiology combined may result in the most accurate and effective breast cancer of a 2022 study agree that AI should support, rather than replace, radiologists. Their results indicate that a combination of AI and a radiologist could detect breast cancer 2.6% more accurately than a radiologist AI detect early breast cancer?Early breast cancer detection and treatment can significantly improve a person's outlook for the disease. The survival rate is almost 100% for the earliest stages of breast cancer and declines to 22% at stage screening mammograms miss about 20% of breast cancers, according to the National Cancer screening may help reduce false-negative results and help identify breast cancer earlier, as research suggests it could improve overall screening accuracy. However, more research is necessary to understand the reliability and implications of the technology. »Learn more:How can people detect breast cancer early?Can AI assess individual breast cancer risk?Research suggests AI may be able to effectively assess a person's risk of developing breast professionals typically use tools like the Breast Cancer Risk Assessment tool (BCRAT) or the Breast Cancer Surveillance Consortium (BCSC) Risk Calculator to estimate a person's likelihood of developing the tools calculate an individual's risk based on several factors, including their age, race and ethnicity, and personal and family medical histories.A recent study found that AI may be able to predict a person's breast cancer risk without these the study, AI systems used mammogram images to predict people's risk of developing breast cancer more accurately than the BCSC risk model researchers found that combining AI and the BCSC model achieved the most accurate there challenges in using AI for breast cancer detection?Potentially, AI offers significant developments in breast cancer detection. However, AI systems lack standardization and rigorous regulatory and ethical guidelines and may present several challenges for researchers and health professionals. These include:Research challenges: AI algorithms are not generalized and often include large numbers of variables. This may affect how consistently AI models are able to perform and the reliability of the data they provide. Scientists need more evidence from large-scale studies to assess how safe, accurate, and reliable the technology may be for breast cancer detection in real-world clinical 'black box enigma': Scientists may refer to AI algorithms as black boxes, as humans cannot always understand the patterns the models find and the decisions they make. This could lead to AI making incomprehensible mistakes that scientists cannot predict, detect, or concerns: The use of AI raises various ethical issues, including contributing to health disparities and the effect on healthcare professionals that AI systems may challenges: AI algorithm and infrastructure development and maintenance involve substantial ongoing a person's data secure when AI screens for breast cancer? There are complex legal, regulatory, and technological challenges that may affect a person's data security when AI is used for breast cancer screening. The Health Insurance Portability and Accountability Act (HIPAA) protects people's health information and health privacy rights in the United States. As a new and evolving technology, however, AI presents legal and regulatory challenges that may affect health data may disclose 'de-identified' protected health information. This involves removing information that could identify an individual or link them to the data. However, researchers suggest AI healthcare may result in opportunities for re-identification, which could link sensitive and private information to specific bodies, healthcare professionals, and AI developers may continue to determine and implement safety measures as the technology AI help reduce breast cancer disparities?Breast cancer disparities can prevent certain groups from receiving equitable screening and treatment. These disparities persist due to various factors, including racism, the underrepresentation of certain groups in clinical trials, and a lack of access to cancer disparities affect Black women especially severely. The group has a 38% higher mortality rate than white women, despite having a lower incidence of the suggest that AI is vulnerable to bias and may contribute to and exacerbate existing racial disparities in healthcare, such as breast cancer suggests that AI reflects human bias as it learns from the data that people provide. Additionally, human choices may influence AI systems to perform in exploitative or discriminatory may help to reduce racial disparities in breast cancer screening if the people who use the technology actively counter existing healthcare biases. This may involve the use of ethical AI programs and the inclusion of diverse data tend to agree that AI breast cancer screening should be integrated to support, rather than replace, radiologists for the most accurate technology may be a promising tool for breast cancer detection and risk prediction. However, it faces several challenges, including ethical concerns, excessive financial costs, and reliability research is needed to determine if the technology is safe, accurate, and reliable before it can be widely implemented.
Medscape
11-07-2025
- Health
- Medscape
AI Outperforms Humans in Mammography Analysis
TOPLINE: An artificial intelligence (AI) tool in mammography showed a high sensitivity and specificity, outperforming human readers in overall performance, a study found. However, the performance of the AI tool was slightly lower at the lesion level than at the breast level. METHODOLOGY: Researchers retrospectively analysed mammograms from the UK's NHS Breast Screening Programme by using a commercial AI tool (Lunit Insight MMG) and human readers to evaluate 882 non-malignant and 318 malignant breasts with 328 lesions. Human readers (n = 1258), including radiologists, radiographers, and breast clinicians, reviewed 1200 mammograms. The same cases were independently reviewed by the AI tool. Human and AI decisions to clear or recall breasts or lesions were compared with real outcomes on the basis of pathology or a 3-year follow-up. Sensitivity, specificity, and area under the curve (AUC) were calculated at both breast and lesion (marked regions of interest) levels. TAKEAWAY: The AI tool outperformed human readers on the basis of the AUC at the breast level (0.942 vs 0.878) and lesion level (0.929 vs 0.851; P < .01 for both). At the developer-recommended recall threshold, the AI tool achieved a significantly higher specificity than human readers at the breast level (87.4% vs 79.2%; P < .01). When calibrated to match the human specificity, the AI tool had a higher sensitivity than human readers at the breast level (92.1% vs 87.5%; P = .051) and lesion level (90.9% vs 83.2%; P < .01). The AI tool failed to localise 4% of total cancer lesions, with a median human error rate of 62.6%. IN PRACTICE: "Our findings support the notion of implementing AI into a prospective screening workflow, where the localisation of malignancies is beneficial to patients and the screening process," the authors wrote. "To improve human-AI collaboration, AI should be assessed at the lesion level; poor accuracy here may lead to automation bias and unnecessary patient procedures," they added. SOURCE: This study was led by Adnan Gani Taib and George John William Partridge, University of Nottingham, Nottingham, England. It was published online on June 25, 2025, in European Radiology. LIMITATIONS: This study could not assess the real-time effect of AI on human decision-making due to its retrospective design. The use of cancer-enriched test sets may have led to an overestimation of human performance. Additionally, prior mammograms were not available for comparison, which are often used in routine clinical practice to aid detection. DISCLOSURES: This study was funded by Lunit. The authors reported having no conflicts of interest. This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication.
