Search Tag: medical imaging
2025 17 Nov
Phantom-based research is widely used in diagnostic radiology to evaluate imaging systems, refine protocols and validate image analysis without exposing patients or animals to risk. Physical or computational models of human tissues and anatomy enable controlled investigation across radiography, mammography, computed tomography, magnetic resonance...Read more
2025 09 Nov
Prostate-specific membrane antigen PET/CT using fluorine-18 PSMA-1007 is being used to stage prostate cancer before treatment. Beyond image quality, the tracer’s practical features support routine deployment and may help visualise pelvic disease. A systematic review and metaanalysis pooled results from clinical studies that compared imaging directly...Read more
2025 28 Oct
Lung cancer remains the leading cause of cancer-related deaths worldwide, yet advances in computed tomography (CT) screening and artificial intelligence are reshaping prospects for earlier detection and improved outcomes. Evidence from large screening programmes and long-term follow-up cohorts indicates that identifying disease at an early stage...Read more
2025 28 Oct
Lung cancer remains the leading cause of cancer-related deaths worldwide, yet advances in computed tomography (CT) screening and artificial intelligence are reshaping prospects for earlier detection and improved outcomes. Evidence from large screening programmes and long-term follow-up cohorts indicates that identifying disease at an early stage...Read more
2025 25 Oct
Prostate-specific membrane antigen (PSMA) PET/CT has transformed prostate cancer assessment and is now embedded in guideline-recommended care. Yet the usefulness of advanced imaging depends on how consistently results are communicated. An analysis of consecutive external PSMA PET/CT reports received at a single tertiary centre highlights substantial...Read more
2025 18 Oct
AI is transforming radiology, offering both interpretative and workflow-enhancing tools. Inspired by sectors like automotive, retail and finance, radiology can adopt AI-driven practices to improve efficiency, personalisation and cost control. From tailored reports to smart scheduling and inventory management, cross-industry innovations show great...Read more
2025 16 Oct
Accurate preoperative classification of bone tumours as benign or malignant supports timely treatment selection and better outcomes, yet interpretation of radiographs can be challenging, particularly for less experienced clinicians. A machine learning approach integrating radiomics features from knee X-ray images with routine clinical data was...Read more
2025 16 Oct
Accurate preoperative classification of bone tumours as benign or malignant supports timely treatment selection and better outcomes, yet interpretation of radiographs can be challenging, particularly for less experienced clinicians. A machine learning approach integrating radiomics features from knee X-ray images with routine clinical data was...Read more
2025 16 Oct
Accurate preoperative classification of bone tumours as benign or malignant supports timely treatment selection and better outcomes, yet interpretation of radiographs can be challenging, particularly for less experienced clinicians. A machine learning approach integrating radiomics features from knee X-ray images with routine clinical data was...Read more
2025 16 Oct
Artificial intelligence is advancing quickly in medical imaging, expanding potential users and use cases while exposing gaps in knowledge about capabilities, risks and deployment. Complex models, large data demands and distinct non-human failure modes make safe adoption challenging. A multisociety syllabus from several institutions sets out role-specific...Read more
2025 16 Oct
Rapid identification of critical radiology findings is essential as reporting volumes rise and language grows more nuanced. Traditional natural language processing depends on rules or large annotated datasets, which can miss context. General-purpose large language models (LLMs) offer a prompt-driven alternative that may work without retraining....Read more
2025 16 Oct
Rapid identification of critical radiology findings is essential as reporting volumes rise and language grows more nuanced. Traditional natural language processing depends on rules or large annotated datasets, which can miss context. General-purpose large language models (LLMs) offer a prompt-driven alternative that may work without retraining....Read more
2025 16 Oct
Rapid identification of critical radiology findings is essential as reporting volumes rise and language grows more nuanced. Traditional natural language processing depends on rules or large annotated datasets, which can miss context. General-purpose large language models (LLMs) offer a prompt-driven alternative that may work without retraining....Read more
2025 16 Oct
Rapid identification of critical radiology findings is essential as reporting volumes rise and language grows more nuanced. Traditional natural language processing depends on rules or large annotated datasets, which can miss context. General-purpose large language models (LLMs) offer a prompt-driven alternative that may work without retraining....Read more
2025 16 Oct
Rapid identification of critical radiology findings is essential as reporting volumes rise and language grows more nuanced. Traditional natural language processing depends on rules or large annotated datasets, which can miss context. General-purpose large language models (LLMs) offer a prompt-driven alternative that may work without retraining....Read more
2025 07 Oct
Radiology’s rapid digitisation has delivered faster workflows and broader access to specialist expertise, yet it has also expanded the attack surface across imaging networks, data stores and remote workstations. Health care delivery has faced sharp growth in ransomware, data exfiltration and operational disruption, with high direct and downstream...Read more
2025 06 Oct
Magnetic resonance imaging (MRI) underpins routine neuroimaging, but lengthy acquisitions can challenge patient comfort, increase motion artefacts and slow clinical workflow. Deep learning (DL) reconstruction has emerged to accelerate image acquisition while aiming to maintain diagnostic performance. A single-centre retrospective comparison evaluated...Read more
2025 06 Oct
Magnetic resonance imaging (MRI) underpins routine neuroimaging, but lengthy acquisitions can challenge patient comfort, increase motion artefacts and slow clinical workflow. Deep learning (DL) reconstruction has emerged to accelerate image acquisition while aiming to maintain diagnostic performance. A single-centre retrospective comparison evaluated...Read more
2025 06 Oct
Artificial intelligence is widely expected to ease pressure on radiology services by supporting detection, prioritisation and reporting. A rapid evaluation examined how AI for chest diagnostics, including lung cancer, was procured and prepared for deployment across National Health Service (NHS) imaging networks in England. The work covered 12...Read more
2025 06 Oct
Artificial intelligence is widely expected to ease pressure on radiology services by supporting detection, prioritisation and reporting. A rapid evaluation examined how AI for chest diagnostics, including lung cancer, was procured and prepared for deployment across National Health Service (NHS) imaging networks in England. The work covered 12...Read more
2025 05 Oct
Artificial intelligence is reshaping chest radiography by automating complex image interpretation tasks and supporting multi-class diagnosis. Two prominent strategies are compared side by side: radiomics, which extracts handcrafted quantitative features, and deep learning, which learns hierarchical representations directly from images using convolutional...Read more
2025 05 Oct
Artificial intelligence is reshaping chest radiography by automating complex image interpretation tasks and supporting multi-class diagnosis. Two prominent strategies are compared side by side: radiomics, which extracts handcrafted quantitative features, and deep learning, which learns hierarchical representations directly from images using convolutional...Read more
2025 05 Oct
Artificial intelligence is reshaping chest radiography by automating complex image interpretation tasks and supporting multi-class diagnosis. Two prominent strategies are compared side by side: radiomics, which extracts handcrafted quantitative features, and deep learning, which learns hierarchical representations directly from images using convolutional...Read more
2025 30 Sep
Artificial intelligence has long supported radiology as a reactive aid, flagging abnormalities and speeding report generation when prompted by users. A newer approach is emerging that shifts from passive assistance to autonomous, context-aware action. Agentic AI can initiate workflow management, plan tasks and deliver clinical decision support...Read more
2025 24 Sep
Prostate cancer remains a major global burden, while diagnostic pathways continue to evolve to balance accuracy, invasiveness and resource use. Multiparametric MRI is central to noninvasive assessment but can be affected by motion, interpretation variability and scan duration. Researchers have reported an in silico evaluation of MRI histopathology,...Read more
2025 17 Sep
Artificial intelligence now supports reconstruction, segmentation, synthetic image generation, disease classification, triage and scheduling across radiology. Yet strong performance still depends on expert-labelled data, which are costly and slow to assemble. Active learning addresses this constraint by selecting the most informative or uncertain...Read more
2025 17 Sep
Artificial intelligence now supports reconstruction, segmentation, synthetic image generation, disease classification, triage and scheduling across radiology. Yet strong performance still depends on expert-labelled data, which are costly and slow to assemble. Active learning addresses this constraint by selecting the most informative or uncertain...Read more
2025 17 Sep
Artificial intelligence now supports reconstruction, segmentation, synthetic image generation, disease classification, triage and scheduling across radiology. Yet strong performance still depends on expert-labelled data, which are costly and slow to assemble. Active learning addresses this constraint by selecting the most informative or uncertain...Read more
2025 17 Sep
Artificial intelligence now supports reconstruction, segmentation, synthetic image generation, disease classification, triage and scheduling across radiology. Yet strong performance still depends on expert-labelled data, which are costly and slow to assemble. Active learning addresses this constraint by selecting the most informative or uncertain...Read more
2025 09 Sep
Imaging is integral to intensive care, where frequent X-rays, fluoroscopy, CT and nuclear medicine guide day-to-day decisions for critically ill patients. Repeated examinations during prolonged admissions can drive cumulative effective dose to levels that warrant careful management, with CT the dominant contributor. Safe delivery relies on robust...Read more