Articles tagged with Medical Imaging
Ashok Veeraraghavan, a Rice University professor, has won the Edith and Peter O'Donnell Award in Engineering from the Texas Academy of Medicine, Engineering, Science and Technology. His research focuses on making invisible objects visible through imaging technology that tackles challenges beyond current technologies.
Researchers at Linköping University have developed an aerogel material that can tune the transmission of terahertz signals between 13% and 91%, enabling various applications. The material's absorption property can be adjusted through a redox reaction, making it suitable for long-range signals from space or radar systems.
Researchers developed a method to measure microvascular changes in the skin using AI and optoacoustic imaging technology, enabling non-invasive assessment of diabetes severity. The study identified 32 significant changes in blood vessels, which can be used to monitor disease progression.
A study published in JAMA Oncology found that regular screening is not enough to prevent advanced breast cancer diagnoses, particularly among women of color who are overweight or obese. The researchers recommend primary prevention strategies to reduce the number of advanced cancer diagnoses.
Novel Dice loss functions, t-vMF Dice loss and Adaptive t-vMF Dice loss, have been developed to improve image segmentation accuracy in medical images. These new functions outperform conventional formulations and show great potential for critical fields like medical imaging and diagnosis.
A new decision rule has been developed to identify patients who can safely forgo a head CT scan after falling, reducing unnecessary imaging and costs. The Falls Decision Rule can be applied to all older adults who have fallen, regardless of sustaining a head injury or recalling the fall.
Outdated medical tools cause delayed recognition and management of adverse reactions in patients of color, leading to significant distress. A more inclusive approach is urgently needed to address structural racism in radiotherapy treatment and education.
Researchers from The University of Texas at Austin have demonstrated a compact particle accelerator that produces an electron beam with an energy of 10 billion electron volts (10 GeV) in a chamber less than 20 meters long. The breakthrough uses nanoparticles to boost the energy delivered to electrons, enabling new applications in semic...
The American Gastroenterological Association released a new guideline recommending the use of biomarkers to help manage Crohn’s disease. Biomarkers such as C-reactive protein and fecal calprotectin can measure levels of inflammation, helping doctors assess disease activity and guide treatment decisions.
Researchers used dynamic total-body PET scans to visualize immune T cell distribution in recovering patients. The study found increased concentrations of CD8+ T cells in the bone marrow of recovering COVID patients compared to healthy controls.
Researchers developed an AI-based method to estimate BMD from plain X-ray images using a hierarchical learning framework. The approach showed high performance and reliability in estimating BMD, with correlation coefficients of 0.88 and 0.92 compared to DXA and QCT.
Researchers at Johns Hopkins University have developed a new algorithm to filter out unwanted signals in medical images of darker skin tones, producing significantly sharper images. This breakthrough aims to mitigate bias in imaging technologies and improve surgical navigation and medical diagnostics for patients with diverse skin tones.
Researchers found that humans can make abstract choices without linking them to motor actions, and the brain processes these choices separately. This study provides new insights into how our brains process decisions related to perception and action.
A new method was developed to predict organ motion in cancer patients undergoing radiation therapy, utilizing cross-sectional images from three orientations. The results showed improved accuracy when analyzing all three directions, with errors reduced to as low as 2.13mm.
A recent study published in Radiology: Artificial Intelligence found significant racial and sex-related biases in an AI chest X-ray foundation model, affecting its performance across patient subgroups. The researchers highlighted the need for comprehensive bias analysis to ensure diversity and representativeness in dataset collection.
A study found that ultrasound scans performed by emergency physicians can nearly halve the time patients spend in emergency departments. This technology, known as point-of-care ultrasound (POCUS), enables faster diagnoses and treatment for suspected deep vein thrombosis (DVT).
An AI system by Lunit identified improperly positioned endotracheal tubes with high sensitivity and specificity, allowing for earlier repositioning and reducing complications. The study included 539 chest radiographs from three institutions and showed promising results in detecting ETT presence and improper position.
Researchers developed a new imaging technique using Bessel beam two-photon microscopy to detect stalling in brain capillaries, which can indicate acute neurological issues. The approach generates clear images of all capillaries every two seconds, providing better temporal resolution and enabling the detection of short stalling events.
A team of Chinese and UK researchers has identified superoxide dismutase 1 (SOD1) as a potential target for reversing drug resistance in ovarian cancer. By using nanoparticles to deliver siRNA that reduces SOD1 levels, the study showed reduced growth and decreased resistance to cisplatin in female mice.
A new imaging technique called quantitative photoacoustic tomography (QPAT) has the potential to provide high-quality images of cancerous tissues. By combining ultrasound and optical tomography, QPAT can help doctors make more accurate diagnoses in shorter time frames.
Researchers developed an AI model that estimates age from chest X-rays and found a correlation between age discrepancy and chronic diseases like hypertension and COPD. The model was validated using data from multiple institutions, showing strong results.
Researchers demonstrate the potential of optical imaging for safely measuring vocal fold elasticity and pliability. The study found good agreement between Brillouin microspectroscopy results and conventional elasticity measurements.
Researchers developed an innovative optical tool, the Schistoscope, to capture microscopy images of urine samples for efficient detection of Schistosoma haematobium eggs. A two-stage diagnostic framework using deep learning accurately identified and counted eggs in field settings with high sensitivity, specificity, and precision.
A new approach boosts light absorption in thin silicon photodetectors with photon-trapping structures, increasing the absorption efficiency over a wide band in the NIR spectrum. The findings demonstrate a promising strategy to enhance the performance of Si-based photodetectors for emerging photonics applications.
Researchers at Monash University developed a co-training AI algorithm that can effectively mimic human oversight in medical imaging. The algorithm achieved an average improvement of 3% compared to state-of-the-art approaches using limited annotated data, enabling AI models to make more informed decisions and uncover accurate diagnoses.
A new position paper reviews TBS for fracture risk prediction, treatment initiation and monitoring in osteoporosis. The evidence-based guide provides practical guidance for clinicians to integrate TBS into clinical practice.
A new geometric deep learning model called GFCN has been developed to detect stroke lesions in brain imaging scans. The model leverages rich geometric information to segment brain tissue and achieves higher segmentation performance than other neural network architectures.
A synoptic report improved the completeness of pretreatment CT reports in patients with advanced ovarian cancer. Involvement of surgically established unresectable or challenging-to-resect disease sites was mentioned in all disease-specific synoptic reports, compared to 37% of simple structured reports.
Researchers introduce a novel class of X-ray scintillators based on monodisperse copper-iodine clusters, demonstrating remarkable sensitivity and stability. The copper-iodide cluster-based microcubes exhibit excellent scintillation performance and exceptional water resistance, making them suitable for large-area flexible X-ray detectors.
A deep learning-based model developed in 7,105 patients predicted 30-day all-cause mortality in patients with CAP with AUCs ranging from 0.77 to 0.80. The model showed higher specificity than the CURB-65 score at the same sensitivity.
A new AI tool utilizing deep-learning algorithms and volumetric thresholds accurately detected splenomegaly in patients undergoing CT scans. The study analyzed a large sample of 8,901 patients, revealing that splenic volume is strongly associated with weight.
Engineers at Rice University and the University of Maryland developed NeuWS, a technology that can undo light scattering effects, enabling full-motion video through various media. The technology measures wavefronts to rapidly decipher phase information, overcoming the 'holy grail problem' in optical imaging.
Researchers created a new method, RESORT, to image and analyze living systems in unprecedented detail. The technique combines benefits of super-resolution fluorescence and vibrational imaging, allowing for high spatial resolution and analysis of complex interactions.
Researchers have developed a new manufacturing pipeline to simplify and advance high-value manufacturing of tissue-compatible organs, reducing costs and increasing efficiency. This breakthrough aims to address the dire need for artificially engineered organs and tissue grafts, potentially saving thousands of lives in the UK.
Researchers from UT Austin created a new composite material that efficiently converts low energy light to higher energy, with applications in bioimaging, solar panels, and night vision goggles. The breakthrough could reduce the size of solar panels by 30% and enable systems for autonomous vehicles and fog detection.
Pre-training in medical data tackles challenges such as data scarcity and privacy concerns using AI techniques like transfer learning and self-supervised learning. Recent advances and new frontiers of pre-training-based techniques are introduced, including applications to medical images, bio-signal data, EHR data, and multi-modality data.
Cancer cells in brain tumors produce lipids at higher rates than surrounding healthy tissue, offering clues for treatment strategies. The study provides insights into the unique biochemical processes fueling cancer growth in the brain.
A team of researchers developed an acoustic metasurface-based holography technique that uses a deep learning algorithm to generate and iteratively improve a hologram of the Mona Lisa. The technique successfully reconstructed the painting, with even greater detail in her left eye.
Researchers at UC San Diego and Stanford University have developed a roadmap of root chemicals that are critical to plant growth, providing new insights into plant development. The study reveals that key small molecules are clustered in patches across the root, suggesting a purposeful distribution for optimal growth.
A multicenter study found that deep learning-based computer-aided diagnosis significantly improved radiologists' diagnostic performance for breast lesion classification on ultrasound. The use of CAD resulted in a 6.0% upgrade of BI-RADS category 3 assessments to category 4A, with 16.7% being malignant.
A recent study found that COVID-19 infection can lead to increased infarct growth and ongoing tissue consumption even after successful reperfusion through angiography. This suggests a potentially aggressive clinical course for patients with COVID-19 and large-vessel occlusion acute ischemic stroke.
A team of researchers from the University of Oklahoma and Yale University has developed a super-resolution imaging platform technology to visualize nanoparticles within cells. The technique, called expansion microscopy, enables 3-D imaging with resolutions as low as 10 nanometers, allowing for safer and more efficient nanomedicines.
Scientists have developed a new method to deliver genetic information to stem cells using nanoparticles coated with a specific polymer, enabling more efficient control over cellular differentiation. This innovation has the potential to improve the efficiency and effectiveness of regenerative medicine treatments.
Researchers at Caltech have developed a technique that uses quantum entanglement to create biphotons, which can be used to image cells with a resolution twice that of traditional microscopes. By harnessing the properties of quantum entanglement, scientists can now visualize tiny structures within living cells with unprecedented precision.
A diffractive optical network-based multispectral imager offers virtual spectral filter arrays, preserving spatial information and yielding an image cube without reconstruction algorithms. The system achieves ~79% average transmission efficiency across distinct bands.
The City University of Hong Kong has developed a novel electron microscope that combines scanning and transmission electron microscope modes in a compact format. The device can produce high-resolution images in five minutes, enabling the study of atom dynamics and beam-sensitive materials.
Two natural coumarin compounds, 5-MOS and 6-MOS, have been identified in the orange climber plant, exhibiting aggregation-induced emission properties. These compounds can clearly identify mitochondria in live cells without additional processing, making cell imaging easier and faster.
The American Roentgen Ray Society presents its 2023 Honorary Lecture on Advanced High-Resolution CT, dedicated to the late Dr. W. Richard Webb, who transformed thoracic imaging with his foundational work in HRCT. The lecture explores multiple conditions diagnosed via HRCT and the radiologist's role on multidisciplinary teams.
Researchers developed an AI-based method for virtual staining of histopathological tissue samples, producing images that closely resemble actual chemical-stained samples. This reduces chemical burden and manual work while enabling the use of tissues for other purposes.
The study used LED imaging to visualize droplet spreading during dental procedures and found that extra-oral and intra-oral suction devices reduced droplet and aerosol spread by 97.8% and 92.1%, respectively. Understanding the dynamics of aerosols and droplets is crucial for preventing infectious diseases like COVID-19.
A new imaging technique using a novel nuclear medicine tracer has been developed to improve the treatment of intestinal strictures in Crohn's disease patients. The technique allows for precise differentiation between inflammation and fibrosis, enabling targeted therapy.
A printable multi-energy X-ray detector made from perovskite thin films has been developed with enhanced flexibility and sensitivity. The detector can operate in a broad energy range, from 0.1 KeV to tens of KeV, making it suitable for real-time detection and imaging applications such as disease diagnosis and explosives detection.
Researchers have developed a new microfluidic chip that enables the visualization of rare cell types and disease patterns in tissue. This method combines imaging and sequencing techniques, providing spatially resolved information about individual cells and their environment.
Researchers have developed a non-invasive method to track human aging using retinal scans, which are less expensive and more accurate than other aging clocks. The study found that changes in the eye can provide an actionable evaluation of gero-protective therapeutics, offering a new tool for tracking aging.
A national survey of radiologists reveals moral distress is widespread, often stemming from high case volumes and lack of administrative support. The study highlights the need for education of leadership regarding causes of distress among frontline workers to address this issue.
Physicists at Delft University of Technology have developed a new technology on a microchip combining optical trapping and frequency combs to measure distances with high precision in opaque materials. The technology uses sound vibrations instead of light, offering a simple and low-power solution for applications such as monitoring the ...
A novel lensless radiomicroscope has been developed for nuclear medicine imaging, offering high-resolution images of cells with a field of view over 500 times larger than current technology. The instrument is made from off-the-shelf parts and costs less than $100, making it accessible to more labs.
A study of US newspaper articles found that lung cancer screening was generally positively covered between 2010 and 2022. However, crucial aspects such as enrollment criteria and cost issues were frequently omitted, highlighting a need for radiologists to take an active role in media coverage.
Researchers from Dartmouth and University Medicine Essen found that strong links between brain measures and traits can be obtained when machine learning algorithms are utilized. This approach allows for high-powered results from moderate sample sizes, opening up studies of many traits and clinical conditions previously inaccessible.
Researchers found that increasing melanin levels in human skin reduces Cherenkov emission intensity, while blood concentration affects different color channels. The study suggests using multispectral signatures to correct attenuated signals based on patient's blood volume or skin color.