A new study finds that AI-powered models exhibit similar levels of accuracy as ophthalmologists in identifying infectious keratitis, a leading cause of corneal blindness worldwide. The AI models displayed a sensitivity and specificity of 89.2% and 93.2%, respectively, matching the diagnostic accuracy of human experts.
A UVA professor has developed a new computational algorithm to find tightly connected clusters, or triangle-dense subgraphs, within large networks. This breakthrough can help uncover suspicious activity in fraud detection and identify community dynamics on social media with greater precision.
Researchers developed an AI model that uses machine learning and combination theory to predict suspicious skin lesions. The new C4C Risk Score has an accuracy of 69% and significantly outperformed existing methods, including 7PCL and Williams score.
A Korean research team has successfully observed living organoids in real time at a high resolution using holotomography. The technology allows for long-term observation of dynamic changes and precise analysis of organoid responses to drug treatments.
Research from Trinity College Dublin found that lower sustained attention in adolescence can predict a larger increase in cigarette and cannabis use by age 23. The study suggests using early biomarkers like sustained attention to identify vulnerable adolescents and guide targeted interventions.
Researchers developed a method to reconstruct hyperspectral images from standard RGB images using deep machine learning. The technique achieved over 70% accuracy in predicting soluble solid content and 88% accuracy in dry matter content in sweet potatoes, with potential applications for the agricultural industry.
Researchers developed a new imaging technique using shortwave-infrared (SWIR) imaging to visualize the lymphatic system, improving resolution and sensitivity compared to traditional near-infrared (NIR) imaging. SWIR imaging with silver sulfide quantum dots offers superior image resolution and outperforms NIR-I imaging techniques.
Researchers developed a method combining AI and thermal cameras to enhance weightlifting training, providing data-driven insights for targeted strategies. The approach enables real-time tracking of muscle activation, strain detection, and temperature changes, ultimately helping athletes optimize performance and safety.
The integration of artificial intelligence in intratumoral immunotherapy can refine diagnoses, guide interventions, predict treatment responses, and adapt therapeutic strategies. This enables the enhancement of patient outcomes, including improved survival rates and quality of life.
Researchers report significant strides in enhancing early diagnosis of bipolar disorder in adolescents by combining multimodal MRI with behavioral assessments. This approach reveals specific changes in brain networks signaling early-stage bipolar disorder, potentially leading to better and more personalized treatments. The study's find...
Researchers analyzed 2 million Google Street View images to explore the utility of digital data in informing public health decision-making. They found that neighborhoods with more crosswalks had lower rates of obesity and diabetes, but no significant link was found between sidewalks and health outcomes.
A new volcano has been discovered on Jupiter's moon Io through analysis of JunoCam images, featuring multiple lava flows and volcanic deposits. The volcano is located just south of the equator and showcases the moon's ongoing geological activity.
A new AI model generates detailed images of cancer tissue that imitate what its staining would look like, reducing the need for resource-intensive lab analyses. The VirtualMultiplexer uses contrastive unpaired translation to create accurate virtual pictures of diagnostic tissue colorations.
Scientists have discovered that some pterosaurs flew by flapping their wings while others soared like vultures. The new findings were made possible by the discovery of remarkably well-preserved fossils in Jordan, including a species with a five-meter wingspan and unique internal structures.
Researchers at Tel Aviv University used modern technologies to challenge the long-held myth that the Roman siege of Masada lasted three years. The study found that the siege actually lasted no more than a few weeks, using precise measurements and 3D digital modeling to calculate the time it took to build the siege system.
Researchers at Heidelberg University developed an AI-supported method to map mosquito populations by analyzing satellite and street view images. This approach helps assess environmental conditions favoring Aedes aegypti presence, enabling targeted disease control measures.
Aston University researcher has developed a new method of analysing crystals in dehydrated blood samples using polarisation-based image reconstruction technique. The technique showed a 90% accuracy rate for early diagnosis and classification of cancer, making it less traumatic and risky for patients.
Researchers in human nutrition developed an innovative tool to assign a healthy hydration recommendation score to governments, promoting water and discouraging sugary beverages. The study analyzed 93 countries with dietary guidelines, finding that 48 had complementary messages encouraging water and reducing sugary beverage intake.
Researchers explore emerging role of Graph Filtration Learning (GFL) in revolutionizing HCC imaging analysis. GFL captures complex topological features inaccessible to traditional pixel-based methods.
The study used spatial transcriptomics and machine learning to analyze gene expression and cell distribution in PanINs, identifying key features of pancreatic cancer progression. Key findings include increased cell proliferation and decreased inflammatory signaling in high-grade PanIN lesions.
Seven rock samples collected along the fan front of Mars' Jezero Crater show evidence of minerals formed in water, suggesting a watery environment. While organic matter cannot be confirmed, these rocks may hold the key to finding remnants of ancient Martian life.
A research team developed an unsupervised domain adaptation approach called DDSP, achieving high-precision cross-modality segmentation without target modality labels. The framework diverges from GANs and incorporates inter-channel similarity feature alignment to boost flexibility and precision.
A Rice University-led team is developing an affordable system to improve tumor removal accuracy for breast and head and neck cancer. The AccessPath system enables rapid, automatic tumor margin classification, revolutionizing real-time surgical guidance.
A computer algorithm has achieved a 98% accuracy in predicting different diseases by analyzing the color of the human tongue. The proposed imaging system can diagnose various health conditions, including diabetes, stroke, and COVID-19, using a simple and affordable method.
A new index uses inflammatory cell proportions to predict tissue healing and outcomes in patients with ulcerative colitis. The index, called the inflammatory cell enumeration index (ICEI), was developed by analyzing data from 220 patients who achieved healing.
Researchers developed DeepLens design method based on curriculum learning to optimize complex lens designs. The approach considers key parameters like resolution, aperture, and field of view, providing optimal solutions without human intervention.
Environmental researchers at NUS use social media and deep learning to classify human activities in nature reserves, analyzing 87,090 photos from 2,813 PAs across 207 countries. The technique demonstrates utility in monitoring land use patterns efficiently and cost-effectively.
Researchers at the University of Göttingen developed a new approach to analyze cell properties, using random fluctuating movement of microscopic particles. The method, called mean back relaxation (MBR), can distinguish between active processes and temperature-dependent processes.
A new clinical algorithm developed at the University of Gothenburg can accurately identify highly aggressive forms of basal cell carcinoma. The algorithm uses a combination of clinical and dermoscopic images to distinguish between low-risk and high-risk tumors, allowing for more effective treatment and better patient outcomes.
Researchers analyzed reflections of light on human eyeballs in real and AI-generated images, finding that fake images often lack consistency between left and right eye reflections. The study employed methods typically used in astronomy to quantify the reflections and checked for consistency.
Researchers used machine learning to create highly detailed maps of individual trees, providing valuable information for conservation efforts and ecological projects. The algorithm achieved high accuracy in classifying common tree species, with strengths shown in areas with open space and lower species diversity.
SourcePLOS·JournalPLOS Biology·TypeComputational simulation/modeling·DateJul 16, 2024
Researchers developed an AI model to analyze heart MRI scans, which can save NHS time and resources. The model provides a complete analysis of the entire heart using a view that shows all four chambers, leading to faster and more accurate diagnosis of heart failure and other cardiac conditions.
Researchers at the University of Utah and Max Planck Institute have discovered an intermediate-mass black hole in the Omega Centauri cluster, providing crucial evidence for a long-theorized class of black holes. The discovery offers insights into galaxy evolution and the formation history of globular clusters.
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.
A team of researchers developed EMOKINE software to measure the objective kinematic features of movements that express emotions. The software provides movement parameters from data sets at the touch of a button, allowing scientists to analyze emotional expression and intentions.
A research team at KAIST has developed an AI-based methodology to predict the major elemental composition and charge-discharge state of NCM cathode materials with high accuracy using convolutional neural networks. The technology can analyze surface morphology images of batteries to determine their composition and lifespan.
Researchers found that facial temperatures are associated with chronic illnesses like diabetes and high blood pressure. They discovered specific regions of the face where temperatures correlate with age and health, including the nose, eyes, and cheeks.
A new liquid biopsy method analyzes gene fragments in the bloodstream to detect and track cancer, enabling oncologists to tailor treatment approaches to individual patients. This non-invasive test can help monitor treatment success, detect cancer recurrence, and improve patient quality of life.
A new North Carolina State University study found a dearth of useful depictions of farmworkers in commercial stock photo libraries, highlighting the need for more relevant educational materials. The research suggests that these images can impact farmworker engagement with safety behaviors.
A new study using NASA's InSight Lander data reveals that Mars may be getting bombarded by space rocks more frequently than previously estimated. The research team detected eight new impact craters from meteoroids not seen before, including two of the largest impacts ever recorded on the Red Planet.
A new study from the University of Copenhagen reveals that AI has helped detect significantly more cases of breast cancer and reduce radiologist workloads. The AI system has been used to analyze tens of thousands of X-rays every year, resulting in a 12% increase in detected cases, including more small tumours of one centimetre or less.
A study found that large language models (LLMs) like ChatGPT underperform state-of-the-art detectors but can explain their analysis in plain language. LLMs' semantic knowledge makes them well-suited for detecting deepfakes, providing a common sense understanding of reality.
The study reveals that supergranules, a flow structure in the sun's interior, challenge standard theories of solar convection. Researchers discovered that downflows appear weaker than upflows, suggesting an unseen component that could be small-scale plumes transporting cooler plasma into the sun's interior.
Researchers at FSU used machine learning to analyze patterns in dried salt solution drops, identifying the chemical composition of different salts with accuracy. The tool has potential applications in lab safety testing, rapid screening for suspected drugs and low-cost blood analysis.
Berkeley Lab's RhizoNet harnesses AI to transform how scientists study plant roots, offering new insights into root behavior under various environmental conditions. The tool semantically segments plant roots for comprehensive biomass and growth assessment, propelling efforts toward self-driving labs.
Researchers used modern technology to estimate the number of rock gardens on Easter Island and food production, revealing that the island couldn't sustain a large population. The study's findings contradict the long-held notion of an ecological catastrophe and instead suggest a more sustainable approach to agriculture.
Researchers developed a novel method to estimate modulation amplitude and determine spatial resolution in Brillouin optical correlation-domain reflectometry (BOCDR) without costly equipment. This innovation simplifies the process, reducing costs and enhancing convenience.
A new method in neuroimaging analysis allows researchers to predict cognition and behavioral variables using smaller datasets, contrary to the long-held belief that thousands of participants are needed. The technique involves examining MRI data to find associations with behaviors and then applying predictions to an independent sample.
A new AI-powered smartphone tool can detect stroke in seconds, improving diagnosis time and reducing permanent brain damage. The tool uses facial expression recognition to identify patients who need prompt treatment.
Researchers have developed a new photonic chip that can process, transmit and reconstruct images in nanoseconds, eliminating optical-electronic conversions. This technology holds promise for revolutionizing edge intelligence in machine vision applications.
A new computer vision technique developed by MIT engineers significantly speeds up the characterization of newly synthesized electronic materials. The technique automatically analyzes images of printed semiconducting samples and quickly estimates two key electronic properties: band gap and stability.
A new study at the University of Toronto reveals a significant association between photo filter use and increased symptoms of muscle dysmorphia among adolescents and young adults. The research found that frequent use of photo filters is linked to greater muscle dissatisfaction and overall muscle dysmorphia symptoms, particularly among ...
Australian scientists have developed an AI-powered system to detect bushfires from space, reducing detection time by 500 times compared to traditional methods. The system uses hyperspectral imagery and onboard AI to identify fire smoke before it takes hold, allowing for faster responses and preventing loss of life and property.
A Penn State-led study found that female giraffes have proportionally longer necks than males, suggesting high nutritional needs drove the evolution of this trait. Giraffes adapt to reach leaves in trees by using their long necks, allowing females to access food with increasing demands as they mature.
A recent study demonstrates that radiomics can effectively forecast the hearing status of patients with vestibular schwannoma. The research team isolated specific radiomics features from MRI images that best predict hearing status, offering an objective method to predict patient outcomes.
Researchers developed a new method to enhance thermal image super-resolution by employing synthetic imagery, significantly improving detail and utility of thermal imaging across various applications. The approach utilizes high-resolution images from the visible spectrum to guide the super-resolution of low-resolution thermal images.
A new Curtin University research study found that taking pictures of food can be an accurate way to track dietary intake. The study used the mobile Food Record app, which analyzed photos to estimate energy and nutrient intake, outperforming traditional recall methods.
Researchers have developed a system combining bio-inspired cameras with AI to quickly detect obstacles around cars, using less computational power. The hybrid system detects objects up to one hundred times faster than current systems while reducing data transmission and processing needs.
The study enhances shape-from-shading technique to create detailed models of lunar terrain with higher resolutions and faster production speeds. Researchers use advanced computer algorithms to automate the process, resulting in more accurate maps that show subtle features and variations of lunar surface terrain.
A team of researchers from Japan, China, and Finland created a system called generative content replacement (GCR) that uses AI to replace parts of images that might threaten confidentiality with visually similar but AI-generated alternatives. In tests, 60% of viewers couldn't tell which images had been altered.