A new AI tool called SUBTLE has been developed for advanced animal behavior analysis. It classifies and analyzes behavior through AI learning based on 3D movement information, reducing time-series data into two dimensions for embedding.
This study analyzed resting state fMRI data to investigate salience network disruptions in schizophrenia. The analysis revealed weaker dorsal salience network connectivity and increased ventral salience network connectivity in patients.
A recent study uses AI to analyze body composition in patients with lung cancer treated with immunotherapy, finding that changes in muscle mass and fat quality are important indicators of outcomes. The research provides a more nuanced understanding of the relationship between body composition and response to immunotherapy.
Researchers developed AI software to analyze animal behavior, enabling precise linking of brain circuits and neurons. The program reconciles differing results by providing transparent explanations for machine-learning predictions, facilitating cross-lab comparisons and reproducibility in behavioral research.
Researchers in Portugal have developed an innovative open-source platform called DL4MicEverywhere, providing life scientists with easy access to advanced artificial intelligence for the analysis of microscopy images. The platform enables researchers to easily train and use deep learning models on their own data, regardless of their com...
A study found a dose-dependent association between adolescent body mass index and mental health, with the strongest link observed over time. The U-shaped relationship was consistent across sex and grade levels, highlighting the need for targeted interventions addressing body image and mental health.
A research team at Kyoto University has developed an AI method to automatically detect methane emissions globally, resolving trade-offs with existing detection methods. The system can identify small methane plumes, paving the way for systematic quantification of global warming.
Researchers have developed new optical tweezers that can stably trap large and irregularly shaped particles using contour-tracking technology. This advancement could expand light-based trapping to a wider range of objects, including groups of cells, bacteria, and microplastics.
The team developed a deep learning AI technique to quantitatively analyze cation mixing using atomic structure images. This approach revealed that introducing metal dopants like aluminum, titanium, and zirconium into the transition metal layer fortified bonds between nickel and oxygen atoms, curbing cation mixing.
Wildfires in the Amazon's old-growth forests increased by 152% in 2023, primarily caused by drought, with most of them occurring in Roraima state. This surge in forest fires poses significant risks to the environment and public health.
Researchers have developed a new imaging technique that rapidly and accurately identifies cancerous tissues in breast samples. The method uses machine learning algorithms trained on hyperspectral dark-field microscopy data to pinpoint regions of invasive ductal carcinoma and invasive mucinous carcinoma.
A new study led by ORNL provides valuable insights into vegetation resilience in response to extreme heat events, informing pathways for climate mitigation. The analysis found that impervious surfaces, moisture conditions, and type of land cover affect vegetation resilience, with preservation and enhancement of vegetation contributing ...
Scientists at Harvard John A. Paulson School of Engineering and Applied Sciences have developed a compact, single-shot polarization imaging system that can provide a complete picture of polarization. The system uses two thin metasurfaces to capture the most complete polarization response of an object in real-time.
FathomVerse combines real underwater images, interactive gameplay, and AI training to improve ocean research. The game engages players in labeling images for machine learning models, contributing to a broader audience in ocean exploration.
Researchers develop laser microscopy technique to analyze pigments in artwork, detecting chemical changes that mark the onset of decay. The technique uses ultra-fast pulses of light to create 3D maps of certain pigments, allowing for nondestructive analysis and early detection of fading.
A new remote sensing method captures details of hurricane Ian's aftermath, identifying 2,427 structures impacted by the storm. The study found that most damaged structures were single-family and multi-unit residences, with a total assessed value of over $200 million.
A computer vision researcher has developed privacy software for surveillance videos that obscures identifiable information such as faces and clothing in real-time. The software, funded by the National Science Foundation's Accelerating Research Translation program, aims to balance surveillance needs with privacy concerns.
Researchers have analyzed over a thousand images of snow to study its optical properties. The findings show promise in improving avalanche safety and autonomous car technology, but more data is needed.
A new study from the University of Illinois explores the use of hyperspectral imaging and explainable artificial intelligence to assess sweet potato attributes, leading to more informed decision-making and higher-quality products. The results can help industry professionals understand the significance of different features in predictin...
Using AI software called SLEAP, scientists at Salk Institute are designing climate-saving plants with optimized root systems that can store more carbon. This approach enables researchers to analyze plant features and connect desirable traits to targetable genes, accelerating the development of carbon-capturing plants.
A new AI model generates realistic images of single cells, which are used as synthetic data to train an AI model for better cell segmentation. The researchers found that providing a more diverse dataset during training improves performance.
Researchers found that watching sports fosters a sense of community and belonging, while triggering activation in the brain's reward circuits. Regular sports viewing may also induce changes in brain structures, leading to long-term benefits for individuals.
Researchers develop AI-assisted algorithm to analyze surgical videos of cataract surgeries in Global South, aiming to improve surgical outcomes and training. The algorithm can work with conventional image material and smartphone videos, addressing the need for resource-saving solutions in these countries.
A research team has made a significant breakthrough in understanding the GPR156 receptor protein's role in maintaining auditory function. The study reveals that GPR156 exhibits sustained activity even without external stimuli, highlighting its potential as a target for treating congenital hearing impairments.
The DISCount framework combines AI-powered image analysis with human analysis to quickly deliver reliable estimates of building damage and bird flock size. It has been recognized by the Association for the Advancement of Artificial Intelligence for its social impact, winning an award for best paper on AI for social impact.
Researchers from the University of Houston used spaceborne-monitoring to detect movements and deformations in the Kakhovka Dam years before its collapse. The study highlights the importance of proactive monitoring and remote sensing in ensuring infrastructure safety and integrity.
Researchers developed an AI model to detect viable tumor cells in osteosarcoma patients, improving prognosis predictions. The model showed comparable detection performance to pathologists and reduced inter-assessor variability, enabling timely assessment.
Researchers have introduced a refined method for analyzing brain signals, providing a more detailed understanding of the brain's complex activity. This enhancement enables scientists to better understand how brain activity correlates with different tasks and behaviors.
A new study published in Stroke found that exposure to artificial, bright outdoor nighttime light may increase the risk of cerebrovascular disease and stroke. The research, which analyzed data from over 28,000 adults living in China, suggests that higher levels of outdoor light pollution at night may be a risk factor for these conditions.
A team of researchers has developed the world's first 3D-printed brain phantom, which can be imaged using dMRI. The brain model is made up of microchannels that mimic nerve cells in the brain, allowing for more accurate analysis and research into neurodegenerative diseases.
A mobile app using AI analyzes images of suspected skin lesions and provides guidance on whether they are melanoma or not. The app was tested in primary care and showed promising results, accurately diagnosing melanoma in all cases and determining harmless lesions with a high probability.
Scientists at Karolinska Institutet and Stockholm University have mapped the cellular architecture of MS lesions using advanced methodology. This reveals how immune cells and glial cells interact in the disease.
A new AI model, called Lars, can accurately detect signs of lymph node cancer in 90% of cases, reducing workload for radiologists and increasing access to healthcare. The model was developed using a large dataset of over 17,000 images from 5,000 patients and is based on deep learning technology.
The T2oFu method offers a new approach to quantitative phase and polarization-sensitive tomography, enabling high-contrast images of muscle fibers with implications for diagnosing skeletal myopathies. The technique has been successfully tested on heart tissue samples with cardiac amyloidosis, providing promising results.
Research using historical satellite images shows that methane emissions in Turkmenistan increased following the Soviet Union's collapse, contradicting previous theories. This finding suggests that economic decline led to reduced oversight and more deliberate off-gassing of methane from oil and gas wells.
A novel path choice model elucidates the influence of different attributes on pedestrians' local and global path choices. The study reveals that pedestrians locally perceive and react to environmental attributes like green views, guiding urban planning decisions.
Researchers developed a new approach to root phenotyping using convolutional neural networks, enabling automated total root length estimation from minirhizotron images. The method demonstrates high accuracy and robustness in capturing root growth patterns, offering significant promise for precision agriculture practices.
Researchers at UNIST have developed a method to measure nanometer-sized samples within a transmission electron microscope, utilizing nano-thermometers based on cathodoluminescence spectroscopy. The technique offers improved accuracy and spatial resolution compared to conventional methods.
New research combines images with computer-enabled analysis to tackle biological questions globally. Imageomics aims to improve image classification and analysis using machine learning and computer vision, enabling faster scientific discoveries.
Researchers found that mental representations, as seen in children's and adults' drawings, influence calculation strategies for solving simple arithmetic problems. The study reveals that certain drawing typologies are associated with effective calculation strategies, regardless of age or experience. This discovery opens up new perspect...
Researchers from OIST used X-ray micro-CT to study a 38 million-year-old termite pair trapped in amber, revealing a male and female in tandem running behavior. The discovery provides new insights into the fidelity of behavior fossilization in amber.
A team of UCF scientists used the James Webb Space Telescope to analyze the elemental composition of a binary duo in the Kuiper Belt, revealing clues about Neptune's formation. The study provides valuable insights into the dynamical history of Neptune and its neighboring objects.
Researchers studied Prorocentrum cordatum to understand its molecular processes, revealing a unique photosynthetic machinery that may help it adapt to changing light conditions. The findings could lead to improved understanding of harmful algal blooms and their role in climate change.
A KAIST team developed an insect-mimicking semiconductor that mimics the optic nerve of insects to detect motion. The device operates at high efficiency and ultra-high speeds, and has been applied to a neuromorphic computing system for predicting vehicle paths. It achieved 92.9% less energy consumption compared to existing technology.
A recent study by Pusan National University scientists discovered the crucial role of PKM gene and EPHA2 pathway in HNSCC development. The research highlights the importance of HPV infection status in shaping the tumor microenvironment, enabling precision medicine for targeted treatment.
Researchers decode underlying mechanisms of DCM, hippocampal neurotoxicity, and dysbiosis mediated AD progression using mass spectrometry imaging. The studies found metabolic changes in DCM rat hearts and regulation of CYPs in the hippocampus, providing new perspectives on treatment strategies.
A research group at Chuo University developed a novel non-destructive inspection technique combining multi-functional photo monitoring devices with image data-driven three-dimensional restoration methods. The technique precisely evaluates target objects by compositional identifications and structural reconstructions, providing a breakt...
Researchers used high-resolution techniques to analyze organic material from the early Earth, shedding light on the formation and composition of ancient biomass. The study found evidence of biological origin in microscopically small particles, suggesting a turbulent history of sediment deposits.
Researchers developed a toolkit to translate neuroimaging data into audiovisual representations, enabling scientists to explore brain activity patterns in real time. The tool uses piano sounds for neural activity and violin sounds for blood flow, allowing viewers to discern coupled relationships between the two.
Researchers have developed a novel 'nano active control platform' to control excitons and trions, providing valuable insights into the optical properties of two-dimensional semiconductors. The breakthrough discovery enables real-time analysis of nano-light properties with exceptional spatial resolution.
A study published in Global Change Biology found that low deep-water oxygen concentrations lead to increased algae growth and further oxygen declines. This positive feedback cycle can result in frequent algal blooms, disrupting lake ecosystems and human health.
Researchers have confirmed a new method for precise body composition analysis using 3D surface scans and dual-energy X-ray absorptiometry. This approach yields accurate measurements of fat, lean muscle, and bone, surpassing commercial software in clinical settings.
The commercial space sector has seen significant growth, with over 2,660 satellites launched into orbit in recent years. International collaborations are also expanding, enabling diverse perspectives and new ideas to emerge in science and space exploration.
A comprehensive online tool, Metrics Reloaded, has been developed to select suitable metrics for AI-assisted image analysis. The tool helps physicians and scientists identify relevant variables for their specific task, increasing understanding of key problems in AI-assisted image analysis.
Researchers at Aston University have discovered that aging skin exhibits distinct optical properties under polarised laser light. This finding could lead to the development of non-invasive light-based techniques for early detection and monitoring of skin conditions, including cancer.
A new tumor spatial mapping tool will help clinicians assess the aggressiveness of cancer and personalize treatment. The tool maps the functional state of oncoproteins onto tumour images, allowing for more accurate diagnosis and informed treatment decisions.
A study found that white actors are still overrepresented on American film posters, with Black and Asian actors gaining ground in recent years. The research suggests that non-white actors tend to appear in minor roles or films related to their ethnicity.
Researchers at the University of São Paulo found evidence of a tropical island with rich mineral deposits, including cobalt and nickel, in the South Atlantic Ocean. The team's analysis of seafloor sediment samples suggests the area was once home to vegetation and had volcanic activity between 30-40 million years ago.
A Brazilian study developed a method using AI to identify crop-livestock integration areas from satellite images. The approach can benefit agriculture by optimizing land use, diversifying farming activities, and encouraging sustainable practices.
Researchers developed a novel deep learning method to study crystal structure and molecular interactions of perchlorate salts. The analysis revealed that the explosives' nature is linked to chemical bonding and intermolecular interactions.