Add BrightSurf on Google Email

THE LANCET ONCOLOGY: First randomised trial finds AI-supported mammography screening is safe and almost halved radiologist workload

A randomized trial involving over 80,000 Swedish women found AI-supported mammography analysis to be as accurate as two breast radiologists working together in detecting breast cancer. The technology also reduced the screen-reading workload by nearly half without increasing false positives.

SourceThe Lancet·JournalThe Lancet Oncology·TypeRandomized controlled/clinical trial·DateAug 1, 2023

Quantitative analysis of cell organelles with artificial intelligence

Researchers developed a convolutional neural network to identify structures in cryo-X-Ray-microscopy data, achieving high accuracy within minutes. The AI-based analysis method enables faster evaluation of 3D X-ray data sets and has potential applications in studying cell responses to environmental influences.

SourceHelmholtz-Zentrum Berlin für Materialien und Energie·JournalProceedings of the National Academy of Sciences·TypeExperimental study·DateJul 18, 2023

Eyes in the skies confirm the end of trash burning in the Maldives

A new AI approach has confirmed that the Maldivian government effectively enforced its ban on open trash burning and single-use plastics, eliminating toxic smoke plumes from satellite imagery. The tool, trained using transfer learning and image segmentation, achieved 88% accuracy in identifying plumes.

SourceDuke University·JournalEnvironmental Science & Technology Letters·TypeExperimental study·DateJul 13, 2023

Hidden details of Egyptian paintings revealed by chemical imaging

Researchers use portable devices to analyze paint composition and layering on ancient Egyptian paintings, revealing alterations made over time. Two paintings from the Theban Necropolis were studied, uncovering changes to a figure's arm and royal items depicted on a portrait of Ramesses II.

SourcePLOS·JournalPLOS ONE·TypeObservational study·DateJul 12, 2023

Generative AI ‘fools’ scientists with artificial data, bringing automated data analysis closer

A new AI technology has been developed to generate artificial scientific data, allowing for faster and more efficient detection of material features. The AI uses generative adversarial networks to incorporate background noise and experimental imperfections into the generated data, making it virtually indistinguishable from real data.

SourceUniversity of Illinois Grainger College of Engineering·Journalnpj Computational Materials·DateJul 11, 2023

Polarized imaging dynamic light scattering measures the nanoparticle size, morphology, as well as their distributions simultaneously, thus finding applications in various fields including catalysts, abrasives, fillers, nanodrugs, and battery materials

Researchers developed a fast and convenient method called polarized imaging dynamic light scattering (PIDLS) to evaluate nanoparticle size, morphology and distributions. The method uses optical sphericity to describe the degree of deviation from spheres and provides statistical morphological distribution.

SourceParticuology·JournalParticuology·DateJul 5, 2023

Genomics- and image-guided subtyping refines characterization of Alzheimer’s disease

Researchers developed a computational technique combining genomic and tau PET imaging data to identify four subtypes of Alzheimer's disease. The integrated approach also revealed top genes associated with each subtype. This personalized diagnostic technique has potential for broad utility across various diseases.

SourceSociety of Nuclear Medicine and Molecular Imaging·JournalJournal of Nuclear Medicine·DateJun 26, 2023

New imaging technique is no last resort

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.

SourceUniversity of Tokyo·JournalScience Advances·TypeExperimental study·DateJun 16, 2023

Fine-tuning 3D lab-grown mini tumors to help predict how patients respond to cancer therapies

Researchers at UCLA have developed a new method to bioprint miniature tumor organoids that can mimic the function and architecture of real tumors. This allows for the accurate measurement of individual organoids, enabling the identification of personalized treatments for people with rare or hard-to-treat cancers.

Reading between the cracks: artificial intelligence can identify patterns in surface cracking to assess damage in reinforced concrete structures

Researchers develop AI-based method to quantify cracking patterns in reinforced concrete structures, enabling more accurate and efficient assessments of structural damage. The approach uses graph theory and machine learning algorithms to create a unique 'fingerprint' for each set of cracks, allowing for quick and consistent evaluations.

SourceDrexel University·JournalComputer-Aided Civil and Infrastructure Engineering·TypeComputational simulation/modeling·DateJun 1, 2023

Reconstructing brain connectivity using 3D images

A team of scientists has developed an automated algorithm to reconstruct the shape of each neuron inside a light microscopy image using deep learning. This breakthrough addresses the challenge of generalizing algorithms across diverse species, brain locations, developmental stages, and microscopy image sets.

SourceTexas A&M University·JournalNature Methods·DateMay 25, 2023

Journal of Pharmaceutical Analysis studies shine the light on advancements in pharmaceutical analytical techniques and overcoming chemoresistance

Researchers have developed new methods to analyze dry-coated drug particles using 3D Raman mapping, which can effectively slow down dissolution rates. Another study introduces a novel technique for detecting complex traditional Chinese medicines, preventing adulteration and counterfeiting.

SourceCactus Communications·JournalJournal of Pharmaceutical Analysis·TypeExperimental study·DateMay 24, 2023

Automated detection of embryonic developmental defects

Researchers developed EmbryoNet, an automated image analysis software that uses AI to detect and classify developmental defects in fish embryos. The software outperforms human experts in terms of speed and accuracy, making it a valuable tool for investigating the mechanisms of drug action and studying embryonic development.

SourceUniversity of Konstanz·JournalNature Methods·DateMay 8, 2023

HIV status is not associated with mpox treatment outcomes in persons using tecovirimat

A cohort study of 196 people treated with tecovirimat found that HIV status did not impact treatment outcomes. Only 22% of participants experienced nonsevere adverse effects, and 4 serious adverse events occurred, with 3 being persons with HIV. The findings contradict previous uncertainty about HIV's role in mpox acquisition.

SourceAmerican College of Physicians·JournalAnnals of Internal Medicine·TypeData/statistical analysis·DateMay 1, 2023

Dynamic 3D structure extraction from HS-AFM images

Computational modeling and simulations allow for reconstruction of 3D conformations with atomistic resolution from topographic resolution-limited AFM images. This enables automated recognition of biomolecular shape changes and feature assignment, including amino acid residue identification on the molecular surface.

SourceKanazawa University·JournalCurrent Opinion in Structural Biology·DateApr 26, 2023

AI algorithm unblurs the cosmos

Researchers have developed an AI algorithm that can remove atmospheric blur from astronomical images, resulting in more accurate scientific measurements and clearer data. The tool produces faster and more realistic images than current methods, producing 38.6% less error compared to classic methods.

SourceNorthwestern University·JournalMonthly Notices of the Royal Astronomical Society·TypeComputational simulation/modeling·DateMar 30, 2023

The shape of your heart matters

Researchers from the Smidt Heart Institute found that individuals with spherical hearts are 31% more likely to develop atrial fibrillation and 24% more likely to develop cardiomyopathy. The study identified four genes associated with cardiomyopathy and a greater risk of developing atrial fibrillation.

Light meets deep learning: computing fast enough for next-gen AI

Researchers developed a novel design for the chip using a crossbar layout, outperforming state-of-the-art photonic counterparts in terms of scalability and technical versatility. The synergy of powerful photonics with the novel crossbar architecture enables next generation neuromorphic computing engines.

SourceInstitute of Electrical and Electronics Engineers·JournalIEEE Journal of Selected Topics in Quantum Electronics·TypeLiterature review·DateMar 22, 2023

Shining a light into the ‘‘black box’’ of AI

An international team developed a novel method for evaluating AI interpretability methods to decipher the basis of AI reasoning and possible biases. The approach helps users understand what influences AI results and whether they can be trusted, especially in medical applications where AI-powered decisions can impact health and lives.

SourceUniversité de Genève·JournalNature Machine Intelligence·TypeNews article·DateMar 21, 2023

Development of technologies for automatic measurement and non-destructive observation of stomata in Arabidopsis thaliana

Researchers developed an image analysis algorithm that can automatically measure Arabidopsis thaliana stomatal aperture with high accuracy and speed. The technology also includes a portable imaging device for non-destructive observation using intact plants, allowing for rapid measurement of subtle changes in stomatal aperture.

SourceInstitute of Transformative Bio-Molecules (ITbM), Nagoya University·JournalPlant and Cell Physiology·TypeExperimental study·DateMar 20, 2023

3D battery imaging reveals the secret real-time life of lithium metal cells

A team from Chalmers University of Technology has developed a method to observe the formation of lithium microstructures in real-time using X-ray tomographic microscopy. This breakthrough aims to improve the safety and capacity of lithium metal batteries, which could replace traditional lithium-ion batteries in the future.

SourceChalmers University of Technology·JournalNature Communications·TypeExperimental study·DateMar 9, 2023

A groundbreaking study reveals the carbon stocks of 10 billion trees in the drylands of sub-Saharan Africa

A groundbreaking study used AI and high spatial resolution imagery to analyze over 300,000 satellite images and identify nearly 10 billion trees in sub-Saharan Africa. The research reveals that tree density and carbon stocks in the arid zone are underestimated, with a total carbon stock of 0.84 billion tonnes.