Add BrightSurf on Google Email

Novel technique distinguishes between types of oral bone lesion based on MRI scan image texture

Researchers used MRI scans and texture analysis to differentiate between two types of benign oral bone lesions, ameloblastomas and odontogenic keratocysts. The study found that certain pixel and voxel organizational parameters in the MRI images were statistically significant, enabling more accurate diagnosis and treatment planning.

Mothers’ alcohol consumption before and during pregnancy is linked to changes in children’s face shapes

A recent study published in Human Reproduction found a significant association between prenatal alcohol exposure and changes in children's facial features. The research used AI to analyze three-dimensional images of children's faces at ages nine and thirteen, revealing that mothers' alcohol consumption before and during pregnancy can h...

SourceEuropean Society of Human Reproduction and Embryology·JournalHuman Reproduction·TypeObservational study·DateFeb 15, 2023

Technology development could bring Raman microscopy to the clinic

Researchers developed high-throughput Raman microscope for rapid large-area imaging hundreds of times faster than traditional approach. The new technique enables label-free molecular analysis and multiplex chemical imaging, holding promise for efficient medical diagnoses and drug development.

SourceOptica·JournalBiomedical Optics Express·DateFeb 7, 2023

Researchers focus AI on finding exoplanets

New research from the University of Georgia reveals that artificial intelligence can be used to find planets outside our solar system. Machine learning can analyze environments where planets are still forming, helping scientists overcome difficulties such as distance and data thickness.

SourceUniversity of Georgia·JournalThe Astrophysical Journal·DateFeb 7, 2023

A faster, more accurate 3D modelling tool recreates a landscape’s digital twin down to the pixel level

The new automated method, called HybridFlow, uses large-scale aerial images to produce precise 3D models of cityscapes and landscapes. This technology has potential applications in natural disaster risk assessment and mitigation, enabling informed decision-making and evaluation of risk-mitigating factors.

SourceConcordia University·JournalScientific Reports·TypeComputational simulation/modeling·DateFeb 7, 2023

Accepting anxiety for peace of mind

A mindfulness-based intervention program significantly decreased subjective anxiety and improved emotional regulation in AN patients. The study found changes in brain regions involved in anxiety, emotion arousal, and self-referential processing.

SourceKyoto University·JournalBJPsych Open·TypeExperimental study·DateFeb 3, 2023

Color images from the shadow of a sample

Scientists at Göttingen University have created a novel approach to produce X-ray images in color from a single exposure, eliminating the need for focusing and scanning. This breakthrough method uses an X-ray color camera and a specially structured plate to capture the intensity pattern of fluorescing atoms in a sample.

SourceUniversity of Göttingen·JournalOptica·TypeExperimental study·DateJan 24, 2023

Dinosaur teeth reveal what they didn’t eat

Researchers used dental microwear texture analysis to infer feeding habits of large theropods, including T. rex and Allosaurus. The study found that these dinosaurs did not eat bones as frequently as thought, with juveniles having a different feeding behavior.

SourceUniversity of Tokyo·JournalPalaeontology·TypeImaging analysis·DateDec 9, 2022

CABBI team adds powerful new dimension to phenotyping next-gen bioenergy crop

Researchers at CABBI used unmanned aerial vehicles with machine learning methods to select the best candidate genotypes in miscanthus breeding programs. The new method leverages high-resolution aerial imagery and three-dimensional neural networks to estimate crop traits such as flowering time, height, and biomass production.

Common approach to demystify black box AI not ready for prime time

A new study published in Nature on saliency heat maps in medical imaging reveals that these tools consistently underperform human radiologists in image assessment and identifying pathological lesions. The researchers caution that saliency-based heat maps should be further refined before being widely adopted in clinical AI models.

SourceHarvard Medical School·JournalNature Machine Intelligence·TypeComputational simulation/modeling·DateOct 10, 2022

Media coverage of hurricanes reinforces images of people of color as victims, study finds

A new study from the University of Kansas reveals that media coverage of Hurricane Harvey in 2017 perpetuated racial biases in image presentation, showing people of color as displaced migrants, women as damsels in distress, and white men as saviors. The study highlights how these representations reinforce cultural narratives and stereo...

SourceUniversity of Kansas·JournalCritical Studies in Media Communication·TypeObservational study·DateOct 10, 2022

Scientists publish perspective paper exploring use of artificial intelligence in skin diseases

A team of scientists from China published a perspective paper on the use of AI in skin diseases, highlighting its potential to assist clinicians. They propose several recommendations to improve AI-assisted diagnosis systems, including establishing a robust database and adapting algorithms to existing real-world databases.

SourceHealth Data Science·JournalHealth Data Science·TypeCommentary/editorial·DateSep 22, 2022

CT-derived body composition with deep learning predicts cardiovascular events

A large retrospective study found that visceral fat area from fully automated and normalized abdominal CT analysis predicts subsequent myocardial infarction or stroke in Black and White patients. The study suggests that body composition analysis using machine learning could be widely adopted to add prognostic utility to clinical practice.

SourceAmerican Roentgen Ray Society·JournalAmerican Journal of Roentgenology·TypeImaging analysis·DateAug 31, 2022

Technique using light and artificial intelligence is effective in selecting immature soybean seeds

A team of Brazilian researchers has developed a novel technique using light and artificial intelligence to identify the maturity stages of soybean seeds. The method utilizes chlorophyll fluorescence and machine learning algorithms to classify commercial seeds with high accuracy. This innovation avoids destroying seeds, which are then c...

SourceFundação de Amparo à Pesquisa do Estado de São Paulo·JournalFrontiers in Plant Science·DateAug 25, 2022

The resolution of a molecular orchestra

A new photoswitching fingerprint analysis overcomes the sub-10 nm resolution barrier in super-resolution microscopy, enabling the imaging of dynamic interactions with other molecules in cells. This breakthrough reveals molecular functions and architectures at the nanoscale, shedding light on cellular processes such as learning and memory.

SourceUniversity of Würzburg·JournalNature Methods·TypeExperimental study·DateAug 2, 2022

Moffitt researchers create software program that allows simultaneous viewing of tissue images through dimensionality reduction

A new software program, Mistic, allows for the simultaneous viewing of tissue images through dimensionality reduction methods. The software enables the extraction of data from multiplexed images, facilitating the understanding of cancer biology and the development of new therapies.

SourceH. Lee Moffitt Cancer Center & Research Institute·JournalPatterns·TypeImaging analysis·DateJul 21, 2022

Russian scientists teach AI to analyze emotions of participants at online events

Researchers developed a neural network algorithm that recognizes emotions and engagement from video images of faces, outperforming existing models in accuracy. The system can be integrated into video conferencing tools and online learning systems to analyze participant engagement and emotions.

SourceNational Research University Higher School of Economics·JournalIEEE Transactions on Affective Computing·DateJul 4, 2022

Unique blend of comics and humor is key to success of public awareness posters in Singapore, finds Singapore-US researchers

The study found that the use of comics for humour, visual-verbal interplay, informality, simple narrative plots, and exaggerated personalities contributed to the campaign's enduring success. The researchers argue that humour is a powerful discursive strategy to educate the public, making content relatable while addressing taboo topics.

SourceNanyang Technological University·JournalDiscourse Context & Media·TypeMeta-analysis·DateJun 28, 2022

Let machines do the work: Automating semiconductor research with machine learning

Researchers use machine learning to automatically analyze Reflection High-Energy Electron Diffraction (RHEED) data, enabling faster and more efficient discovery of new materials. The study focused on surface superstructures in thin-film silicon surfaces and identified optimal synthesis conditions using non-negative matrix factorization.

SourceTokyo University of Science·JournalScience and Technology of Advanced Materials Methods·TypeExperimental study·DateJun 16, 2022