Toggle light / dark theme

Using AI to improve standard-of-care cardiac imaging

Heart disease is the leading cause of adult death worldwide, making cardiovascular disease diagnosis and management a global health priority. An echocardiogram, or cardiac ultrasound, is one of the most commonly used imaging tools employed by physicians to diagnose a variety of heart diseases and conditions.

Most standard echocardiograms provide two-dimensional visual images (2D) of the three-dimensional (3D) cardiac anatomy. These echocardiograms often capture hundreds of 2D slices or views of a beating heart that can enable physicians to make clinical assessments about the function and structure of the heart.

To improve diagnostic accuracy of cardiac conditions, researchers from UC San Francisco set out to determine whether deep neural networks (DNNs), a type of AI algorithm, could be re-designed to better capture complex 3D anatomy and physiology from multiple imaging views simultaneously. They developed a new “multiview” DNN structure—or architecture—to enable it to draw information from multiple imaging views at once, rather than the current approach of using only a single view. They then trained demonstration DNNs using this architecture to detect disease states for three cardiovascular conditions: left and right ventricular abnormalities, diastolic dysfunction, and valvular regurgitation.

How Zinc Protects Injured Arteries From Accelerated Aging

Researchers publishing in Aging Cell have discovered that the nuclei of the cells that line injured arteries quickly become misshapen and that this leads to accelerated cellular senescence. Delivering zinc to these cells partially alleviates this dysmorphism.

Two seemingly unrelated concepts

This paper begins with a discussion of two different concepts that, on the surface, appear to be unrelated. First, the researchers discuss vascular damage, particularly in the context of surgeries; even minimally invasive procedures that involve cutting, scraping, or burning arteries must cause some level of damage. This includes such procedures as catheter implantation as a treatment for heart disease [1] and the resection of cancerous tumors [2].

Infant Heart Surgery Mends Brain Networks Too

Infants born with congenital heart disease (CHD) often have neurodevelopmental impairments that affect them later in life, including their ability to regulate their emotions and movements. As CHD is the most prevalent congenital disorder in the United States, researchers are eager to find new ways to treat it.

To better understand how CHD affects an infant’s developing nervous system, researchers at Children’s National Hospital used resting-state functional magnetic resonance imaging (rs-fMRI) to evaluate how healthy infants and those with CHD differed. They recently reported in the Journal of Neuroscience that babies with CHD had altered brain activity in their sensorimotor and limbic networks, but after neonatal heart surgery, these brain networks looked more like those of healthy children.

“Using fMRI, we can identify brain networks that are vulnerable to altered oxygen and blood flow from congenital heart disease, which could help guide interventions to improve care for children,” said Jung-Hoon Kim, a brain researcher at Children’s National Hospital and a coauthor of the study, in a press release.

In their study, the researchers analyzed rs-fMRI data from 448 neonates. They first analyzed publicly available data from the Developing Human Connectome Project, which contains a large amount infant brain development MRI data.3 They identified 15 different resting state networks, which represented different regions of brain activity, in the healthy neonate brains.

Read More


Babies with congenital heart disease have altered brain activity in regions involved in movement and emotions, but heart surgery restored these brain networks to healthy connectivity.

AI model predicts chemical effects on gene expression, speeding drug discovery

Inside a diseased cell, the genes are in chaos. Some are receiving signals to overproduce a protein. Others are reducing activity to abnormal levels. Up is down and down is up. The right molecule could restore order, reversing dysregulation in specific genes. But finding the ideal compound could require examining millions of chemicals for their influence on hundreds or thousands of genes.

An MSU-led team of researchers has demonstrated a better way. Using machine learning trained on enormous amounts of published data, they were able to predict how chemicals will influence gene expression, based solely on the structure of the chemical.

Their study, recently published in the journal Cell, has discovered compounds that are promising for treatment of two difficult diseases: the most aggressive form of liver cancer and a chronic lung disease with no curative options.

Nano 3D metallic parts turn out to be surprisingly strong despite defects

Scientists at Caltech have figured out how to precisely engineer tiny three-dimensional (3D) metallic pieces with nanoscale dimensions. The process can work with any metal or metal alloy and yields components of surprising strength despite having a porous and defect-ridden microstructure, making it potentially useful in a wide range of applications, including medical devices, computer chips, and equipment needed for space missions.

The scientists describe their method in a paper published in the journal Nature Communications. The work was completed in the lab of Julia R. Greer, the Ruben F. and Donna Mettler Professor of Materials Science, Mechanics and Medical Engineering at Caltech, and Huajian Gao of Tsinghua University in Beijing.

The researchers use a technique called two-photon lithography that allows them to sequentially build an object of a desired size and shape by carefully controlling the geometry at the level of individual voxels, the smallest distinguishable volumes, or features, in a 3D image. Beginning with a light-sensitive liquid, the scientists use a tightly focused femtosecond laser beam—a femtosecond is 1 quadrillionth of a second—to build a desired shape out of a gel-like material called hydrogel. After infusing the miniature hydrogel sculpture with metallic salts, such as copper nitrate or nickel nitrate, they heat the structure twice in a specialized furnace to produce a shrunken metallic replica of the original shape.

A ‘consortium’ of bacteria cooperates to eat phthalate plasticizers that single microbes can’t stomach

Plastic trash has reached the world’s most remote locations, from the bottom of the Mariana Trench to the summit of Everest. Hundreds of plastic-eating microbes that could help us clean up have been discovered over the past quarter of a century, but there is a long way to go before they can be put to work in natural environments: Microbial digestion of plastic is still slow, requires high temperatures, and only proceeds efficiently in bioreactors. Moreover, most plastic-eating microbes discovered so far can only digest a single kind of plastic.

One solution would be to combine different microbes to tackle plastic pollution as a team. This allows them to share tasks, compensate for each other’s weaknesses, and continue working even when environmental conditions change.

Now, scientists in Germany have discovered such a synergistic “consortium” of plastic-eating bacteria, which can eat phthalate esters (PAEs)—plasticizers that are often found in building materials, food packages, and personal care products, but have been implicated in hormonal, metabolic, and developmental disorders and some cancers. The results are published in Frontiers in Microbiology.

Exercise Triggers Memory-Related ‘Brain Ripples’, Study Finds

Exercise works wonders throughout the human body, including the brain.

Research suggests an array of neurological benefits, such as reducing the brain’s biological age, enhancing learning and memory, and protecting against dementia.

Now, a new study offers one of the clearest glimpses yet into a suspected mechanism: after a single 20-minute session of light-to-moderate cycling, people showed changes in memory-linked brain activity.

Lifelong behavioral screen reveals an architecture of vertebrate aging

By tracking nearly every movement of a tiny fish’s life from adolescence to death, a new Science study reveals a hidden behavioral blueprint of aging—one that can predict a fish’s age or how long an individual will live.


Mapping behavior of individual vertebrate animals across lifespan could provide an unprecedented view into the lifelong process of aging. We created a platform for high-resolution continuous behavioral tracking of the African killifish across natural lifespan from adolescence to death. We found that animals follow distinct individual aging trajectories. The behaviors of long-lived animals differed markedly from those of short-lived animals, even relatively early in life, and were linked to organ-specific transcriptomic shifts. Machine-learning models accurately inferred age and even forecasted an individual’s future lifespan, given only behavior at a young age. Finally, we found that animals progressed through adulthood in a sequence of stable and stereotyped behavioral stages with abrupt transitions, revealing precise structure for an architecture of aging.

Immune cells regulate eye pressure linked to glaucoma

In the study, researchers tracked fluorescently tagged resident macrophages in mouse eyes. Long-lived resident tissue macrophages were concentrated in the trabecular meshwork and Schlemm’s canal, whereas steady-state monocyte-derived macrophages were abundant around distal vessels.

When they selectively removed these cells, the eye’s drain became clogged, fluid built up, and eye pressure increased and was linked to aberrant extracellular matrix turnover in the resistance-generating tissues of the trabecular meshwork.

“Our findings show that resident macrophages are essential for maintaining healthy eye pressure,” said the author. “Disruption of this system may contribute directly to the development of glaucoma.”

This discovery could lead to the development of future glaucoma treatments. The next step is to do research that identifies these resident macrophages in human eye tissue. ScienceMission sciencenewshighlights.


When the eye’s drainage system clogs, pressure builds up and causes damage. The pressure can lead to glaucoma and vision loss.

New research published in the journal Immunity, reveals that a specialized set of immune cells act as the cleanup crew, pointing to a promising new target for therapies to prevent a major cause of blindness.

/* */