New dog, old tricks: New AI approach yields ‘athletically intelligent’ robotic dog

A doglike robot can navigate unknown obstacles using a simple algorithm that encourages forward progress with minimal effort.

Video Credit: Shanghai Qi Zhi Institute/Stanford University

With a simplified machine learning technique, AI researchers created a real-world “robodog” able to leap, climb, crawl, and squeeze past physical barriers as never before.

Someday, when quakes, fires, and floods strike, the first responders might be packs of robotic rescue dogs rushing in to help stranded souls. These battery-powered quadrupeds would use computer vision to size up obstacles and employ doglike agility skills to get past them.

Toward that noble goal, AI researchers at Stanford University and Shanghai Qi Zhi Institute say they have developed a new vision-based algorithm that helps robodogs scale high objects, leap across gaps, crawl under thresholds, and squeeze through crevices – and then bolt to the next challenge. The algorithm represents the brains of the robodog.

“The autonomy and range of complex skills that our quadruped robot learned is quite impressive,” said Chelsea Finn, assistant professor of computer science and senior author of a new peer-reviewed paper announcing the teams’ approach to the world, which will be presented at the upcoming Conference on Robot Learning. “And we have created it using low-cost, off-the-shelf robots – actually, two different off-the-shelf robots.”

Predictions of the effect of drugs on individual cells are now possible

How differently do various cancer cells respond to the effects of drugs? A new method from Zurich researchers now makes it possible to accurately predict the effect on individual cells.
Photo Credit: National Cancer Institute

Experts from ETH Zurich, the University of Zurich, and University Hospital Zurich have used machine learning to jointly create a innovative method. This new approach can predict how individual cells react to specific treatments, offering hope for more accurate diagnoses and therapeutics.

Cancer is triggered by changes in cells that lead to the proliferation of pathogenic tumor cells. In order to find the most effective combination and dosage of drugs, it is advantageous if physicians can see inside the body, so to speak, and determine what effect the drugs will have on individual cells.

An interdisciplinary research team of biomedical and computer scientists from ETH Zurich, the University of Zurich, and the University Hospital Zurich has now developed a machine learning approach that allows such cell changes and drug effects to be modelled and predicted with much greater accuracy and nuance than before.

AI copilot enhances human precision for safer aviation

With Air-Guardian, a computer program can track where a human pilot is looking (using eye-tracking technology), so it can better understand what the pilot is focusing on. This helps the computer make better decisions that are in line with what the pilot is doing or intending to do.
Illustration Credit: Alex Shipps/MIT CSAIL via Midjourney

Imagine you're in an airplane with two pilots, one human and one computer. Both have their “hands” on the controllers, but they're always looking out for different things. If they're both paying attention to the same thing, the human gets to steer. But if the human gets distracted or misses something, the computer quickly takes over.

Meet the Air-Guardian, a system developed by researchers at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). As modern pilots grapple with an onslaught of information from multiple monitors, especially during critical moments, Air-Guardian acts as a proactive copilot; a partnership between human and machine, rooted in understanding attention.

But how does it determine attention, exactly? For humans, it uses eye-tracking, and for the neural system, it relies on something called "saliency maps," which pinpoint where attention is directed. The maps serve as visual guides highlighting key regions within an image, aiding in grasping and deciphering the behavior of intricate algorithms. Air-Guardian identifies early signs of potential risks through these attention markers, instead of only intervening during safety breaches like traditional autopilot systems. 

Deciphering the secrets of the brain

Adrian Wanner is delighted with the exceptional international recognition from the US National Institute of Health (NIH).
Photo Credit: Scanderbeg Sauer Photography

PSI researchers are to receive funding from the US National Institutes of Health (NIH) as part of its “BRAIN Initiative”. Their aim is to produce a comprehensive map of a mouse’s brain.

Unlocking the secrets of the brain, especially its architecture and wiring, is one of the big challenges in modern life sciences. That is why the National Institutes of Health (NIH) in the USA, one of the world’s largest research agencies, has included this in its program. As part of the NIH BRAIN Initiative, a Swiss researcher has now been awarded a major grant of up to 2.6 million US dollars. The neurobiologist Adrian Wanner, a group leader at the Paul Scherrer Institute PSI, is the project’s principal investigator. Andreas Schaefer from the Francis Crick Institute in London is also closely involved.

The NIH’s decision to invest such a large sum in a project at a Swiss institute demonstrates the exceptional competitiveness of Swiss researchers and confirms PSI’s position as a center for world-class research. “For a young research group leader to receive such a large grant, especially from another country, is by no means commonplace; it testifies to his great scientific talent and the confidence that the international community has in Switzerland as a research location,” says Gebhard Schertler, Head of the Department of Biology and Chemistry, who is delighted with the good news from the United States. Schaefer adds, “This funding will further strengthen the existing collaboration between our groups and institutes.”

Researchers Develop AI Model to Improve Tumor Removal Accuracy During Breast Cancer Surgery

Radiology-specific
Image Credit: Courtesy of UNC School of Medicine

Kristalyn Gallagher, DO, Kevin Chen, MD, and Shawn Gomez, EngScD, in the UNC School of Medicine have developed an AI model that can predict whether or not cancerous tissue has been fully removed from the body during breast cancer surgery.

Artificial intelligence (AI) and machine learning tools have received a lot of attention recently, with the majority of discussions focusing on proper use. However, this technology has a wide range of practical applications, from predicting natural disasters to addressing racial inequalities and now, assisting in cancer surgery.

A new clinical and research partnership between the UNC Department of Surgery, the Joint UNC-NCSU Department of Biomedical Engineering, and the UNC Lineberger Comprehensive Cancer Center has created an AI model that can predict whether or not cancerous tissue has been fully removed from the body during breast cancer surgery. Their findings were published in Annals of Surgical Oncology.

New way of identifying proteins supports drug development

The illustration shows how different areas of PRC2 protein (the one on the right side) binds to survivin. The color pixel diagram shows binding strength to survivin. The bright pink pixels are the strongest binders.
Illustration Credit: Atsarina Larasati Anindya

All living cells contain proteins with different functions, depending on the type of cell. Researchers at the University of Gothenburg have discovered a way to identify proteins without even looking at their structure. Their method is faster, easier and more reliable than previous methods.

Currently, the general view is that each protein’s structure is what controls its function in cells. The atomic sequences, meaning how the atoms are arranged in the proteins, create the protein’s structure and shape. But there are many proteins that lack a well-defined structure.

Researcher Gergely Katona has developed a new method where proteins are scanned based on the number of amino acids (or the number of different atoms) they contain in order to identify them and their function instead of identifying them based on their structure. With this scanning method, the researchers were able to predict relatively reliably which combination of amino acids is needed to bind to the protein survivin. The outcome was a reliability of about 80 per cent, which is better than when you use the protein’s primary structures for identification. The results are now published in the scientific journal iScience.

AI helps show how the brain’s fluids flow

A video shows a perivascular space (area within white lines) into which the researchers injected tiny particles. The particles (shown as moving dots) are trailed by lines which indicate their direction. Having measured the position and velocity of the particles over time, the team then integrated this 2D video with physics-informed neural networks to create an unprecedented high-resolution, 3D look at the brain’s fluid flow system.
Video Credit: Douglas Kelley

New research targets diseases including Alzheimer’s.

A new artificial intelligence-based technique for measuring fluid flow around the brain’s blood vessels could have big implications for developing treatments for diseases such as Alzheimer’s.

The perivascular spaces that surround cerebral blood vessels transport water-like fluids around the brain and help sweep away waste. Alterations in the fluid flow are linked to neurological conditions, including Alzheimer’s, small vessel disease, strokes, and traumatic brain injuries but are difficult to measure in vivo.

A multidisciplinary team of mechanical engineers, neuroscientists, and computer scientists led by University of Rochester Associate Professor Douglas Kelley developed novel AI velocimetry measurements to accurately calculate brain fluid flow. The results are outlined in a study published by Proceedings of the National Academy of Sciences.

AI unlikely to gain human-like cognition, unless connected to real world through robots

Embodying AI in robots so they can interact with the world around them and evolve like the human brain does is the most likely way AI will develop human-like cognition
Photo Credit: Gerd Altmann

Connecting artificial intelligence systems to the real world through robots and designing them using principles from evolution is the most likely way AI will gain human-like cognition, according to research from the University of Sheffield.

• University of Sheffield researchers say artificial intelligence systems are unlikely to gain human-like cognition, unless they’re connected to the real world through robots and designed using principles from evolution 

• Current AI systems, such as ChatGPT, copy some processes in the human brain to use datasets to solve difficult problems, but Sheffield researchers say this form of disembodied AI is unlikely to resemble the complexities of real brain processing no matter how big these datasets become

• Biological intelligence - such as the human brain - is achieved through a specific architecture that learns and improves using its connections to the real world, but this is rarely used in the design of AI

• Embodying AI in robots so they can interact with the world around them and evolve like the human brain does is the most likely way AI will develop human-like cognition

New model offers a way to speed up drug discovery

Researchers can screen more than 100 million compounds in a single day — much more than any existing model.
Photo Credit: Myriam Zilles

Huge libraries of drug compounds may hold potential treatments for a variety of diseases, such as cancer or heart disease. Ideally, scientists would like to experimentally test each of these compounds against all possible targets, but doing that kind of screen is prohibitively time-consuming.

In recent years, researchers have begun using computational methods to screen those libraries in hopes of speeding up drug discovery. However, many of those methods also take a long time, as most of them calculate each target protein’s three-dimensional structure from its amino-acid sequence, then use those structures to predict which drug molecules it will interact with.

Researchers at MIT and Tufts University have now devised an alternative computational approach based on a type of artificial intelligence algorithm known as a large language model. These models — one well-known example is ChatGPT — can analyze huge amounts of text and figure out which words (or, in this case, amino acids) are most likely to appear together. The new model, known as ConPLex, can match target proteins with potential drug molecules without having to perform the computationally intensive step of calculating the molecules’ structures.

AI Predicts Future Pancreatic Cancer

Pancreatic cancer cells
Image Credit: National Cancer Institute

An artificial intelligence tool has successfully identified people at the highest risk for pancreatic cancer up to three years before diagnosis using solely the patients’ medical records, according to new research led by investigators at Harvard Medical School and the University of Copenhagen, in collaboration with VA Boston Healthcare System, Dana-Farber Cancer Institute, and the Harvard T.H. Chan School of Public Health.

The findings, published May 8 in Nature Medicine, suggest that AI-based population screening could be valuable in finding those at elevated risk for the disease and could expedite the diagnosis of a condition found all too often at advanced stages when treatment is less effective and outcomes are dismal, the researchers said. Pancreatic cancer is one of the deadliest cancers in the world, and its toll projected to increase.

Currently, there are no population-based tools to screen broadly for pancreatic cancer. Those with a family history and certain genetic mutations that predispose them to pancreatic cancer are screened in a targeted fashion. But such targeted screenings can miss other cases that fall outside of those categories, the researchers said.

“One of the most important decisions clinicians face day to day is who is at high risk for a disease, and who would benefit from further testing, which can also mean more invasive and more expensive procedures that carry their own risks,” said study co-senior investigator Chris Sander, faculty member in the Department of Systems Biology in the Blavatnik Institute at HMS. “An AI tool that can zero in on those at highest risk for pancreatic cancer who stand to benefit most from further tests could go a long way toward improving clinical decision-making.”

‘Raw’ data show AI signals mirror how the brain listens and learns

Researchers found strikingly similar signals between the brain and artificial neural networks. The blue line is brain wave when humans listen to a vowel. Red is the artificial neural network’s response to the exact same vowel. The two signals are raw, meaning no transformations were needed.
Illustration Credit: Courtesy Gasper Begus

New research from the University of California, Berkeley, shows that artificial intelligence (AI) systems can process signals in a way that is remarkably similar to how the brain interprets speech, a finding scientists say might help explain the black box of how AI systems operate.

Using a system of electrodes placed on participants’ heads, scientists with the Berkeley Speech and Computation Lab measured brain waves as participants listened to a single syllable — “bah.” They then compared that brain activity to the signals produced by an AI system trained to learn English.

“The shapes are remarkably similar,” said Gasper Begus, assistant professor of linguistics at UC Berkeley and lead author on the study published recently in the journal Scientific Reports. “That tells you similar things get encoded, that processing is similar. “

A side-by-side comparison graph of the two signals shows that similarity strikingly.

Study shows how machine learning can identify social grooming behavior from acceleration signals in wild baboons

Photo Credit: Charl Durand

Scientists from Swansea University and the University of Cape Town have tracked social grooming behavior in wild baboons using collar-mounted accelerometers.

The study, published in the journal Royal Society Open Science, is the first to successfully calculate grooming budgets using this method, which opens a whole avenue of future research directions.

Using collars containing accelerometers built at Swansea University, the team recorded the activities of baboons in Cape Town, South Africa, identifying and quantifying general activities such as resting, walking, foraging and running, and also the giving and receiving of grooming.

A supervised machine learning algorithm was trained on acceleration data matched to baboon video recordings and successfully recognized the giving and receiving grooming with high overall accuracy.

The team then applied their machine learning model to acceleration data collected from 12 baboons to quantify grooming and other behaviors continuously throughout the day and night-time.

Personalized Gut Microbiome Analysis for Colorectal Cancer Classification with Explainable AI

Explainable AI offers a promising solution for finding links between diseases and certain species of gut bacteria, finds a research team at Tokyo Tech. Using a concept borrowed from game theory, the researchers developed a framework that reveals which bacterial species are closely associated with colorectal cancer in individual subjects, providing a more reliable way to find and characterize disease subgroups and identify biomarkers in the gut microbiome.

The gut microbiome comprises a complex population of different bacterial species that are essential to human health. In recent years, scientists across several fields have found that changes in the gut microbiome can be linked to a wide variety of diseases, notably colorectal cancer (CRC). Multiple studies have revealed that a higher abundance of certain bacteria, such as Fusobacterium nucleatum and Parvimonas micra, is typically associated with CRC progression.

AI Tool Predicts Colon Cancer Survival, Treatment Response

New AI tool accurately predicts both overall survival and disease-free survival after colorectal cancer diagnosis.
Image Credit: bodymybody

A new artificial intelligence model designed by researchers at Harvard Medical School and National Cheng Kung University in Taiwan could bring much-needed clarity to doctors delivering prognoses and deciding on treatments for patients with colorectal cancer, the second deadliest cancer worldwide.

Solely by looking at images of tumor samples — microscopic depictions of cancer cells — the new tool accurately predicts how aggressive a colorectal tumor is, how likely the patient is to survive with and without disease recurrence, and what the optimal therapy might be for them.

Having a tool that answers such questions could help clinicians and patients navigate this wily disease, which often behaves differently even among people with similar disease profiles who receive the same treatment — and could ultimately spare some of the 1 million lives that colorectal cancer claims every year.

AI predicts enzyme function better than leading tools

An Illinois research team created an AI tool to predict an enzyme’s function from its sequence using the campus network and resource group servers. Pictured, from left: Tianhao You, Haiyang (Ocean) Cui, Huimin Zhao and Guangde Jiang.   
Photo Credit: Fred Zwicky

A new artificial intelligence tool can predict the functions of enzymes based on their amino acid sequences, even when the enzymes are unstudied or poorly understood. The researchers said the AI tool, dubbed CLEAN, outperforms the leading state-of-the-art tools in accuracy, reliability and sensitivity. Better understanding of enzymes and their functions would be a boon for research in genomics, chemistry, industrial materials, medicine, pharmaceuticals and more.

“Just like ChatGPT uses data from written language to create predictive text, we are leveraging the language of proteins to predict their activity,” said study leader Huimin Zhao, a University of Illinois Urbana-Champaign professor of chemical and biomolecular engineering. “Almost every researcher, when working with a new protein sequence, wants to know right away what the protein does. In addition, when making chemicals for any application – biology, medicine, industry – this tool will help researchers quickly identify the proper enzymes needed for the synthesis of chemicals and materials.”

The researchers will publish their findings in the journal Science and make CLEAN accessible online March 31.

Machine learning models rank predictive risks for Alzheimer’s disease

Xiaoyi Raymond Gao, PhD Associate Professor
Photo Credit: Courtesy of Ohio State University

Once adults reach age 65, the threshold age for the onset of Alzheimer’s disease, the extent of their genetic risk may outweigh age as a predictor of whether they will develop the fatal brain disorder, a new study suggests. 

The study, published recently in the journal Scientific Reports, is the first to construct machine learning models with genetic risk scores, non-genetic information and electronic health record data from nearly half a million individuals to rank risk factors in order of how strong their association is with eventual development of Alzheimer’s disease.

Researchers used the models to rank predictive risk factors for two populations from the UK Biobank: White individuals aged 40 and older, and a subset of those adults who were 65 or older. 

Results showed that age – which constitutes one-third of total risk by age 85, according to the Alzheimer’s Association – was the biggest risk factor for Alzheimer’s in the entire population, but for the older adults, genetic risk as determined by a polygenic risk score was more predictive. 

“We all know Alzheimer’s disease is a later-onset disease, so we know age is an important risk factor. But when we consider risk only for people age 65 or older, then genetic information captured by a polygenic risk score ranks higher than age,” said lead study author Xiaoyi Raymond Gao, associate professor of ophthalmology and visual sciences and of biomedical informatics in The Ohio State University College of Medicine. “That means it’s really important to consider genetic information when we work on Alzheimer’s disease.” 

Can Artificial Intelligence Predict Spatiotemporal Distribution of Dengue Fever Outbreaks with Remote Sensing Data?

Image Credit: Sophia University
Full Size Image

Researchers train machine learning model with climatic and epidemiology remote sensing data to predict the spatiotemporal distribution of disease outbreaks

Cases of dengue fever and other zoonotic diseases will keep increasing owing to climate change, and prevention via early warning is one of our best options against them. Recently, researchers combined a machine learning model with remote sensing climatic data and information on past dengue fever cases in Chinese Taiwan, with the aim of predicting likely outbreak locations. Their findings highlight the hurdles to this approach and could facilitate more accurate predictive models.

Outbreaks of zoonotic diseases, which are those transmitted from animals to humans, are globally on the rise owing to climate change. In particular, the spread of diseases transmitted by mosquitoes is very sensitive to climate change, and Chinese Taiwan has seen a worrisome increase in the number of cases of dengue fever in recent years.

Like for most known diseases, the popular saying “an ounce of prevention is worth a pound of cure” also rings true for dengue fever. Since there is still no safe and effective vaccine for all on a global scale, dengue fever prevention efforts rely on limiting places where mosquitoes can lay their eggs and giving people an early warning when an outbreak is likely to happen. However, thus far, there are no mathematical models that can accurately predict the location of dengue fever outbreaks ahead of time.

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

With no insight into how Al algorithms work or what influences their results, the “black box” nature of AI technology raises important questions over trustworthiness.
Illustration Credit: Gerd Altmann

An international team led by UNIGE, HUG and NUS has developed an innovative method for evaluating AI interpretability methods, with the aim of deciphering the basis of AI reasoning and possible biases.

 Researchers from the University of Geneva (UNIGE), the Geneva University Hospitals (HUG), and the National University of Singapore (NUS) have developed a novel method for evaluating the interpretability of artificial intelligence (AI) technologies, opening the door to greater transparency and trust in AI-driven diagnostic and predictive tools. The innovative approach sheds light on the opaque workings of so-called "black box" AI algorithms, helping users understand what influences the results produced by AI and whether the results can be trusted. This is especially important in situations that have significant impacts on the health and lives of people, such as using AI in medical applications. The research carries particular relevance in the context of the forthcoming European Union Artificial Intelligence Act which aims to regulate the development and use of AI within the EU. The findings have recently been published in the journal Nature Machine Intelligence.

“Denoising” a Noisy Ocean

Study lead author Ella Kim (pink helmet) helps deploy a HARP instrument package.
Photo Credit: Ana Širović

Come mating season, fishes off the California coast sing songs of love in the evenings and before sunrise. They vocalize not so much as lone crooners but in choruses, in some cases loud enough to be heard from land. It’s a technique of romance shared by frogs, insects, whales, and other animals when the time is right.

For most of these vocal arrangements, the choruses are low-frequency. They’re hard to distinguish from the sounds of ships passing in the night among others.

Biologists, however, have long been interested in listening in on them in the name of understanding fish behavior toward an ultimate goal: They can help preserve fish populations and ocean health by identifying spawning seasons to inform fisheries management.

Now scientists at Scripps Institution of Oceanography at UC San Diego and colleagues have developed a way for computers to sift through sounds collected by field acoustic recording packages known as HARPs and process them faster than even the most trained human analysts. The method represents a major advance in the field of signal processing with uses beyond marine environments.

AI offers ‘paradigm shift’ in Stanford study of brain injury

Models discovered by the Constitutive Artificial Neural Network outperform existing models for brain tissue.
Image Credit: Ellen Kuhl

By helping researchers choose among thousands of available computational models of mechanical stress on the brain, AI is yielding powerful new insight on traumatic brain injury.

From the gridiron to the battlefield, the study of traumatic brain injury has exploded in recent years. Crucial to understanding brain injury is the ability to model the mechanical forces that compress, stretch, and twist the brain tissue and cause damage that ranges from fleeting to fatal.

Researchers at Stanford University now say they have tapped artificial intelligence to produce a profoundly more accurate model of how deformations translate into stresses in the brain and believe that their approach could reveal a more definitive understanding of when and why concussion sometimes leads to lasting brain damage, and other times not.

“The problem in brain modeling to date is that the brain is not a homogeneous tissue – it’s not the same in every part of the brain. Yet, trauma is often pervasive,” said Ellen Kuhl, professor of mechanical engineering, director of the Living Matter Lab, and senior author of a new study appearing in the journal, Acta Biomaterialia. “The brain is also ultrasoft, much like Jell-O, which makes both testing and modeling physical effects on the brain very challenging.”