Connect with us
We’re experimenting with AI-generated content to help deliver information faster and more efficiently.
While we try to keep things accurate, this content is part of an ongoing experiment and may not always be reliable.
Please double-check important details — we’re not responsible for how the information is used.

Brain Injury

“Revolutionizing Multiple Sclerosis Treatment with AI: UCL Researchers’ Breakthrough Tool, MindGlide”

A new artificial intelligence (AI) tool that can help interpret and assess how well treatments are working for patients with multiple sclerosis (MS) has been developed.

Avatar photo

Published

on

Here is the rewritten article:

The University College London (UCL) has made a groundbreaking discovery in the field of multiple sclerosis (MS) research. A new artificial intelligence (AI) tool called MindGlide has been developed by UCL researchers, enabling them to track the effectiveness of MS treatments more accurately than ever before.

MindGlide is an AI-powered platform that uses mathematical models to train computers and perform complex tasks like image recognition. This innovative tool can extract key information from brain images acquired during the care of MS patients, including measuring damaged areas of the brain, highlighting subtle changes such as brain shrinkage and plaques.

MS is a condition where the immune system attacks the brain and spinal cord, causing problems in movement, feelings, or thoughts. In the UK, 130,000 people live with MS, costing the NHS more than £2.9 billion a year. Magnetic Resonance Imaging (MRI) markers are crucial for studying and testing treatments for MS; however, measuring these markers needs different types of specialized MRI scans, limiting the effectiveness of many routine hospital scans.

The researchers tested MindGlide on over 14,000 images from more than 1,000 patients with MS. This task had previously required expert neuro-radiologists to interpret years of complex scans manually – a process that took weeks due to NHS workload constraints. However, for the first time, MindGlide was able to successfully use AI to detect how different treatments affected disease progression in clinical trials and routine care, using images that could not previously be analyzed and routine MRI scan images. The process took just five to 10 seconds per image.

MindGlide performed better than two other AI tools – SAMSEG (a tool used to identify and outline different parts of the brain in MRI scans) and WMH-SynthSeg (a tool that detects and measures bright spots seen on certain MRI scans, important for diagnosing and monitoring conditions like MS) – when compared to expert clinical analysis. MindGlide was 60% better than SAMSEG and 20% better than WMH-SynthSeg for locating brain abnormalities known as plaques or lesions or for monitoring treatment effect.

First author Dr Philipp Goebl (UCL Queen Square Institute of Neurology and UCL Hawkes Institute) said, “Using MindGlide will enable us to use existing brain images in hospital archives to better understand multiple sclerosis and how treatment affects the brain. We hope that the tool will unlock valuable information from millions of untapped brain images that were previously difficult or impossible to understand, immediately leading to valuable insights into multiple sclerosis for researchers and, in the near future, to better understand a patient’s condition through AI in the clinic.”

The results show that it is possible to use MindGlide to accurately identify and measure important brain tissues and lesions even with limited MRI data and single types of scans that aren’t usually used for this purpose. As well as performing better at detecting changes in the brain’s outer layer, MindGlide also performed well in deeper brain areas.

The researchers now hope that MindGlide can be used to evaluate MS treatments in real-world settings, overcoming previous limitations of relying solely on high-quality clinical trial data, which often did not capture the full diversity of people with MS.

Brain Injury

The Hidden Glitch Behind Hunger: Scientists Uncover the Brain Cells Responsible for Meal Memories

A team of scientists has identified specialized neurons in the brain that store “meal memories” detailed recollections of when and what we eat. These engrams, found in the ventral hippocampus, help regulate eating behavior by communicating with hunger-related areas of the brain. When these memory traces are impaired due to distraction, brain injury, or memory disorders individuals are more likely to overeat because they can’t recall recent meals. The research not only uncovers a critical neural mechanism but also suggests new strategies for treating obesity by enhancing memory around food consumption.

Avatar photo

Published

on

The Hidden Glitch Behind Hunger: Scientists Uncover the Brain Cells Responsible for Meal Memories

Imagine forgetting about lunch and suddenly feeling extremely hungry. It’s a common phenomenon that can lead to overeating and disordered eating behaviors. Researchers have now identified a specific group of brain cells called “meal memory” neurons in laboratory rats that could explain why people with memory problems often overeat.

These specialized cells, found in the ventral hippocampus region of the brain, become active during eating and form what scientists call “meal engrams” – sophisticated biological databases that store information about food consumption experiences. An engram is essentially the physical trace a memory leaves behind in the brain, making it possible for us to recall specific details about our meals.

The discovery has significant implications for understanding human eating disorders. Patients with memory impairments, such as those with dementia or brain injuries that affect memory formation, may often consume multiple meals in quick succession because they cannot remember eating. Furthermore, distracted eating – such as mindlessly snacking while watching television or scrolling on a phone – may impair meal memories and contribute to overconsumption.

Researchers used advanced neuroscience techniques to observe the brain activity of laboratory rats as they ate, providing the first real-time view of how meal memories form. They found that meal memory neurons are distinct from other types of brain cells involved in memory formation. When these neurons were selectively destroyed, lab rats showed impaired memory for food locations but retained normal spatial memory for non-food-related tasks.

The study revealed that meal memory neurons communicate with the lateral hypothalamus, a brain region long known to control hunger and eating behavior. When this hippocampus-hypothalamus connection was blocked, the lab rats overate and could not remember where meals were consumed.

The findings have immediate relevance for understanding human eating disorders and could eventually inform new clinical approaches for treating obesity and weight management. Current weight management strategies often focus on restricting food intake or increasing exercise, but the new research suggests that enhancing meal memory formation could be equally important.

“We’re finally beginning to understand that remembering what and when you ate is just as crucial for healthy eating as the food choices themselves,” said Scott Kanoski, professor of biological sciences at the USC Dornsife College of Letters, Arts and Sciences and corresponding author of the study.

In addition to understanding human eating disorders, this research could also inform new strategies for treating obesity and weight management. Current approaches often focus on restricting food intake or increasing exercise, but the new findings suggest that enhancing meal memory formation could be equally important.

By uncovering the brain cells responsible for meal memories, scientists have taken a significant step towards understanding the complex relationships between our brains, bodies, and eating habits. The discovery of these specialized neurons offers new hope for developing effective treatments and interventions to help individuals manage their weight and improve their overall health.

Continue Reading

Brain Injury

Krakencoder Breakthrough: Predicting Brain Function 20x Better Than Past Methods

Scientists at Weill Cornell Medicine have developed a new algorithm, the Krakencoder, that merges multiple types of brain imaging data to better understand how the brain s wiring underpins behavior, thought, and recovery after injury. This cutting-edge tool can predict brain function from structure with unprecedented accuracy 20 times better than past models and even estimate traits like age, sex, and cognitive ability.

Avatar photo

Published

on

By

The breakthroughs in brain mapping technology have brought us closer than ever before to understanding how our minds work. Researchers at Weill Cornell Medicine have developed an algorithm called the Krakencoder, which can accurately predict individual’s functional connectome about 20 times better than previous approaches. This study, published in Nature Methods, utilized imaging data from the Human Connectome Project to align neural activity with its underlying circuitry.

The brain’s wiring and activity patterns are crucial for understanding behavior, identifying biomarkers of disease, predicting outcomes in neurological disorders, and designing personalized interventions. Dr. Amy Kuceyeski, a senior author of the study, explains that regions “wired together” don’t always “fire together.” This patchwork approach to examining the brain has led scientists to develop different methods for processing raw images, resulting in various maps of the brain’s networks.

To overcome this limitation, Dr. Kuceyeski and her team built a tool that can take multiple views of the brain’s underlying system and collapse them into one unified interpretation. This autoencoder program, known as the Krakencoder, compresses and reconstructs more than a dozen different “flavors” of input data.

The researchers trained the Krakencoder on data from over 700 subjects who participated in the Human Connectome Project. They found that the Krakencoder allowed them to take an individual’s structural connectome and correctly predict their functional connectome about 20 times more accurately than previously published approaches.

The combined and compressed representation also predicted an individual’s age, sex, and cognitive performance scores received on tests administered along with imaging scans. This breakthrough has significant implications for understanding how anatomy and physiology give rise to our behaviors and abilities.

In the future, Dr. Kuceyeski and her colleagues plan to combine the Krakencoder with a network modification tool called NeMo that will allow them to examine the connectomes of people whose brains have been damaged by diseases. This approach could identify brain network connections associated with improved cognitive or motor performance and boost the activity of damaged circuits through transcranial magnetic stimulation, potentially hastening recovery.

Continue Reading

Autism

The Brain’s Hidden Patterns: Uncovering the Secret to Flexibility and Stability

A new study challenges a decades-old assumption in neuroscience by showing that the brain uses distinct transmission sites — not a shared site — to achieve different types of plasticity.

Avatar photo

Published

on

By

The Brain’s Hidden Patterns: Uncovering the Secret to Flexibility and Stability

For decades, scientists believed that the brain used a single, shared transmission site for all types of plasticity. However, a groundbreaking study from researchers at the University of Pittsburgh has challenged this assumption, revealing that the brain employs distinct transmission sites to achieve different types of plasticity.

The study, published in Science Advances, offers a deeper understanding of how the brain balances stability with flexibility – a process essential for learning, memory, and mental health. By uncovering the hidden patterns of the brain’s transmission sites, researchers hope to shed light on the underlying mechanisms that govern our thoughts, emotions, and behaviors.

Neurons communicate through synaptic transmission, where one neuron releases chemical messengers called neurotransmitters from a presynaptic terminal. These molecules travel across a microscopic gap called a synaptic cleft and bind to receptors on a neighboring postsynaptic neuron, triggering a response.

Traditionally, scientists believed that spontaneous transmissions (signals that occur randomly) and evoked transmissions (signals triggered by sensory input or experience) originated from one type of canonical synaptic site and relied on shared molecular machinery. However, the research team led by Oliver Schlüter discovered that the brain instead uses separate synaptic transmission sites to carry out regulation of these two types of activity.

The study focused on the primary visual cortex, where cortical visual processing begins. The researchers expected spontaneous and evoked transmissions to follow a similar developmental trajectory, but instead found that they diverged after eye opening.

As the brain began receiving visual input, evoked transmissions continued to strengthen. In contrast, spontaneous transmissions plateaued, suggesting that the brain applies different forms of control to the two signaling modes. To understand why, the researchers applied a chemical that activates otherwise silent receptors on the postsynaptic side, causing spontaneous activity to increase while evoked signals remained unchanged.

This division likely enables the brain to maintain consistent background activity through spontaneous signaling while refining behaviorally relevant pathways through evoked activity. This dual system supports both homeostasis and Hebbian plasticity – the experience-dependent process that strengthens neural connections during learning.

“Our findings reveal a key organizational strategy in the brain,” said Yue Yang, a research associate in the Department of Neuroscience and first author of the study. “By separating these two signaling modes, the brain can remain stable while still being flexible enough to adapt and learn.”

The implications could be broad. Abnormalities in synaptic signaling have been linked to conditions like autism, Alzheimer’s disease, and substance use disorders. A better understanding of how these systems operate in the healthy brain may help researchers identify how they become disrupted in disease.

“Learning how the brain normally separates and regulates different types of signals brings us closer to understanding what might be going wrong in neurological and psychiatric conditions,” said Yang.

Continue Reading

Trending