A new deep learning framework can accurately classify four molecular subgroups of medulloblastoma and predict critical genetic risk factors using magnetic resonance imaging, according to a study by researchers from China. The artificial intelligence model achieved a median accuracy of 77.5% for subgroup classification and up to 91.3% for predicting high-risk genetic alterations. This approach could help clinicians stratify risk and tailor therapies without invasive testing.

Researchers at the National University of Singapore have fabricated ultra-thin memtransistor arrays from two-dimensional transition metal dichalcogenide with controllable Schottky barriers. These arrays are highly uniform, demonstrating low device-to-device variation and provide high performance for image recognition tasks.

Vincent van Gogh, Leonardo da Vinci and Pablo Picasso created some of the most recognizable works of art in history. Their masterpieces have been displayed around the world, admired by millions and inspired generations of artists.

But if artificial intelligence generated an image mimicking their distinct styles and techniques, would their original work still stand apart? And if AI draws on their creations to produce something new, should those artists receive credit for the inspiration their work provides?  

For the first time, a USC-led research team has mapped the genetic architecture of a crucial part of the human brain known as the corpus callosum—the thick band of nerve fibers that connects the brain’s left and right hemispheres. The findings open new pathways for discoveries about mental illness, neurological disorders and other diseases related to defects in this part of the brain. In the new study, published in Nature Communications, the team analyzed brain scans and genetic data from over 50,000 people, ranging from childhood to late adulthood, with the help of a new tool the team created that leverages artificial intelligence. The AI tool finds the corpus callosum in different types of brain MRI scans and automatically takes its measurements. Using this tool, the researchers identified dozens of genetic regions that influence the size and thickness of the corpus callosum and its subregions. The study revealed that different sets of genes govern the area versus the thickness of the corpus callosum—two features that change across the lifespan and play distinct roles in brain function. Several of the implicated genes are active during prenatal brain development, particularly in processes like cell growth, programmed cell death, and the wiring of nerve fibers across hemispheres. These findings provide a genetic blueprint for one of the brain’s most essential communication pathways. By uncovering how specific genes shape the corpus callosum and its subregions, researchers can start to understand why differences in this structure are linked to various mental health and neurological conditions at a molecular level.

It doesn’t take technical expertise to work around the built-in guardrails of artificial intelligence (AI) chatbots like ChatGPT and Gemini, which are intended to ensure that the chatbots operate within a set of legal and ethical boundaries and do not discriminate against people of a certain age, race or gender. A single, intuitive question can trigger the same biased response from an AI model as advanced technical inquiries, according to a team led by researchers at Penn State.