Latest news with #MRI
Tom's Guide
4 hours ago
- Science
- Tom's Guide
Study reveals ChatGPT and other AI systems lag behind humans in one essential skill — and it's entirely unique
ChatGPT seems to be outpacing us at every turn. The AI chatbot is a better poet, mathematician, and coder than we are. But don't worry, researchers at the University of Amsterdam have identified a point where AI lags behind humans and it's all to do with a simple concept our brains grapple with on a daily basis. When you see a mountain path, a busy road or meandering river, your brain can instantly determine how to navigate it, whether that be by walking, swimming, cycling or even arriving at the conclusion it's not possible to pass. This decision-making process is possible because of unique brain patterns. Normally, AI is pretty good at replicating human decision-making, but not in this case. "AI models turned out to be less good at this and still have a lot to learn from the efficient human brain," said Iris Groen, a computational neuroscientist who led the study. The team utilised MRI scanners to try to understand what happens in the brain in these navigational situations. Brain scans were taken while participants looked at various photos of both indoor and outdoor environments. Each participant was told to use a button, indicating if the image invited them to walk, cycle, drive, swim, boat, or climb. While they were set this task, their brains were analysed. 'We wanted to know: when you look at a scene, do you mainly see what is there, such as objects or colours, or do you also automatically see what you can do with it,' says Groen. Get instant access to breaking news, the hottest reviews, great deals and helpful tips. The answer, they found, was both. Participants' brain activity showed that they recognised both what was in the image and how to interact with it. 'Even if you do not consciously think about what you can do in an environment, your brain still registers it,' says Groen. The team of scientists wanted to see how well AI algorithms compared to the human brain in this test. They used image recognition models and GPT-4. In the tests, they were worse at predicting possible actions. "When trained specifically for action recognition, they could somewhat approximate human judgments, but the human brain patterns didn't match the models' internal calculations," says Groen. ChatGPT doesn't have to cross rivers or navigate busy streets. However, as AI becomes more and more prevalent, these kinds of problems will arise more. This didn't just occur with standard AI models without training. Even leading AI models didn't give exactly the same answers as humans, despite the task being so normal for us. But why does any of this matter? ChatGPT doesn't have to cross rivers or navigate busy streets. However, as AI becomes more and more prevalent, these kind of problems will arise more. AI chatbots are rolling out live video and audio discussions, and AI is finding its way into other areas like self-driving cars, robotics, and healthcare. As the technology gets more advanced, we are discovering areas where AI struggles to think in a human capacity. In other words, it struggles to interact with a world in the way it has been designed. ChatGPT and its competitors will likely quickly work out how to navigate environments. But in the meantime, feel some pride in the fact that you are smarter than an all-knowing chatbot when it comes to navigating across a rocky hill. As the technology gets more advanced, we are discovering areas where AI struggles to think in a human capacity. In other words, it struggles to interact with a world in the way it has been designed. ChatGPT and its competitors will likely quickly work out how to navigate environments. But in the meantime, feel some pride in the fact that you are smarter than an all-knowing chatbot when it comes to navigating across a rocky hill.
The Star
8 hours ago
- Health
- The Star
Scientists develop tool to 'tell how fast someone is ageing'
WASHINGTON: Assessing how and why people age differently has long eluded doctors and scientists, particularly when there are no obvious explanations such as illness or history of injury. But a team of researchers at Duke University, Harvard University and the University of Otago believe they could have solved the riddle by developing a brain scan-based tool they say can "tell how fast someone is ageing", be that physically or cognitively. Following a magnetic resonance imaging (MRI) scan, the tool "can estimate your risk in midlife for chronic diseases that typically emerge decades later," the developers said, ahead of their findings being published in the journal Nature Aging. "Patterns of ageing detected during midlife are clinically useful among people in advanced age, including people with neurodegenerative disease," the researchers claimed. For older people, the tool can tell them if they are likely to develop dementia or "other age-related diseases," according to the team, which worked with around 50,000 scans from Canada, New Zealand, the UK, the US and countries in Latin America. The system measures blood pressure, body mass index, glucose and cholesterol levels, lung and kidney function, gum recession and tooth decay over time against a scan done when a person is 45 years old. For middle-aged people, the heads-up "could help motivate lifestyle and dietary changes that improve health," while for the elderly, a warning of susceptibility to dementia might mean "a better shot at slowing the course of disease" if given early enough, meaning "years before symptoms appear." "What's really cool about this is that we've captured how fast people are aging using data collected in midlife," said Ahmad Hariri, professor of psychology and neuroscience at Duke University, who claimed the device is helping "predict diagnosis of dementia among people who are much older." – dpa
Time of India
12 hours ago
- Health
- Time of India
‘Patient fell asleep mid-surgery. What happened next taught me a vital lesson'
Dr Gurneet Singh Sawhney Sir, please help me.' It was a busy Monday morning in my OPD when I heard those words. Even before he introduced himself, I could hear the anxiety in Anil's trembling voice. Frail and slumped in a wheelchair, he was accompanied by his wife who looked visibly distressed. A house help in Navi Mumbai, she had taken time off work to tend to him. An employee at a small workshop, Anil hadn't been able to report to work for the last few weeks. About a month earlier, he had started losing balance and developed blurred vision. He felt like he'd topple while walking and his speech had turned robotic. Worried, the couple had gone to a hospital to report the symptoms. There, an MRI revealed a large tumour in the pons — a critical part of the brainstem that controls vital functions. Surgery was scheduled, but at the last minute, the hospital backed out, citing high risk. Anil was sent home. He approached other hospitals but got no clear answers. Exhausted but clinging to hope, he came to us. I saw classic signs of a pontine lesion: abnormal eye movements, slurred speech, unsteady gait, cerebellar swelling. The MRI also showed unexplained cerebellar inflammation and signs of hydrocephalus — fluid buildup in the brain. by Taboola by Taboola Sponsored Links Sponsored Links Promoted Links Promoted Links You May Like Rare, Refined, and Ready Soon – Monte South is the Answer Monte South A Joint Venture between Adani Realty and Marathon Realty Learn More Undo Something didn't quite add up. We decided to proceed with a stereotactic biopsy in the brainstem, a delicate, high-stakes procedure called 'no man's land' for a reason — coma or paralysis are real possibilities. You don't see what you're doing directly; everything is guided by imaging and meticulous planning. Anil was terrified. 'Will this help me? Should I just get the whole tumour removed? Will I survive this?' His earlier experience had left him shaken. I reassured him: without the biopsy, we wouldn't know what we were truly dealing with. Despite the risks, I was confident we could carry it out safely. He consented. During the awake procedure, Anil chatted with me in Marathi about wanting to return to his village and farm again. 'Yes, definitely, we will make that happen,' I promised. But just as I reached the lesion, he suddenly dozed off. The anaesthetist panicked: 'Sir, he's not responding!' I knew what had happened. I had touched the reticular activating system — part of the brain responsible for consciousness. His sudden sleep confirmed we were exactly at the right spot. We took the sample and sent it for frozen section analysis. Then came a surprising call from the microbiologist: It was TB. I was stunned. I've seen TB affect almost every part of the body — except maybe tooth enamel — but the brainstem? That's extremely rare Dr Sawhney The pathologist confirmed abnormal tissue, likely a low-grade tumour. This was expected. But then came a surprising call from the microbiologist: It was tuberculosis (TB). I was stunned. I've seen TB affect almost every part of the body — except maybe tooth enamel — but the brainstem? That's extremely rare. 'Are you sure?' I asked. She double-checked. 'Yes.' In medical school, we're taught to look for one unifying diagnosis. But Anil had two: a tumour causing pressure and TB causing inflammation and swelling. This changed everything. We immediately began aggressive TB treatment while managing the tumour conservatively. At first, Anil improved. But within days, he became drowsy again. A follow-up MRI showed worsening hydrocephalus — a known complication when dying TB bacteria block brain fluid pathways. I performed a ventriculoperitoneal (VP) shunt to drain excess fluid and relieve pressure. The results were immediate. His headaches eased, he sat up, and his responses became clearer. He was discharged the next day. A week later, he returned, visibly better. Since then, his recovery has been steady. Anil now walks into my OPD with confidence. 'I'm feeling better now,' he tells me. 'And I want to feel even better.' That's my true reward. Neurosurgery is emotionally intense. You witness both miraculous recoveries and devastating outcomes. To cope, I meditate every night. But Anil's story has stayed with me. Scanning his brain taught me a vital lesson: never assume there's only one culprit. TB can be a silent player in neurology, and since Anil, I've diagnosed other cases where something hidden — like TB — was the missing piece. Medicine isn't always about finding a neat, singular answer. Sometimes, your gut tells you there's more to the story. Anil reminded me to trust that instinct and to never stop digging. Dr Sawhney is senior consultant, neurosurgery and spine surgery at Fortis Mulund & Vashi. He spoke to Sharmila Ganesan Ram
Time of India
14 hours ago
- Entertainment
- Time of India
Seth Rollins' Crutches Appearance During WWE Evolution Raises Questions About His Wrestling Future
Seth Rollins (Image Source: Getty) Seth Rollins shocked the WWE Universe when he was seen with crutches backstage during WWE Evolution, but was he really that hurt, and how long will Rollins be out? Rollins' appearance came just days after he tweaked his knee performing the move at a live event, and he did so looking to be in discomfort and wearing a knee brace. Those headlines now lead to speculation over whether the "Visionary" will return in time for SummerSlam or if WWE's plans for him are on the cusp of a less monumental redirect. WWE remains silent as speculation grows While Rollins has been the subject of circulated photos and mostly backstage chatter, WWE has been unusually quiet about Rollins' injury status. Neither the company nor Rollins has specifically commented on the matter. Because of this silence, speculation by the fans has increased. — thepgeraa (@thepgeraa) Others are convinced WWE is sitting on a declaration until medical testing, likely an MRI, is fully evaluated. Some speculate the silence is an intentional stall tactic to allow the creative team time to pivot, plan, and reshape SummerSlam around the results. Rollins has been one of the main focuses of WWE programming with his new faction as well as the Money in the Bank briefcase. That raises a huge question mark over both, given his injury. Should it be severe knee damage — like an ACL or MCL tear — Rollins could spend up to six to nine months away from the ring, similar to his previous knee injury that had him out for nearly a year. Even a mild strain of the ligament could put him out for a minimum of 3 to 4 months, which would take him beyond SummerSlam and possibly to the beginning of 2026. Will Seth Rollins return at SummerSlam? As long as Rollins didn't suffer too serious an injury — which you would think would have been announced already if he did — hope remains that he will be making some sort of dramatic SummerSlam return. WWE has always loved a surprise return to bump the ratings, and a Money in the Bank cash-in at the premium live event would be a headline steal. But, after all he has been through physically and not having appeared on TV in a wrestling capacity since the incident, the likelihood of this becomes less and less every day. Also Read: Seth Rollins Injury Update: Triple H Shares Status on 'The Architect' After the Vicious Match at Saturday Night's Main Event Within WWE, they now have to consider what to do with the MITB briefcase. Do they take it off Rollins and give it to somebody else? Are they constructing a narrative of a delayed or postponed cash-in? Or do they play the guessing game and continue to catch that uncertainty wave? However, Seth Rollins is experiencing an undeniable gray area missing for one of WWE's biggest stars. In several weeks at hell, or maybe his return date, and again following the creative direction of the entire company through the rest of the season of 12 months, the clouds may very well settle down. Catch Rani Rampal's inspiring story on Game On, Episode 4. Watch Here!
Yahoo
17 hours ago
- Health
- Yahoo
RSNA: AI Tool Accurately Detects Tumor Location on Breast MRI
An AI model trained to detect abnormalities on breast MR images accurately depicted tumor locations and outperformed benchmark models when tested in three different groups, according to a study published today in Radiology, a journal of the Radiological Society of North America (RSNA). OAK BROOK, Ill., July 15, 2025 /PRNewswire-PRWeb/ -- An AI model trained to detect abnormalities on breast MR images accurately depicted tumor locations and outperformed benchmark models when tested in three different groups, according to a study published today in Radiology, a journal of the Radiological Society of North America (RSNA). "AI-assisted MRI could potentially detect cancers that humans wouldn't find otherwise," said the study's lead investigator Felipe Oviedo, Ph.D., a senior research analyst at Microsoft's AI for Good Lab. Screening mammography is considered the standard of care in breast cancer screening. However, mammography is less effective in patients with dense breasts. Breast density is an independent risk factor for breast cancer and can mask a tumor. Physicians may order breast MRI to supplement screening mammography for women who have dense breasts and those at high risk for cancer. "MRI is more sensitive than mammography," Dr. Oviedo said. "But it's also more expensive and has a higher false-positive rate." To enhance the accuracy and efficiency of screening breast MRI, Dr. Oviedo's research team closely collaborated with clinical investigators in the Department of Radiology at the University of Washington to develop an explainable AI anomaly detection model. Anomaly detection models distinguish between normal and abnormal data, flagging the anomalies, or abnormalities, for further investigation. "Previously developed models were trained on data of which 50% were cancer cases and 50% were normal cases, which is a very unrealistic distribution," Dr. Oviedo said. "Those models haven't been rigorously evaluated in low-prevalence cancer or screening populations (where 2% of all cases or less are cancer), and they also lack interpretability, both of which are essential for clinical adoption." To address these limitations, the researchers trained their model using data from nearly 10,000 consecutive contrast-enhanced breast MRI exams performed at the University of Washington between 2005 and 2022. Patients were predominately white (greater than 80%), and 42.9% had heterogeneously dense breasts, while 11.6% had extremely dense breasts. "Unlike traditional binary classification models, our anomaly detection model learned a robust representation of benign cases to better identify abnormal malignancies, even if they are underrepresented in the training data," Dr. Oviedo said. "Since malignancies can occur in multiple ways and are scarce in similar datasets, the type of anomaly detection model proposed in the study is a promising solution." In addition to providing an estimated anomaly score, the detection model produces a spatially resolved heatmap for an MR image. This heatmap highlights in color the regions in the image that the model believes to be abnormal. The abnormal regions identified by the model matched areas of biopsy-proven malignancy annotated by a radiologist, largely surpassing the performance of benchmark models. The model was tested on internal and external datasets. The internal dataset consisted of MRI exams performed on 171 women (mean age 48.8) for screening (71.9%; 31 cancers confirmed on subsequent biopsy) or pre-operative evaluation for a known cancer (28.1%; 50 cancers confirmed by biopsy). The external, publicly available, multicenter dataset included pre-treatment breast MRI exams of 221 women with invasive breast cancer. The anomaly detection model accurately depicted tumor location and outperformed benchmark models in grouped cross-validation, internal and external test datasets, and in both balanced (high prevalence of cancer) and imbalanced (low cancer prevalence) detection tasks. If integrated into radiology workflows, Dr. Oviedo said the anomaly detection model could potentially exclude normal scans for triage purposes and improve reading efficiency. "Our model provides an understandable, pixel-level explanation of what's abnormal in a breast," he said. "These anomaly heatmaps could highlight areas of potential concern, allowing radiologists to focus on those exams that are more likely to be cancer." Before clinical application, he said the model needs to be evaluated in larger datasets and prospective studies to assess its potential for enhancing radiologists' workflow. ### "Cancer Detection in Breast MRI Screening via Explainable AI Anomaly Detection." Collaborating with Dr. Oviedo were Anum S. Kazerouni, Ph.D., Philipp Liznerski, Ph.D., Yixi Xu, Ph.D., Michael Hirano, M.S., Robert A. Vandermeulen, Ph.D., Marius Kloft, Ph.D., Elyse Blum, M.D., Ph.D., Adam M. Alessio, Ph.D., Christopher I. Li, M.D., Ph.D., William B. Weeks, M.D., Ph.D., M.B.A., Rahul Dodhia, Ph.D., Juan M. Lavista Ferres, Ph.D., Habib Rahbar, M.D., and Savannah C. Partridge, Ph.D. Radiology is edited by Linda Moy, M.D., New York University, New York, N.Y., and owned and published by the Radiological Society of North America, Inc. ( RSNA is an association of radiologists, radiation oncologists, medical physicists and related scientists promoting excellence in patient care and health care delivery through education, research and technologic innovation. The Society is based in Oak Brook, Illinois. ( For patient-friendly information on breast MRI, visit Media Contact Linda Brooks, Radiological Society of North America (RSNA), 630-590-7762, lbrooks@ View original content: SOURCE Radiological Society of North America (RSNA) Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
