Latest news with #AmericanCollegeofRadiology
Boston Globe
30-05-2025
- Health
- Boston Globe
AI-based mammography is here, and it has a trust problem
Enthusiasm is growing for the technology, as prospective trials conducted in Europe suggest that some AI tools can detect more cancers than radiologists alone. But beyond radiology networks that are implementing their own algorithms, many imaging centers and the radiologists who work for them are still skeptical. Advertisement 'It'll take time for us to really gain a lot of trust and confidence in it,' said Manisha Bahl, a breast radiologist at Massachusetts General Hospital, which is currently testing several AI-based tools for mammography in a head-to-head study. One large Advertisement Radiologists were much less likely to call patients for follow-up when their mammogram was flagged by the AI than when it was flagged by a human radiologist — even though the AI-flagged cases were more likely to be cancerous. If both members of a human-AI pair flagged a case for possible malignancy, only 39 percent of patients were called back. If it was two radiologists that flagged a case, callbacks shot up to 57 percent. The researchers used technology from South Korean developer Lunit, which also partly funded the study. 'Providing a superior performing algorithm doesn't actually necessarily improve human performance,' said Adam Rodman, a clinical reasoning researcher and practicing internist who co-directs the iMED initiative at Beth Israel Deaconess Medical Center. 'This study does a really good job at explaining why that is, and it's trust.' It's a common refrain for breast radiologists, who have been burned by technology before. Computer-aided detection tools for mammograms became standard starting in the 1980s, but in the long run, they never improved cancer detection or recall rates. 'We have to be very careful what we do with AI once it's out in the wild,' said Etta Pisano, chief research officer at the American College of Radiology, at the meeting of the Radiological Society of North America in December. Advertisement Performance for breast cancer AI — which marks or annotates suspicious lesions on a mammogram and provides a score or some indication of the likelihood of malignancy — is typically reported based on how well it identifies cancers in databases of old mammograms that have been previously screened by human radiologists. But in practice, that performance can vary significantly from center to center and radiologist to radiologist. The radiologist's level of trust, the way the software is integrated into their With all those variables, how can a radiologist make sure that they're using AI the most effective way? 'The answer is, nobody knows,' said Rodman. Normally, Bahl, the radiologist at Mass General, opens up a mammogram and interprets it entirely on her own before she activates any AI-based image processing. That's to cut down on the risk of automation bias — where she learns to rely too much on the machine. That approach makes sense for radiologists who trust their professional judgement more than a new tool, and it aligns with surveys of patients that suggest they typically want a doctor making the final call on image analysis, said Sanjay Aneja, a radiation oncologist at Yale Cancer Center who studies mammography AI. But that approach doesn't fulfill AI's other main promise: the potential for efficiency. 'If anything, it might be a little bit less efficient,' said Aneja. With skilled radiologists in shortage, AI will ideally help them work smarter and faster — which means looking at the algorithm's output upfront. Advertisement At radiology practices that are more aggressively leaning into mammogram AI, 'radiologists gain confidence and start to look earlier in the process,' said Chris McKinney, director of North American sales for Lunit. That kind of comfort doesn't emerge unless radiologists are getting regular practice with a new system — and adoption of the tools is inconsistent, since they aren't reimbursed by insurance. Instead, most practices deploying the tools ask patients to pay a cash fee of $40 to $90 for an AI add-on. At the top-adopting practice within Rezolut, a network of more than 40 US radiology practices that use Lunit's breast AI system, about 40 percent of patients opt to pay. 'Every radiologist is going to have to work with the AI product and get more comfortable with it and then utilize it individually,' said Stamatia Destounis, chair of the American College of Radiology's breast imaging commission. 'I don't think everyone's going to use it the same way.' But 'practice makes perfect' isn't enough for many AI researchers and physicians, who want more explicit guidance when it comes to appropriate deployment of these tools as they become more widely used. 'The problem is that there's actually very little guardrails with a lot of these devices as they get put out there,' said Aneja. Imaging quality can vary significantly between radiology practices, for example. 'There's very few algorithms that say, 'This image is of poor quality, can't evaluate it,'' said Aneja. 'We want an algorithm to be able to say what they don't know.' Advertisement Chiara Corti, an oncologist from Italy and clinical fellow at Dana-Farber, calls for more disclosure of the race and ethnicity of patients whose mammograms were used to train AI tools to ensure accuracy across groups. (ACR's AI The performance — and relative value — of an AI tool also depends on the radiologists who are using it. Not every radiologist is an expert in reading mammograms, and 'one of the biggest benefits of AI is to disseminate that level of knowledge,' said Aneja. To ensure radiology practices use this new generation of algorithms in a way that drives better cancer outcomes, they need more real-world, prospective research in the US 'We need to see those human interactions,' said Destounis. 'It's impossible to deduce from a study going back in time how every radiologist is going to interact with the AI system in practice, daily.' A 2024 Advertisement That kind of real-world evidence is one of the goals of a program out of ARPA-H called ACTR, for Advancing Clinical Trial Readiness. Pisano, the program's director, said at the December RSNA meeting that ACTR planned to test AI products in real-world, pragmatic trials out of imaging centers across the country, most likely starting with trials of breast cancer screening algorithms that could include hundreds of thousands of mammograms. The trials, she said at the time, were planned to start this spring. They have yet to be announced.
The Star
16-05-2025
- Health
- The Star
Your AI radiologist will not be with you soon
ROCHESTER, Minnesota: Nine years ago, one of the world's leading artificial intelligence scientists singled out an endangered occupational species. 'People should stop training radiologists now,' Geoffrey Hinton said, adding that it was 'just completely obvious' that within five years AI would outperform humans in that field. Today, radiologists – the physician specialists in medical imaging who look inside the body to diagnose and treat disease – are still in high demand. A recent study from the American College of Radiology projected a steadily growing workforce through 2055. Hinton, who was awarded a Nobel Prize in physics last year for pioneering research in AI, was broadly correct that the technology would have a significant impact – just not as a job killer. That's true for radiologists at the Mayo Clinic, one of the nation's premier medical systems, whose main campus is in Rochester, Minnesota. There, in recent years, they have begun using AI to sharpen images, automate routine tasks, identify medical abnormalities and predict disease. AI can also serve as 'a second set of eyes'. 'But would it replace radiologists? We didn't think so,' said Dr Matthew Callstrom, the Mayo Clinic's chair of radiology, recalling the 2016 prediction. 'We knew how hard it is and all that is involved.' An AI presentation on Callstrom's computer at the Mayo Clinic, where he is the chair of radiology, in Rochester, Minn., April 24, 2025. Experts predicted that artificial intelligence would steal radiology jobs. But at the Mayo Clinic, the technology has been more friend than foe. — JENN ACKERMANN/The New York Times Computer scientists, labour experts and policymakers have long debated how AI will ultimately play out in the workforce. Will it be a clever helper, enhancing human performance, or a robotic surrogate, displacing millions of workers? The debate has intensified as the leading-edge technology behind chatbots appears to be improving faster than anticipated. Leaders at OpenAI, Anthropic and other companies in Silicon Valley now predict that AI will eclipse humans in most cognitive tasks within a few years. But many researchers foresee a more gradual transformation in line with seismic inventions of the past, like electricity or the Internet. The predicted extinction of radiologists provides a telling case study. So far, AI is proving to be a powerful medical tool to increase efficiency and magnify human abilities, rather than take anyone's job. When it comes to developing and deploying AI in medicine, radiology has been a prime target. Of the more than 1,000 AI applications approved by the Food and Drug Administration for use in medicine, about three-fourths are in radiology. AI typically excels at identifying and measuring a specific abnormality, such as a lung lesion or a breast lump. 'There's been amazing progress, but these AI tools for the most part look for one thing,' said Dr Charles E. Kahn Jr., a professor of radiology at the University of Pennsylvania's Perelman School of Medicine and editor of the journal Radiology: Artificial Intelligence. Radiologists do far more than study images. They advise other doctors and surgeons, talk to patients, write reports and analyse medical records. After identifying a suspect cluster of tissue in an organ, they interpret what it might mean for an individual patient with a particular medical history, tapping years of experience. Predictions that AI will steal jobs often 'underestimate the complexity of the work that people actually do – just as radiologists do a lot more than reading scans,' said David Autor, a labour economist at the Massachusetts Institute of Technology. At the Mayo Clinic, AI tools have been researched, developed and tailored to fit the work routines of busy doctors. The staff has grown 55% since Hinton's forecast of doom, to more than 400 radiologists. In 2016, spurred by the warning and advances in AI-fueled image recognition, the leaders of the radiology department assembled a group to assess the technology's potential impact. 'We thought the first thing we should do is use this technology to make us better,' Callstrom recalled. 'That was our first goal.' They decided to invest. Today, the radiology department has an AI team of 40 people including AI scientists, radiology researchers, data analysts and software engineers. They have developed a series of AI tools, from tissue analysers to disease predictors. That team works with specialists like Dr Theodora Potretzke, who focuses on the kidneys, bladder and reproductive organs. She describes the radiologist's role as 'a doctor for other doctors,' clearly communicating the imaging results, assisting and advising. Potretzke has collaborated on an AI tool that measures the volume of kidneys. Kidney growth, when combined with cysts, can predict decline in renal function before it shows up in blood tests. In the past, she measured kidney volume largely by hand, with the equivalent of a ruler on the screen and guesswork. Results varied, and the chore was a time-consuming. Potretzke served as a consultant, end user and tester while working with the department's AI team. She helped design the software program, which has colour coding for different tissues, and checked the measurements. Today, she brings up an image on her computer screen and clicks an icon, and the kidney volume measurement appears instantly. It saves her 15 to 30 minutes each time she examines a kidney image, and it is consistently accurate. 'It's a good example of something I'm very comfortable handing off to AI for efficiency and accuracy,' Potretzke said. 'It can augment, assist and quantify, but I am not in a place where I give up interpretive conclusions to the technology.' Down the hall, Dr Francis Baffour, a staff radiologist, explained the varied ways that AI had been applied to the field, often in the background. The makers of MRI and CT scanners use AI algorithms to speed up taking images and to clean them up, he said. Halamka, president of Mayo Clinic Platform, on his farm in Sherborn, Massachusetts. An AI optimist, he believes the technology will transform medicine. — TONY LUONG/The New York Times AI can also automatically identify images showing the highest probability of an abnormal growth, essentially telling the radiologist, 'Look here first.' Another program scans images for blood clots in the heart or lungs, even when the medical focus may be elsewhere. 'AI is everywhere in our workflow now,' Baffour said. Overall, the Mayo Clinic is using more than 250 AI models, both developed internally and licensed from suppliers. The radiology and cardiology departments are the largest consumers. In some cases, the new technology opens a door to insights that are beyond human ability. One AI model analyses data from electrocardiograms to predict patients more likely to develop atrial fibrillation, a heart-rhythm abnormality. A research project in radiology employs an AI algorithm to discern subtle changes in shape and texture of the pancreas to detect cancer up to two years before conventional diagnoses. The Mayo Clinic team is working with other medical institutions to further test the algorithm on more data. 'The math can see what the human eye cannot,' said Dr John Halamka, president of the Mayo Clinic Platform, who oversees the health system's digital initiatives. Halamka, an AI optimist, believes the technology will transform medicine. 'Five years from now, it will be malpractice not to use AI,' he said. 'But it will be humans and AI working together.' Hinton agrees. In retrospect, he believes he spoke too broadly in 2016, he said in an email. He didn't make clear that he was speaking purely about image analysis, and was wrong on timing but not the direction, he added. In a few years, most medical image interpretation will be done by 'a combination of AI and a radiologist, and it will make radiologists a whole lot more efficient in addition to improving accuracy,' Hinton said. – ©2025 The New York Times Company This article originally appeared in The New York Times.
Time of India
15-05-2025
- Science
- Time of India
Your AI radiologist will not be with you soon
Nine years ago, one of the world's leading artificial intelligence scientists singled out an endangered occupational species. "People should stop training radiologists now," Geoffrey Hinton said, adding that it was "just completely obvious" that within five years AI would outperform humans in that field. Today, radiologists -- the physician specialists in medical imaging who look inside the body to diagnose and treat disease -- are still in high demand. A recent study from the American College of Radiology projected a steadily growing workforce through 2055. Hinton, who was awarded a Nobel Prize in physics last year for pioneering research in AI , was broadly correct that the technology would have a significant impact -- just not as a job killer. That's true for radiologists at the Mayo Clinic , one of the nation's premier medical systems, whose main campus is in Rochester, Minnesota. There, in recent years, they have begun using AI to sharpen images, automate routine tasks, identify medical abnormalities and predict disease. AI can also serve as "a second set of eyes." Live Events "But would it replace radiologists? We didn't think so," said Dr. Matthew Callstrom, the Mayo Clinic's chair of radiology, recalling the 2016 prediction. "We knew how hard it is and all that is involved." Discover the stories of your interest Blockchain 5 Stories Cyber-safety 7 Stories Fintech 9 Stories E-comm 9 Stories ML 8 Stories Edtech 6 Stories Computer scientists, labour experts and policymakers have long debated how AI will ultimately play out in the workforce. Will it be a clever helper, enhancing human performance, or a robotic surrogate, displacing millions of workers? The debate has intensified as the leading-edge technology behind chatbots appears to be improving faster than anticipated. Leaders at OpenAI, Anthropic and other companies in Silicon Valley now predict that AI will eclipse humans in most cognitive tasks within a few years. But many researchers foresee a more gradual transformation in line with seismic inventions of the past, like electricity or the internet. The predicted extinction of radiologists provides a telling case study. So far, AI is proving to be a powerful medical tool to increase efficiency and magnify human abilities, rather than take anyone's job. When it comes to developing and deploying AI in medicine , radiology has been a prime target. Of the more than 1,000 AI applications approved by the Food and Drug Administration for use in medicine, about three-fourths are in radiology. AI typically excels at identifying and measuring a specific abnormality, such as a lung lesion or a breast lump. "There's been amazing progress, but these AI tools for the most part look for one thing," said Dr. Charles E. Kahn Jr., a professor of radiology at the University of Pennsylvania's Perelman School of Medicine and editor of the journal Radiology: Artificial Intelligence. Radiologists do far more than study images. They advise other doctors and surgeons, talk to patients, write reports and analyse medical records. After identifying a suspect cluster of tissue in an organ, they interpret what it might mean for an individual patient with a particular medical history, tapping years of experience. Predictions that AI will steal jobs often "underestimate the complexity of the work that people actually do -- just as radiologists do a lot more than reading scans," said David Autor, a labour economist at the Massachusetts Institute of Technology. At the Mayo Clinic, AI tools have been researched, developed and tailored to fit the work routines of busy doctors. The staff has grown 55% since Hinton's forecast of doom, to more than 400 radiologists. In 2016, spurred by the warning and advances in AI-fuelled image recognition, the leaders of the radiology department assembled a group to assess the technology's potential impact. "We thought the first thing we should do is use this technology to make us better," Callstrom recalled. "That was our first goal." They decided to invest. Today, the radiology department has an AI team of 40 people including AI scientists, radiology researchers, data analysts and software engineers. They have developed a series of AI tools, from tissue analyzers to disease predictors. That team works with specialists like Dr. Theodora Potretzke , who focuses on the kidneys, bladder and reproductive organs. She describes the radiologist's role as "a doctor for other doctors," clearly communicating the imaging results, assisting and advising. Potretzke has collaborated on an AI tool that measures the volume of kidneys. Kidney growth, when combined with cysts, can predict decline in renal function before it shows up in blood tests. In the past, she measured kidney volume largely by hand, with the equivalent of a ruler on the screen and guesswork. Results varied, and the chore was a time-consuming. Potretzke served as a consultant, end user and tester while working with the department's AI team. She helped design the software program, which has colour coding for different tissues, and checked the measurements. Today, she brings up an image on her computer screen and clicks an icon, and the kidney volume measurement appears instantly. It saves her 15 to 30 minutes each time she examines a kidney image, and it is consistently accurate. "It's a good example of something I'm very comfortable handing off to AI for efficiency and accuracy," Potretzke said. "It can augment, assist and quantify, but I am not in a place where I give up interpretive conclusions to the technology." Down the hall, Dr. Francis Baffour, a staff radiologist, explained the varied ways that AI had been applied to the field, often in the background. The makers of MRI and CT scanners use AI algorithms to speed up taking images and to clean them up, he said. AI can also automatically identify images showing the highest probability of an abnormal growth, essentially telling the radiologist, "Look here first." Another program scans images for blood clots in the heart or lungs, even when the medical focus may be elsewhere. "AI is everywhere in our workflow now," Baffour said. Overall, the Mayo Clinic is using more than 250 AI models, both developed internally and licensed from suppliers. The radiology and cardiology departments are the largest consumers. In some cases, the new technology opens a door to insights that are beyond human ability. One AI model analyzes data from electrocardiograms to predict patients more likely to develop atrial fibrillation, a heart-rhythm abnormality. A research project in radiology employs an AI algorithm to discern subtle changes in shape and texture of the pancreas to detect cancer up to two years before conventional diagnoses. The Mayo Clinic team is working with other medical institutions to further test the algorithm on more data. "The math can see what the human eye cannot," said Dr. John Halamka, president of the Mayo Clinic Platform , who oversees the health system's digital initiatives. Halamka, an AI optimist, believes the technology will transform medicine. "Five years from now, it will be malpractice not to use AI," he said. "But it will be humans and AI working together." Hinton agrees. In retrospect, he believes he spoke too broadly in 2016, he said in an email. He didn't make clear that he was speaking purely about image analysis, and was wrong on timing but not the direction, he added. In a few years, most medical image interpretation will be done by "a combination of AI and a radiologist, and it will make radiologists a whole lot more efficient in addition to improving accuracy," Hinton said.
Business Journals
01-05-2025
- Health
- Business Journals
The role of imaging in women's preventive health
May is Women's Health Month — a timely opportunity to consider the vital impact of disease prevention in the female population, including the essential role of advanced imaging in early detection of some of the most common and high morbidity diseases that affect women. Breast cancer screening Breast cancer impacts 1 in 8 women in their lifetime, with 1 in 6 diagnosed in their 40s. It remains the second leading cause of cancer death in women. There is well-established clinical data supporting the efficacy of routine screening mammography in reducing breast cancer mortality. The American College of Radiology (ACR) recommends annual screening mammograms for women of average risk to begin at age 40 and continue annually until age 80. Advanced 3D/tomosynthesis technology is the standard of care for screening mammography and has been shown to improve the cancer detection rate. In fact, annual 3D screening mammography can help detect breast cancer up to three years before a lump can be felt by a physician or patient. Early detection stage 0 or stage 1 has a nearly 100% five-year survival rate, making annual screening an imperative for women. Osteoporosis screening Osteoporosis affects about 1 in 5 women over age 50, and 80% of the approximately 10 million Americans with osteoporosis are women. The U.S. Preventive Services Task Force (USPSTF) lists several risks associated with osteoporotic fractures, including stress, subsequent fractures, loss of mobility and diminished performance of activities of daily living (ADLs) and death. Only 40-60% of patients who sustain an osteoporotic hip fracture will return to their pre-fracture level of mobility and ADLs. DEXA (dual energy x-ray absorptiometry) is a low-dose radiation exam that provides a patient's bone mineral density (BMD). The study is typically performed on the hip or lumbar spine and takes less than 20 minutes to complete. Clinical guidelines advise performing bone density testing in all women 65 and older and sooner in women between 50-64 with at least one risk factor for osteoporosis, including menopause, low body weight, family history of a parent with an osteoporotic hip fracture, smoking and excess alcohol intake. The recommended frequency of DEXA screening varies based on the patient's risk level, with high-risk patients performed every two years and moderate risk every three to five years (CDC). Atherosclerotic cardiovascular disease screening Atherosclerotic cardiovascular disease (ACVD) is the leading cause of death in women, affecting more than 60 million women in the U.S. alone. Standard ACVD screening guidelines advise assessing for traditional risk factors of hypertension, hyperlipidemia, diabetes, obesity and gender-specific considerations (e.g. menopausal status). Coronary artery calcium (CAC) is a very specific feature of coronary atherosclerosis. Multiple studies have demonstrated that the addition of CAC score to a patient risk profile improves cardiovascular risk assessment and better informs clinical decision-making and treatment planning. CAC scoring with computed tomography (CT) is typically used for assessing risk for cardiovascular health. CAC-CT is a non-contrast CT of the chest performed with ECG and centered on the heart. A specific software application calculates the CAC score. Newer generation CT scanners use lower radiation doses, which are comparable to a mammogram or lung screening chest CT. expand Courtesy photo Lung cancer screening Lung cancer is the leading cause of cancer death in women. Tobacco smoking is by far the biggest risk factor, and nearly 20% of all women in the U.S. are current smokers. The estimated lifetime risk for a woman to develop lung cancer is 1 in 18, including both smokers and nonsmokers; this breaks down to a lifetime risk of 11.2% for current smokers, 5.8% former smokers, and 1.3% nonsmokers. [1] Leading national health organizations, like the American Cancer Society and USPSTF, recommend annual low dose CT (LDCT) lung screening exams for patients at high risk of lung cancer (current or former smokers with 20 or greater pack year history) between the ages 50-80 years. These guidelines were updated in 2023. LDCT lung screening is a non-contrast CT of the entire chest performed with low dose radiation, substantially lower than a routine chest CT. All of these advanced imaging exams are available in our greater Buffalo community to provide convenient and essential preventive health services to the women we care for. Visit to learn more, or to schedule, call 716-631-2500. Windsong Radiology has been serving patients throughout Western New York for over 35+ years, providing comprehensive diagnostic imaging and women's breast health services, advanced technology, and board-certified, subspecialized radiologists who read over 340K studies each year. Windsong is committed to delivering regional clinical excellence and expert, compassionate care for patients. [1] Bruder C, Bulliard JL, Germann S, Konzelmann I, Bochud M, Leyvraz M, Chiolero A. Estimating lifetime and 10-year risk of lung cancer. Prev Med Rep. 2018 Jun 18;11:125-130. doi: 10.1016/ PMID: 29942733; PMCID: PMC6010924.
