(Press-News.org) OAK BROOK, Ill. – Artificial intelligence (AI) improves breast cancer detection accuracy for radiologists when reading screening mammograms, helping them devote more of their attention to suspicious areas, according to a study published today in Radiology, a journal of the Radiological Society of North America (RSNA).
Previous research has shown that AI for decision support improves radiologist performance by increasing sensitivity for cancer detection without extending reading time. However, the impact of AI on radiologists’ visual search patterns remains underexplored.
To learn more, researchers used an eye tracking system to compare radiologist performance and visual search patterns when reading screening mammograms without and with an AI decision support system. The system included a small camera-based device positioned in front of the screen with two infrared lights and a central camera. The infrared lights illuminate the radiologist’s eyes, and the reflections are captured by the camera, allowing for computation of the exact coordinates of the radiologist’s eyes on the screen.
“By analyzing this data, we can determine which parts of the mammograms the radiologist focus on, and for how long, providing valuable insights into their reading patterns,” said the study’s joint first author Jessie J. J. Gommers, M.Sc., from the Department of Medical Imaging, Radboud University Medical Center in Nijmegen, Netherlands.
In the study, 12 radiologists read mammography examinations from 150 women, including 75 with breast cancer and 75 without.
Breast cancer detection accuracy among the radiologists was higher with AI support compared with unaided reading. There was no evidence of a difference in mean sensitivity, specificity or reading time.
“The results are encouraging,” Gommers said. “With the availability of the AI information, the radiologists performed significantly better.”
Eye tracking data showed that radiologists spent more time examining regions that contained actual lesions when AI support was available.
“Radiologists seemed to adjust their reading behavior based on the AI’s level of suspicion: when the AI gave a low score, it likely reassured radiologists, helping them move more quickly through clearly normal cases,” Gommers said. “Conversely, high AI scores prompted radiologists to take a second, more careful look, particularly in more challenging or subtle cases.”
The AI’s region markings functioned like visual cues, Gommers said, guiding radiologists’ attention to potentially suspicious areas. In essence, she said, the AI acted as an additional set of eyes, providing the radiologists with additional information that enhanced both the accuracy and efficiency of interpretation.
“Overall, AI not only helped radiologists focus on the right cases but also directed their attention to the most relevant regions within those cases, suggesting a meaningful role for AI in improving both performance and efficiency in breast cancer screening,” Gommers said.
Gommers noted that overreliance on erroneous AI suggestions could lead to missed cancers or unnecessary recalls for additional imaging. However, multiple studies have found that AI can perform as well as radiologists in mammography interpretation, suggesting that the risk of erroneous AI information is relatively low.
To mitigate the risks of errors, Gommers said, it is important that the AI is highly accurate and that the radiologists using it feel accountable for their own decisions.
“Educating radiologists on how to critically interpret the AI information is key,” she said.
The researchers are currently conducting additional reader studies to explore when AI information should be made available, such as immediately upon opening a case, versus on request. Additionally, the researchers are developing methods to predict if AI is uncertain about its decisions.
“This would enable more selective use of AI support, applying it only when it is likely to provide meaningful benefit,” Gommers said.
###
“Influence of AI Decision Support on Radiologists’ Performance and Visual Search in Screening Mammography.” Collaborating with Gommers were Sarah D. Verboom, M.Sc., Katya M. Duvivier, M.D., Cornelis Jan van Rooden, M.D., Ph.D., A. Fleur van Raamt, M.D., Ph.D., Janneke B. Houwers, M.D., Dick B. Naafs, M.D., Lucien E. M. Duijm, M.D., Ph.D., Miguel P. Eckstein, Ph.D., Craig K. Abbey, Ph.D., Mireille J. M. Broeders, Ph.D., and Ioannis Sechopoulos, 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. (https://pubs.rsna.org/journal/radiology)
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. (RSNA.org)
For patient-friendly information on screening mammography, visit RadiologyInfo.org.
END
New research into the muscles of world-class athletes and performance artists has revealed that a small number of “general motor skills” raise these experts above regional-level and novice competitors, with interesting implications for competitive sport and musculoskeletal health.
Contrary to the belief that athletic motor skills are highly specific to individual sports or activities, this research has found that previously unexamined fundamental traits are associated with world-class performance across a range of athletic disciplines.
“We discovered that world-class ...
Research often points to exercise as a good way to boost mental health, but a recent study from the University of Georgia suggests that it’s not just physical movement that affects mental health.
It’s how, where and why you exercise that makes the difference.
“Historically, physical activity research has focused on how long someone exercises for or how many calories were burned,” said Patrick O’Connor, co-author of the study and a professor in the Mary ...
New research into the biomechanics of explosive seed dispersal in squirting cucumbers (Ecballium elaterium) reveals how these plants have adapted a suite of unique traits that help propel their high-speed seeds far and wide.
Seed dispersal comes in many forms, and much is known about animal, wind and water-assisted dispersal – but less is known about the self-propelled dispersal mechanisms of plants. One of these is the ballistic dispersal of the squirting cucumber, which uses high-pressure explosions to eject its seeds at ...
Highlights:
Human papillomaviruses, or HPVs, cause cutaneous and mucosal infections that may lead to cancer.
To date, no antiviral treatment options exist for HPVs.
Researchers have identified a promising new compound that inhibits cutaneous HPV.
In lab studies, the compound inhibited viral replication genes in cutaneous HPVs without damaging host cells.
Washington, D.C. — Human papillomaviruses, or HPVs, can cause dangerous infections in the skin and mucous membranes and may lead to cancer. Vaccines that prevent mucosal HPV infections aren’t effective against cutaneous infections, which can cause serious diseases, particularly ...
LOS ANGELES — City of Hope® Research Spotlight offers a glimpse at groundbreaking scientific and clinical discoveries advancing lifesaving cures for patients with cancer, diabetes and other chronic, life-threatening diseases. Each spotlight features research-related news, such as recognitions, collaborations and the latest research defining the future of medical treatment.
To learn more about research at City of Hope, one of the largest and most advanced cancer research and treatment organizations in the United States with its National Medical Center named a Top 5 “Best Hospital” in the nation for cancer care by U.S. News & World Report, subscribe to City of ...
Background and Aims
Gut dysbiosis has been reported in severe liver diseases. However, information on the impact of hepatitis E virus infection on the gut microbiota, and the association between enteric microbiota disturbances and acute hepatitis E (AHE), is limited, particularly in elderly patients with AHE (AHE-elderly). Our objective was to characterize the AHE-specific microbiome in elderly patients and evaluate its association with clinical outcomes.
Methods
Fecal samples and clinical data were collected from 58 AHE-elderly patients ...
The Three Gorges Region (TGR) of the Yangtze River spans Chongqing Municipality and Hubei Province, serving as a vital corridor connecting western and central China. The climate in the TGR features four distinct seasons with abundant precipitation and synchronized rain–heat periods. The climatic conditions in the TGR directly impact the safety of navigation in the Yangtze River, as well as the basin's agricultural production patterns and clean energy supply, all of which are crucial to regional socioeconomic development and ecological conservation. Therefore, ...
A combination of data from the FDA and two independent studies prompted a group of scientists to speak out on conversations surrounding 7-OH and its parent plant, kratom. The science confirms the strong safety profile of 7-OH and slams the door closed on continued efforts by industry competitors to push 7-OH out of the marketplace with public smears, unfounded science, and government overreach.
The Marwood Group recently completed an independent analysis of data from the FDA, CDC and other federal agencies that confirms 7-OH’s strong real-world safety profile. According to the FDA’s Adverse Event Reporting System (FAERS), there have ...
A study of the genetic basis of plague immunity in prairie dogs has broad implications for conservation. From white-nose syndrome in bats to avian malaria in Hawaiian birds, introduced pathogens are a major cause of population declines in native species. Many prairie dog populations in North America have been nearly wiped out by sylvatic plague, which is caused by the same bacteria that causes the Black Death in humans: Yersinia pestis. Loren Cassin-Sackett and colleagues studied an outbreak of plague in Boulder County, Colorado in 2006–2009 that hit the site of a long-term prairie dog ecology study. The authors trapped and sampled the ...
MINNEAPOLIS / ST. PAUL (07/08/2025) — Should AI chatbots replace your therapist? New research says “no.”
The new study exposes the dangerous flaws in using artificial intelligence (AI) chatbots for mental health support. For the first time, the researchers evaluated these AI systems against clinical standards for therapists.
The research, recently published and presented at the Association for Computing Machinery Conference on Fairness, Accountability, and Transparency (ACM FAccT), was a multi-disciplinary collaboration including researchers at the Stanford Institute for ...