Radiology in public focus
Press releases were sent to the medical news media for the following articles appearing in recent issues of RSNA Journals.

Amplifying the Voice of Radiologists Worldwide
In today’s fast-moving information landscape, a strong media presence is essential for any organization with a public mission. RSNA expands the reach of radiologists by sharing the latest research and information to help shape the public’s understanding of health care issues and the role of radiologists in this sphere.
In March, 1,797 RSNA-related news stories were tracked in the media. These stories had over 631 million audience impressions. Coverage included high-profile publications that included U.S. News & World Report, HealthDay, AuntMinnie. com, Radiology Today, Medical Imaging, Health Imaging News, Healthcare Business News and Applied Radiology.
In March, the following press release was issued for research published in Radiology: Cardiothoracic Imaging:
Ultra-Low Dose CT Aids Pneumonia Diagnosis in Immunocompromised Patients
Researchers tested the denoising capabilities of a deep learning algorithm on ultra-low dose CT scans and found that denoised ultra-low dose CT can effectively diagnose pneumonia in immunocompromised patients using only 2% of the radiation dose of standard CT.

Radiologists Share Tips to Prevent AI Bias
Radiologists, computers scientists and informaticists outline pitfalls and best practices to mitigate bias in AI models in an article published in Radiology.
While there is growing awareness of the biases AI algorithms can exhibit, there are challenges associated with the evaluation and measurement of algorithmic bias.
In the article, Paul H. Yi, MD, associate member/professor in the Department of Radiology and director of Intelligent Imaging Informatics at St. Jude Children’s Research Hospital in Memphis, TN, and colleagues identify key areas where pitfalls occur. The team also offers best practices and initiative that should be taken.
“AI offers an incredible opportunity to scale diagnostic capabilities in ways we’ve never seen before, potentially improving health outcomes for millions of people,” Dr. Yi said. “At the same time, if biases are left unchecked, AI could unintentionally worsen health care disparities.”
Read the related RSNA News story.

Researchers Identify Texture Patterns Associated with Breast Cancer Risk
In one of the larger studies of its kind, researchers have identified six breast texture patterns that may be associated with increased cancer risk, according to a study published in Radiology.
Women with dense breasts make up a large proportion of screening-eligible women. Breast cancer can be difficult to detect on mammograms of dense breasts due to the similarity of appearance of dense breast tissue and cancer growths.
Celine M. Vachon, PhD, professor of epidemiology at the Mayo Clinic in Rochester, MN, and colleagues used radiomics on the mammograms of over 30,000 women without a prior history of cancer from three different screening cohorts. The researchers extracted 390 radiomic features that were condensed into six phenotypes. The phenotypes were evaluated on mammograms from over 3,500 women, some who developed breast cancer and some who did not.
Results showed that the radiomic phenotypes were associated with a higher risk of invasive breast cancer in both Black and white women. “We were surprised to find that these radiomic phenotypes showed suggestion of a stronger risk among Black vs. white women,” said co-senior author Despina Kontos, PhD, Herbert and Florence Irving Professor of Radiological Sciences and chief research information officer at Columbia University Irving Medical Center in New York City. “This is particularly important as breast cancer tends to be more aggressive in Black women, highlighting the need for novel risk factors in this population.”
Read the related RSNA News story.

Patients Support AI as Radiologist Backup in Screening Mammography
The results of a large survey from a diverse patient population revealed cautious support for AI implementation in screening mammography, according to a study published in Radiology: Imaging Cancer.
Basak E. Dogan, MD, clinical professor of radiology and director of breast imaging research at the University of Texas Southwestern Medical Center in Dallas, and colleagues sought to understand patient opinions and concerns regarding AI use in screening mammography. They developed a 29-question survey to be offered to all patients who attended their institution for a breast cancer screening mammogram. It was available for a period of seven months in 2023.
Of the 518 patients who completed the survey, most indicated support for the use of AI alongside a radiologist’s review, with 71% of respondents preferring AI to be used as a second reader. Less than 5% were comfortable with AI alone interpreting their screening mammogram.
“Our study shows that trust in AI is highly individualized, influenced by factors such as prior medical experiences, education and racial background,” Dr. Dogan said. “Incorporating patient perspectives into AI implementation strategies ensures that these technologies improve and not hinder patient care, fostering trust and adherence to imaging reports and recommendations.”
Read the related RSNA News story.
RadiologyInfo.org Radiation Dose Chart Updated
As part of its “Safety: Radiation Dose” article, RadiologyInfo.org provides approximate comparisons of background radiation and effective radiation dose in adults for several radiology procedures.
The information is presented as a chart on the website and is also available for download as a PDF from the “Physician Resources” page. The effective doses are typical values for an average-sized adult. The actual dose can vary substantially, depending on a person’s size, the reason for imaging and differences in imaging practices.
Visit RadiologyInfo.org to view the radiation dose chart and access other expert-approved, patient-friendly information addressing radiation benefits and risks.