AI Mammography Interpretation Model With Uncertainty Quantifications Can Reduce Radiologist Workload
MONDAY, Aug. 25, 2025 -- An artificial intelligence (AI) strategy can reduce radiologists' workload by incorporating an interpretation of mammography that includes uncertainty quantifications, according to a study published online Aug. 19 in Radiology.
Sarah D. Verboom, from Radboud University Medical Center in the Netherlands, and colleagues examined the reduction in radiologists' reading workload in mammographic screening while maintaining performance by incorporating an AI model that outputs a probability of malignancy (PoM) and a measure of its uncertainty. Eight candidate uncertainty metrics were tested. A hybrid reading approach was proposed. When predictions were deemed confident, recall decisions were made by the model; otherwise, radiologist double reading was applied. Recall and cancer detection rates were compared to standard double reading.
A total of 41,469 examinations from 15,522 women were included in the data set. The researchers found that 61.9 percent of the examinations were read by radiologists with the best-performing uncertainty metric, the entropy of the mean PoM of one region. Hybrid reading resulted in a recall rate of 23.6 percent and a cancer detection rate of 6.6 percent, which was similar to the 23.9 and 6.6 percent, respectively, seen with standard double reading. Compared with examinations with certain predictions, the model's area under the receiver operating characteristic curve was lower for examinations with uncertain predictions.
"Although the overall performance of state-of-the-art AI models is very high, AI sometimes makes mistakes," Verboom said in a statement. "Identifying exams in which AI interpretation is unreliable is crucial to allow for and optimize use of AI models in breast cancer screening programs."
Several authors disclosed ties to the medical technology and device industries.
Editorial (subscription or payment may be required)
Disclaimer: Statistical data in medical articles provide general trends and do not pertain to individuals. Individual factors can vary greatly. Always seek personalized medical advice for individual healthcare decisions.
© 2025 HealthDay. All rights reserved.
Read this next
2016 to 2023 Saw Decline in U.S. Pediatric Radiologists
MONDAY, Sept. 15, 2025 -- The number of U.S. pediatric radiologists declined from 2016 to 2023, according to a study published online Sept. 9 in the Journal of the American...
Deescalated Radiotherapy Tolerated After Surgery for HPV-Linked Oropharyngeal Cancer
THURSDAY, Sept. 11, 2025 -- For patients following surgery for human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma, a deescalated regimen of adjuvant...
Complication Risk Top Concern for African American Women Undergoing Breast Reconstruction
TUESDAY, Sept. 9, 2025 -- For African American patients undergoing mastectomy, the risk for complications and additional surgeries are the top concerns driving breast...
More news resources
- FDA Medwatch Drug Alerts
- Daily MedNews
- News for Health Professionals
- New Drug Approvals
- New Drug Applications
- Drug Shortages
- Clinical Trial Results
- Generic Drug Approvals
Subscribe to our newsletter
Whatever your topic of interest, subscribe to our newsletters to get the best of Drugs.com in your inbox.