Breast imaging AI tools are seeing only modest clinical benefits according to a recent radiologist survey.
Key Details
- 1A survey of 215 Society of Breast Imaging members was conducted.
- 247% had implemented breast cancer detection AI; 41.8% had not, 11.2% planned to.
- 3Only 34.7% of AI users reported reductions in recall rates, versus 59.3% of non-users expecting such impact.
- 4Similarly, only 9.1% of AI users reported biopsy rate reductions, compared with 36.4% of non-users expecting reductions.
- 5AI users and non-users had similar perceptions regarding patient outcomes (p = 0.87).
- 6Implementation cost was the top barrier (53.3%), followed by concerns about accuracy/reliability and workflow disruption.
Why It Matters
This study suggests that the clinical impact of breast AI is lagging behind expectations, highlighting the need for improved solutions and more robust evidence for AI adoption in practice. Understanding radiologists' real-world experiences will help guide future development and deployment of imaging AI tools.

Source
AuntMinnie
Related News

•AuntMinnie
Deep Learning PET Biomarkers Outperform Clinical Tools in Prostate Cancer Survival Prediction
Deep learning-derived PET biomarkers more accurately predict metastatic prostate cancer survival than standard clinical risk models.

•AuntMinnie
Multinational AI Model Flags Osteoporosis on Chest X-rays
AI can opportunistically detect osteoporosis from chest x-rays across diverse international populations.

•AuntMinnie
AI Worklist Prioritization Dramatically Reduces MSK Fracture Reporting Times
AI-driven worklist prioritization lowered turnaround times for musculoskeletal fracture detection on radiographs by over 80%.