摘要
Mammographic screening has been pivotal in early breast cancer detection,significantly reducing mortality by enabling timely detection for interventions.1 Mammography remains the gold standard for breast cancer screening due to its proven ability to detect early-stage cancers and its accessibility for large-scale population screening.Unlike ultrasound,which is typically used as a supplementary tool for dense breast tissue,or MRI,which is often reserved for high-risk cases due to its high cost and longer procedure time,mammography provides a standardized,cost-effective modality suitable for widespread use.By applying artificial intelligence(AI)in mammography,healthcare systems can enhance the accuracy and efficiency of screening programs,particularly in high-volume settings.However,interpreting mammograms requires highly trained specialists,and training radiologists is both time consuming and resource-intensive.
基金
supported by the NUHS Clinician Scientist Program 2.0(NCSP 2.0)under Department of Surgery,National University Hospital.The study design,data collection,data analysis and interpretation were conducted by the study team independently.
