The purpose of this study is to develop computer programs to assist radiologists in finding breast cancer on mammograms and to compare the computer's accuracy of detecting cancers on direct digital and film mammograms.
To develop a computer-aided diagnosis (CAD) system for full field digital mammography (FFDM) using advanced computer vision techniques and to evaluate the effects of CAD on interpretation of digital mammograms (DMs). This system will assist radiologists with the four most important areas in mammographic interpretation: (1) detection of masses, (2) classification of masses, (3) detection of microcalcifications, (4) classification of microcalcifications. The proposed approach is distinctly different from previous approaches in that image information from two-view and bilateral mammograms will be fused with that from the single-view mammogram to improve lesion detection and characterization.
Study Type
INTERVENTIONAL
Allocation
NA
Purpose
DIAGNOSTIC
Masking
NONE
Enrollment
433
Using non-invasive digital mammography with computer aided programs to screen, detect and characterize breast lesions/cancer.
University of Michigan Health System
Ann Arbor, Michigan, United States
Using computer aided programs to assist in detection and characterization of breast lesions in digital mammography.
Time frame: Research scan will be completed at the time of scheduled clinical visit.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.