Office of Technology Transfer – University of Michigan

Computer-aided Diagnosis Method and System for Mass Detection in Digital Tomosynthesis Mammograms

Technology #2974


Breast cancer is the leading cause of cancer death in women worldwide, accounting for more than 400,000 deaths per year. In 2002, more than 1.15 million new cases were diagnosed worldwide, including more than 200,000 in theĀ United StatesĀ alone. Mammography is one of the leading screening methods for early detection of breast cancer; however, the technology alone is limited and thought to miss 10-15%of breast cancers. Digital tomosynthesis mammography (DTM) is a promising new modality that may reduce the camouflaging effects of dense tissue and improve mammographic sensitivity for breast cancer detection in dense breasts. However, the number of slices per breast may range from 30 to over 80, thus increasing the time required for interpretation.


Researchers at the University of Michigan have developed a computerized detection system for breast cancer screening using digital tomosynthesis mammograms. Their computer-aided diagnosis (CAD) method applies a three-dimensional gradient field analysis to the collected image files to detect lesion candidates. Additionally, these candidates are evaluated with respect to morphological, gray level, or texture features to recommend a benign or cancerous diagnosis.

Applications and Advantages


  • Breast cancer detection


  • Improved sensitivity in breast cancer detection
  • Better analysis method to diagnose benign and malignant lesions, thus reducing unnecessary biopsies