Adapting Breast Density Classification from Digitized to Full-Field Digital Mammograms

Mammographic density is strongly associated with breast cancer, being considered one of the most important risk indicators for the development of this type of disease. Likewise, the sensitivity of automatic breast lesion detection systems is significantly dependent on breast tissue characteristics. Therefore, the measurement of density is definitely useful for detecting breast cancer. The aim of this work is to adapt our previously developed automatic breast tissue density classification methodology for digitized mammograms to full-field digital mammograms (FFDM), as well as to evaluate the possible improvements and the classification results. After breast area extraction and peripheral enhancement, the method segments the breast area into fatty and dense tissue, then morphological and texture features from each class are extracted and finally FFDM are classified according to a standard qualitative criteria. Results show a strong correlation (κ = 0.88) between automatic and expert assessments and a better classification correction percentage (CCP = 92%) compared to our earlier work.