| 摘要 |
Methods, a system, and a computer readable medium are presented that detect and classify mass-like regions exhibiting spiculated and/or dense characteristics with high sensitivity and at acceptable false positive rates. One or more suspicious masses are identified in medical imagery of the breast. In accordance with certain embodiments, for each suspicious mass located, a quantitative measure of spiculation and quantitative measure of density are computed. At least one classification scheme is then selected for each suspicious mass according to both quantitative measures. Each classification scheme is developed using true positives and false positives with similar quantitative measures. In accordance with certain other embodiments, for each suspicious mass located, a measure of breast location is computed. At least one classification scheme is then selected for each suspicious mass according to the measure of breast location. Each classification scheme is developed using true positives and false positives that appear in the same breast location. In one embodiment, the location measure determines whether a suspicious mass appears inside or outside of the parenchyma region of the breast.
|
