Latest question:
How do you think the new GigE standards will influence the machine vision industry?
Respond or ask your question now!





Screening mammography efficiency is enhanced when sensitivity is high and the recall rate is low. Double reading, though used by few practices in the United States, is more commonly used in European screening programs for increasing sensitivity. CAD has become increasingly popular as an alternative way to increase sensitivity, since double-reading is time-consuming and because of a shortage of radiologists.
CAD has the potential to increase sensitivity of screening mammography by marking areas of interest that might otherwise be overlooked by interpreting radiologists. However, it also may place false marks, identifying areas of suspicion that are not cancer. A small fraction of false marks may result in unnecessary patient recalls for further evaluation. The major goal is to reduce oversights when screening mammograms are read; the radiologist still is responsible for lesion analysis and final interpretation of an examination.
There are three primary CAD marks: the R2 Triangle (calcification clusters), the R2 Asterisk (masses) and R2 Malc (regions with both mass and calcification).
Additional emphasis marks are displayed in various sizes correlating to the prominence of a mass or calcification. When the algorithm determines that a region contains more prominent features, the CAD mark appears larger.
The algorithm examines signal intensity, number of calcifications in a cluster, and shape of calcifications. For masses, it evaluates characteristics such as degree of speculation, lesion shape, contrast to surrounding tissue, texture of lesion interior, and edge texture. As more features are found the algorithm enlarges the size of the mark.
During the period of the study (2001-2005) the nine radiologists interpreted a total 428,909 mammograms—
including second readings and diagnostic examinations.