Breast cancer remains one of the leading causes of cancer-related deaths among women worldwide. Early detection of breast lesions signifi-cantly improves the chances of successful treatment and survival. However, identifying small or subtle abnormalities can be particularly challenging for radiologists, especially in women with dense breast tissue. This highlights the urgent need for computer-aided diagnosis (CAD) systems to support radiologists in detecting breast lesions at an earlier, more treatable stage. Many challenges are encountered when using CAD systems on digital mammograms. The first obstacle is the existence of elements that have a density similar to that of breast lesions such as artifacts and pectoral muscle. A pre-processing step is therefore essential in order to remove these components and thus optimize the results of breast anomalies segmentation. This chapter provides an overview of various image processing methods developed since 2000 for the detection and removal of the pectoral muscle in digital mammograms, specifically using the mini-MIAS database.