Robust Initial Detection of Landmarks in Film-Screen Mammograms Using Multiple FFDM Atlases

• Published in: IEEE transactions on medical imaging Vol. 28; no. 11; pp. 1815 - 1824
• Main Authors: Iglesias, J.E., Karssemeijer, N.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2009; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Breast cancer; Cancer detection; Change detection algorithms; Data mining; detection; Female; Humans; Image Processing, Computer-Assisted - methods; Image segmentation; Mammography; Mammography - methods; Muscles; nipple; Nipples - anatomy & histology; Normal Distribution; Optical films; Optical noise; pectoralis; Pectoralis Muscles - anatomy & histology; Robustness; ROC Curve; segmentation

Automated analysis of mammograms requires robust methods for pectoralis segmentation and nipple detection. Locating the nipple is especially important in multiview computer aided detection systems, in which findings are matched across images using the nipple-to-finding distance. Segmenting the pecto...