作者: Alexander Horsch , Alexander Hapfelmeier , Matthias Elter
DOI: 10.1007/S11548-011-0553-9
关键词:
摘要: Introduction Breast cancer is globally a major threat for women’s health. Screening and adequate follow-up can significantly reduce the mortality from breast cancer. Human second reading of screening mammograms increase detection rates, whereas this has not been proven current computer-aided systems as “second reader”. Critical factors include accuracy experience training radiologist with system. When assessing performance system components, choice evaluation methods particularly critical. Core assets herein are reference image databases statistical methods.