2007 | OriginalPaper | Buchkapitel
Elimination of Linear Structures as an Attempt to Improve the Specificity of Cancerous Mass Detection in Mammograms
verfasst von : Marcin Bator, Leszek J. Chmielewski
Erschienen in: Computer Recognition Systems 2
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In the screening mammographic examination of large parts of populations thousands of mammograms are analysed. The Computer Aided Diagnosis methods available still tend to produce too many false positive (FP) detections with respect to the number of true positive (TP) detections, which makes it impractical to use such methods to support the human observer in the analysis of mammograms. In this paper an attempt has been made to decrease the number of FP errors in the hierarchical correlation-based cancerous mass detection method by eliminating the images of linear structures (LSs) from the mammograms. The LSs were detected with an accumulationbased line detector and the image intensity function in the regions of the LSs was interpolated with an anisotropic membrane. Examples of images representing typical detection problems caused by the LSs selected from the MIAS database suggest the feasibility of the proposed approach.