PuSH - Publikationsserver des Helmholtz Zentrums München

Wang, L. ; Belagiannis, V.* ; Marr, C. ; Theis, F.J. ; Yang, G.Z.* ; Navab, N.*

Anatomic-landmark detection using graphical context modelling.

In: Proceedings (12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, 16-19 April 2015, Brooklyn, United States). 2015. 1304-1307
DOI Verlagsversion bestellen
Anatomical landmarks in images play an important role in medical practice. This paper presents a graphical model that fully automatically detects such landmarks. The model includes a unary potential using a random forest classifier based on local appearance and binary and ternary potentials encoding geometrical context among different landmarks. The weightings of different potentials are learned in a maximum likelihood manner. The final detection result is formulated as the maximum-a-posteriori estimation jointly over the whole set of landmarks in one image. For validation, the model is applied to detect right-ventricle insert points in cardiac MR images. The result shows that the context modelling is able to substantially improve the overall accuracy.
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Anatomical Landmark Detection ; Context Modelling ; Graphical Model ; Parameter Learning
ISSN (print) / ISBN 1945-7928
e-ISSN 978-147992374-8
Konferenztitel 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
Konferzenzdatum 16-19 April 2015
Konferenzort Brooklyn, United States
Konferenzband Proceedings
Quellenangaben Band: , Heft: , Seiten: 1304-1307 Artikelnummer: , Supplement: ,