2014 | OriginalPaper | Buchkapitel
Accurate Cortical Bone Detection in Peripheral Quantitative Computed Tomography Images
verfasst von : T. Cervinka, J. Hyttinen, H. Sievänen
Erschienen in: XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013
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
An accurate assessment of the whole bone strength is an essential goal in clinical bone research. This is, however, possible only with accurate and precise description of actual bone geometry. In this paper, we introduce a refined automated approach of OBS method for accurate segmentation of cortical bone cross-sectional area. The approach employs morphological operations and utilization of two fixed thresholds. For comparison, the standard OBS and method based on level set evolution (DRLSE) were evaluated. The performance of used methods was tested on in vivo peripheral quantitative computed tomography (pQCT) images of distal tibia. As to the detection of cortical bone geometry in pQCT images, the new refined OBS method performed reasonably well and was indicating somewhat more consistent results in comparison to standard OBS and DRLSE based method.