Rafael Wiemker has received an MS in Astronomy for tomographic reconstruction of binary star systems from the Center of High Angular Resolution Astronomy at Georgia State University Atlanta in 1992. He completed his PhD in 1997 at the university of Hamburg, Germany, on problems of spectral classification of aerial and satellite images. Since 1998 RW is with the Philips Research Lab Hamburg, as a senior scientist working on medical imaging of digital radiography and high resolution computer tomography, mainly on topics of computer aided detection and quantification in thoracic CT.
This will count as one of your downloads.
You will have access to both the presentation and article (if available).
Results indicate that spectral CT adds significant discrimination power, in particular when utilizing local spectral variances and covariances, which can be computed efficiently by standard Gaussian filter operations. Simple linear spectral material separation, however, is sufficient only in extended homogeneous regions. In subtle finely structured transition areas, non-linear classifiers or convolutional neural networks are required because of non-linear local multi material superposition effects.
Affine registration of unseen CT images to the probabilistic atlas can be used to transfer reference annotations, e.g. organ models for segmentation initialization or reference bounding boxes for field-of-view selection. The robustness and generality of the method is shown using a three-fold cross-validation of the registration on a set of 316 CT images of unknown content and large anatomical variability. As an example, 17 organs are annotated in the atlas reference space and their localization in the test images is evaluated. The method yields a recall (sensitivity), specificity and precision of at least 96% and thus performs excellent in comparison to competitors.
View contact details
No SPIE Account? Create one
