Various approaches have been proposed for segmentation of cardiac MRI. An accurate segmentation of the
myocardium and ventricles is essential to determine parameters of interest for the function of the heart, such as
the ejection fraction. One problem with MRI is the poor resolution in one dimension.
A 3D registration algorithm will typically use a trilinear interpolation of intensities to determine the intensity
of a deformed template image. Due to the poor resolution across slices, such linear approximation is highly
inaccurate since the assumption of smooth underlying intensities is violated. Registration-based interpolation
is based on 2D registrations between adjacent slices and is independent of segmentations. Hence, rather than
assuming smoothness in intensity, the assumption is that the anatomy is consistent across slices. The basis for
the proposed approach is the set of 2D registrations between each pair of slices, both ways. The intensity of a
new slice is then weighted by (i) the deformation functions and (ii) the intensities in the warped images. Unlike
the approach by Penney et al. 2004, this approach takes into account deformation both ways, which gives more
robustness where correspondence between slices is poor.
We demonstrate the approach on a toy example and on a set of cardiac CINE MRI. Qualitative inspection reveals
that the proposed approach provides a more convincing transition between slices than images obtained by linear
interpolation. A quantitative validation reveals significantly lower reconstruction errors than both linear and
registration-based interpolation based on one-way registrations.
Clustering is the preferred choice of method in many applications, and support vector clustering (SVC) has proven efficient for clustering noisy and high-dimensional data sets. A method for multiscale support vector clustering is demonstrated, using the recently emerged method for fast calculation of the entire regularization path of the support vector domain description. The method is illustrated on artificially generated examples, and applied for detecting blood vessels from high resolution time series of magnetic resonance imaging data. The obtained results are robust while the need for parameter estimation is reduced, compared to support vector clustering.
We present a new statistical deformation model suited for parameterized grids with different resolutions. Our method models the covariances between multiple grid levels explicitly, and allows for very efficient fitting of the model to data on multiple scales.
The model is validated on a data set consisting of 62 annotated MR images of Corpus Callosum. One fifth of the data set was used as a training set, which was non-rigidly registered to each other without a shape prior. From the non-rigidly registered training set a shape prior was constructed by performing principal component analysis on each grid level and using the results to construct a conditional shape model, conditioning the finer parameters with the coarser grid levels. The remaining shapes were registered with the constructed shape prior. The dice measures for the registration without prior and the registration with a prior were 0.875 ± 0.042 and 0.8615 ± 0.051, respectively.
Myocardial perfusion Magnetic Resonance (MR) imaging has proven to be a powerful method to assess coronary artery diseases. The current work presents a novel approach to the analysis of registered sequences of myocardial perfusion MR images. A previously reported active appearance model (AAM) based segmentation and registration of the myocardium provided pixel-wise signal intensity curves that were analyzed using the Support Vector Domain Description (SVDD). In contrast to normal SVDD, the entire regularization path was calculated and used to calculate a generalized distance, which is used to discriminate between ischemic and healthy tissue. The results corresponded well to the ischemic segments found by assessment of the three common perfusion parameters; maximum upslope, peak and time-to-peak obtained pixel-wise.
We present a polymer lab-on-a-chip (LOC) microsystem with integrated optics, fabricated by thermal nanoimprint lithography (NIL) in a cyclic olefin copolymer, Topas from Ticona. The LOC contains microfluidic channels and mixers, an absorbance cell, optical waveguides, a microfluidic dye laser, and Fresnel lenses to couple light in and out of the waveguides. The polymer structure is embedded between two glass substrates. By this device we exploit the excellent chemical, mechanical and optical properties of Topas, and demonstrate the fabrication of millimeter to micrometer sized structures in one lithographic step. In addition, the NIL approach allows for addition of nanometer-scale features, limited only by the stamp fabrication. The silicon stamp for the imprint process is fabricated by standard UV-lithography and silicon deep reactive ion etching (DRIE). The sidewall roughness of the DRIE process is reduced to below 15 nm by thermal oxidation and subsequent oxide etching. Prior to imprint the stamp is coated with an anti-sticking coating from a perfluorodecyltrichlorosilane precursor by molecular vapor deposition. Topas, in our case grade 8007, dissolved in toluene is spin coated onto a SiO2 substrate. The imprint temperature is 200 °C, at an imprint force of 15000 N on a 4 inch wafer, imprint time is 5 min. Finally the imprinted structure is bonded to a pyrex wafer with a second layer of Topas in our case grade 9506. Bonding temperature is 70 °C, at a bonding force of 5000 N on a 4 inch wafer. Bonding time is 5 min.