Faculty Bibliography

Image Guided Radiation Therapy (IGRT) improves radiation therapy for prostate cancer by facilitating precise radiation dose coverage of the object of interest, and minimizing dose to adjacent normal organs. In an effort to optimize IGRT, we developed a fast segmentation-registration-segmentation framework to accurately and efficiently delineate the clinically critical objects in Cone Beam CT images obtained during radiation treatment. The proposed framework started with deformable models automatically segmenting the prostate, bladder, and rectum in planning CT images. All models were built around seed points and involved in the CT image under the influence of image features using the level set formulation. The deformable models were then converted into meshless point sets and underwent a 3D non rigid registration from the planning CT to the treatment CBCT. The motion of deformable models during the registration was constrained by the global shape prior on the target surface during the deformation. The meshless formulation provided a convenient interface between deformable models and the image feature based registration method. The final registered deformable models in the CBCT domain were further refined using the interaction between objects and other available image features. The segmentation results for 15 data sets has been included in the validation study, compared with manual segmentations by a radiation oncologist. The automatic segmentation results achieved a satisfactory convergence with manual segmentations and met the speed requirement for on line IGRT.

The purposes of this study were to develop a semiautomated cardiac contour segmentation method for use with cine displacement-encoded MRI and evaluate its accuracy against manual segmentation. This segmentation model was designed with two distinct phases: preparation and evolution. During the model preparation phase, after manual image cropping and then image intensity standardization, the myocardium is separated from the background based on the difference in their intensity distributions, and the endo- and epi-cardial contours are initialized automatically as zeros of an underlying level set function. During the model evolution phase, the model deformation is driven by the minimization of an energy function consisting of five terms: model intensity, edge attraction, shape prior, contours interaction, and contour smoothness. The energy function is minimized iteratively by adaptively weighting the five terms in the energy function using an annealing algorithm. The validation experiments were performed on a pool of cine data sets of five volunteers. The difference between the semiautomated segmentation and manual segmentation was sufficiently small as to be considered clinically irrelevant. This relatively accurate semiautomated segmentation method can be used to significantly increase the throughput of strain analysis of cine displacement-encoded MR images for clinical applications

We propose a novel meshless deformable model for in vivo Left Ventricle (LV) 3D motion estimation and analysis based on tagged MRI (tMRI). The meshless deformable model can capture global deformations such as contraction and torsion with a few parameters, while track local deformations with Laplacian representation. In particular, the model performs well even when the control points (tag intersections) are relatively sparse. We test the performance of the meshless model on a numeric phantom, as well as in vivo heart data of healthy subjects and patients. The experimental results show that the meshless deformable model can fully recover the myocardial motion and strain in 3D

Fast tracking of motion is the key step towards tagged MRI-based quantitative cardiac analysis. Existing motion tracking approaches, including the widely used HARP method, are either time consuming or qualitatively inconsistent, or both. We present in this paper a new fast motion tracking method based on a meshless kernel. For MR image sequences containing multiple image frames, tag intersections are automatically detected in all frames and indexed in the first frame. Then a thin plate spline approach is used to establish a point-to-point correspondence between tag intersections in the initial and the current frame. Lastly, we use a meshless registration kernel to generate a dense displacement map that minimizes the residual of sparse motion at intersections. To further improve the motion tracking, we develop a special technique to preserve tangential angles of tags at tag intersections. We tested our new method on both numerical phantoms and in vivo heart data. The motion tracking results are evaluated against the ground truth and manually drawn tags. Clinical application potential is demonstrated by cardiac strain analysis based on the proposed methodology