The rupture of Intracranial Aneurysms is the most severe form of stroke with high rates of mortality and disability. One of its primary treatments is to use stent or Flow Diverter to divert the blood flow away from the IA in a minimal invasive manner. To optimize such treatments, it is desirable to provide an automatic tool for virtual stenting before its actual implantation. In this paper, we propose a novel method, called ball-sweeping, for rapid virtual stenting. Our method sweeps a maximum inscribed sphere through the aneurysmal region of the vessel and directly generates a stent surface touching the vessel wall without needing to iteratively grow a deformable stent surface. Our resulting stent mesh has guaranteed smoothness and variable pore density to achieve an enhanced occlusion performance. Comparing to existing methods, our technique is computationally much more efficient.
The automatic localization and segmentation, or parsing, of neuroanatomical brain structures is a key step
in many neuroscience tasks. However, the inherent variability in these brain structures and their appearance
continues to challenge medical image processing methods. The state of the art primarily relies upon local voxelbased
morphometry, Markov random field, and probabilistic atlas based approaches, which limits the ability to
explicitly capture the parts-based structure inherent in the brain. We propose a method that defines a principled
parts-based representation of the sub-cortical brain structures. Our method is based on the pictorial structures
model and jointly models the appearance of each part as well as the layout of the parts as a whole. Inference
is cast as a maximum a posteriori problem and solved in a steepest-descent manner. Experimental results on a
28-case data set demonstrate high accuracy of our method and substantiate our claim that there is significant
promise in a parts-based approach to modeling medical imaging structures.
Intervertebral disc herniation is a major reason for lower back pain (LBP), which is the second most common
neurological ailment in the United States. Automation of herniated disc diagnosis reduces the large burden
on radiologists who have to diagnose hundreds of cases each day using clinical MRI. We present a method
for automatic diagnosis of lumbar disc herniation using appearance and shape features. We jointly use the
intensity signal for modeling the appearance of herniated disc and the active shape model for modeling the
shape of herniated disc. We utilize a Gibbs distribution for classification of discs using appearance and shape
features. We use 33 clinical MRI cases of the lumbar area for training and testing both appearance and shape
models. We achieve over 91% accuracy in detection of herniation in a cross-validation experiment with specificity
of 91% and sensitivity of 94%.
With a steady increase of CT interventions, population dose is increasing. Thus, new approaches must be
developed to reduce the dose. In this paper, we present a means for rapid identification and reconstruction of
objects of interest in reconstructed data. Active shape models are first trained on sets of data obtained from
similar subjects. A reconstruction is performed using a limited number of views. As each view is added, the
reconstruction is evaluated using the active shape models. Once the object of interest is identified, the volume of
interest alone is reconstructed, saving reconstruction time. Note that the data outside of the objects of interest
can be reconstructed using fewer views or lower resolution providing the context of the region of interest data.
An additional feature of our algorithm is that a reliable segmentation of objects of interest is achieved from
a limited set of projections. Evaluations were performed using simulations with Shepp-Logan phantoms and
animal studies. In our evaluations, regions of interest are identified using about 33 projections on average. The
overlap of the identified regions with the true regions of interest is approximately 91%. The identification of the
region of interest requires about 1/5 of the time required for full reconstruction, the time for reconstruction of the
region of interest is currently determined by the fraction of voxels in the region of interest (i.e, voxels in region
of interest/voxels in full volume). The algorithm has several important clinical applications, e.g., rotational
angiography, digital tomosynthesis mammography, and limited view computed tomography.
We propose a statistical model-based approach for the segmentation of fragments of DNA as a first step in the automation of the primarily manual process of comparing two or more images resulting from the Restriction Landmark Genomic Scanning (RLGS) method. These 2D gel electrophoresis images are the product of the separation of DNA into fragments that appear as spots on X-ray films. The goal is to find instances where a spot appears in one image and not in another since a missing spot can be correlated with a region of DNA that has been affected by a disease such as cancer. The entire comparison process is typically done manually, which is tedious and very error prone. We pose the problem as the labeling of each image pixel as either a spot or non-spot and use a Markov Random Field (MRF) model and simulated annealing for inference. Neighboring spot labels are then connected to form spot regions. The MRF based model was tested on actual 2D gel electrophoresis images.
The use of cone beam computed tomography (CBCT) is growing in the clinical arena, due to its ability to
provide 3-D information during interventions, its high diagnostic quality (sub-millimeter resolution), and its short
scanning times (10 seconds). In many situations, the reconstructions suffer from artifacts from high contrast
objects (due mainly to angular sampling by the projections or by beam hardening) which can reduce image
quality. In this study, we propose a novel algorithm to reduce these artifacts. In our approach, these objects are
identified and then removed in the sinogram space by using computational geometry techniques. In particular,
the object is identified in a reconstruction from a few views. Then, the rays (projection lines) intersecting the
high contrast objects are identified using the technique of topological walk in a dual space which effectively
models the problem as a visibility problem and provides a solution in optimal time and space complexity. As a
result, the corrections can be performed in real time, independent of the projection image size. Subsequently,
a full reconstruction is performed by leaving out the high contrast objects in the reconstructions. Evaluations
were performed using simulations and animal studies. The artifacts are significantly reduced when using our
approach. This optimal time and space complexity and relative simple implementation makes our approach
attractive for artifact reduction.
Endoscopy is an invaluable tool for several surgical and diagnostic applications. It permits minimally invasive
visualization of internal structures thus involving little or no injury to internal structures. This method of visualization
however restricts the size of the imaging device and therefore compromises on the field of view captured in a single
image. The problem of a narrow field of view can be solved by capturing video sequences and stitching them to generate
a mosaic of the scene under consideration. Registration of images in the sequence is therefore a crucial step. Existing methods compute frame-to-frame registration estimates and use these to resample images in order to generate a mosaic. The complexity of the appearance of internal structures and accumulation of registration error in frame to frame estimates however can be large enough to cause a cumulative drift that can misrepresent the scene. These errors can be reduced by application of global adjustment schemes. In this paper, we present a set of techniques for overcoming this problem of drift for pixel based registration in order to achieve global consistency of mosaics. The algorithm uses the frame-to-frame estimate as an initialization and subsequently corrects these estimates by setting up a large scale optimization problem which simultaneously solves for all corrections of estimates. In addition we set up a graph and introduce loop closure constraints in order to ensure consistency of registration. We present our method and results in semi global and fully global graph based adjustment methods as well as validation of our results.
We present a novel methodology for the automated segmentation of Glioblastoma Multiforme tumors given only a high-resolution
T1 post-contrast enhanced channel, which is routinely done in clinical MR acquisitions. The main
contribution of the paper is the integration of contextual filter responses, to obtain a better class separation of abnormal
and normal brain tissues, into the multilevel segmentation by weighted aggregation (SWA) algorithm. The SWA
algorithm uses neighboring voxel intensities to form an affinity between the respective voxels. The affinities are then
recursively computed for all the voxel pairs in the given image and a series of cuts are made to produce segments that
contain voxels with similar intensity properties. SWA provides a fast method of partitioning the image, but does not
produce segments with meaning. Thus, a contextual filter response component was integrated to label the aggregates as
tumor or non-tumor. The contextual filter responses were computed via texture filter responses based on the gray level
co-occurrence matrix (GLCM) method. The GLCM results in texture features that are used to quantify the visual
appearance of the tumor versus normal tissue. Our results indicate the benefit of incorporating contextual features and
applying non-linear classification methods to segment and classify the complex case of grade 4 tumors.