Skull is the anatomic landmark for patient set up of head radiation therapy. Skull is generally segmented from
CT images because CT provides better definition of skull than MR imaging. In the mean time, radiation therapy is
planned on MR images for soft tissue information. This study utilized a knowledge-guided active model (KAM) method
to segmented skull on MR images in order to enable radiation therapy planning with MR images as the primary
planning dataset. KAM utilized age-specific skull mesh models that segmented from CT images using a conditional
region growing algorithm. Skull models were transformed to given MR images using an affine registration algorithm
based on normalized mutual information. The transformed mesh models actively located skull boundaries by
minimizing their total energy. The preliminary validation was performed on MR and CT images from five patients. The
KAM segmented skulls were compared with those segmented from CT images. The average image similarity (kappa
index) was 0.57. The initial validation showed that it was promising to segment skulls directly on MR images using
KAM.
Accurate registration of diagnosis and treatment images is a critical factor for the success of radiotherapy. This
study presents a feature-based image registration algorithm that uses a branch- and-bound method to search the
space of possible transformations, as well as a Hausdorff distance metric to evaluate their quality. This distance
is computed in the space of responses to a circular Gabor filter, in which, for each point of interest in both
reference and subject images, a vector of complex responses to different Gabor kernels is computed. Each kernel
is generated using different frequencies and variances of the Gabor function, which determines correspondent
regions in the images to be registered, by virtue of its rotation invariance characteristics. Responses to circular
Gabor filters have also been reported in literature as a successful tool for image classification; and in this
particular application we utilize them for patient positioning in cranial radiotherapy. For test purposes, we use
2D portal images acquired with an electronic portal imaging device (EPID). Our method presents EPID-EPID
registrations errors under 0.2 mm for translations and 0.05 deg for rotations (subpixel accuracy). We are using
fiducial marker registration as the ground truth for comparisons. Registration times average 2.70 seconds based
on 1400 feature points using a 1.4 GHz processor.
KEYWORDS: Brain, Magnetic resonance imaging, Neuroimaging, Image segmentation, 3D modeling, Visualization, Shape analysis, Tissues, Thalamus, Medical research
In this paper, we have developed a digital atlas of the pediatric human brain. Human brain atlases, used to visualize spatially complex structures of the brain, are indispensable tools in model-based segmentation and quantitative analysis of brain structures. However, adult brain atlases do not adequately represent the normal maturational patterns of the pediatric brain, and the use of an adult model in pediatric studies may introduce substantial bias. Therefore, we proposed to develop a digital atlas of the pediatric human brain in this study. The atlas was constructed from T1 weighted MR data set of a 9 year old, right-handed girl. Furthermore, we extracted and simplified boundary surfaces of 25 manually defined brain structures (cortical and subcortical) based on surface curvature. Higher curvature surfaces were simplified with more reference points; lower curvature surfaces, with fewer. We constructed a 3D triangular mesh model for each structure by triangulation of the structure's reference points. Kappa statistics (cortical, 0.97; subcortical, 0.91) indicated substantial similarities between the mesh-defined and the original volumes. Our brain atlas and structural mesh models (www.stjude.org/BrainAtlas) can be used to plan treatment, to conduct knowledge and modeldriven segmentation, and to analyze the shapes of brain structures in pediatric patients.
Automated brain tumor segmentation and detection are immensely important in medical diagnostics because it provides information associated to anatomical structures as well as potential abnormal tissue necessary to delineate appropriate surgical planning. In this work, we propose a novel automated brain tumor segmentation technique based on multiresolution texture information that combines fractal Brownian motion (fBm) and wavelet multiresolution analysis. Our wavelet-fractal technique combines the excellent multiresolution localization property of wavelets to texture extraction of fractal. We prove the efficacy of our technique by successfully segmenting pediatric brain MR images (MRIs) from St. Jude Children’s Research Hospital. We use self-organizing map (SOM) as our clustering tool wherein we exploit both pixel intensity and multiresolution texture features to obtain segmented tumor. Our test results show that our technique successfully segments abnormal brain tissues in a set of T1 images. In the next step, we design a classifier using Feed-Forward (FF) neural network to statistically validate the presence of tumor in MRI using both the multiresolution texture and the pixel intensity features. We estimate the corresponding receiver operating curve (ROC) based on the findings of true positive fractions and false positive fractions estimated from our classifier at different threshold values. An ROC, which can be considered as a gold standard to prove the competence of a classifier, is obtained to ascertain the sensitivity and specificity of our classifier. We observe that at threshold 0.4 we achieve true positive value of 1.0 (100%) sacrificing only 0.16 (16%) false positive value for the set of 50 T1 MRI analyzed in this experiment.
We propose formal analytical models for identification of tumors in medical images based on the hypothesis that the tumors have a fractal (self-similar) growth behavior. Therefore, the images of these tumors may be characterized as Fractional Brownian motion (fBm) processes with a fractal dimension (D) that is distinctly different than that of the image of the surrounding tissue. In order to extract the desired features that delineate different tissues in a MR image, we study multiresolution signal decomposition and its relation to fBm. The fBm has proven successful to modeling a variety of physical phenomena and non-stationary processes, such as medical images, that share essential properties such as self-similarity, scale invariance and fractal dimension (D). We have developed the theoretical framework that combines wavelet analysis with multiresolution fBm to compute
D.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.