In this work, we introduce a new representation technique of 2D contour shapes and a sequence similarity measure to
characterize 2D regions of interest in medical images. First, we define a distance function on contour points in order to
map the shape of a given contour to a sequence of real numbers. Thus, the computation of shape similarity is reduced to
the matching of the obtained sequences. Since both a query and a target sequence may be noisy, i.e., contain some outlier
elements, it is desirable to exclude the outliers in order to obtain a robust matching performance. For the computation of
shape similarity, we propose the use of an algorithm which performs elastic matching of two sequences. The contribution
of our approach is that, unlike previous works that require images to be warped according to a template image for
measuring their similarity, it obviates this need, therefore it can estimate image similarity for any type of medical image
in a fast and efficient manner. To demonstrate our method's applicability, we analyzed a brain image dataset consisting
of corpus callosum shapes, and we investigated the structural differences between children with chromosome 22q11.2
deletion syndrome and controls. Our findings indicate that our method is quite effective and it can be easily applied on
medical diagnosis in all cases of which shape difference is an important clue.
We study the problem of classifying brain tumors as benign or malignant using information from magnetic resonance (MR) imaging and magnetic resonance spectroscopy (MRS) to assist in clinical diagnosis. The proposed approach consists of several steps including segmentation, feature extraction, feature selection, and classification model construction. Using an automated segmentation technique based on fuzzy connectedness we accurately outline the tumor mass boundaries in the MR images so that further analysis concentrates on these regions of interest (ROIs). We then apply a concentric circle technique on the ROIs to extract features that are utilized by the classification algorithms. To remove redundant features, we perform feature selection where only those features with discriminatory information (among classes) are used in the model building process. The involvement of MRS features further improves the classification accuracy of the model. Experimental results demonstrate the effectiveness of the proposed approach in classifying brain tumors in MR images.
Proc. SPIE. 5744, Medical Imaging 2005: Visualization, Image-Guided Procedures, and Display
KEYWORDS: 3D image reconstruction, Visualization, Image segmentation, Image processing, Image analysis, Medical imaging, 3D metrology, Stomach, Single photon emission computed tomography, 3D image processing
We have developed semi-automated and fully-automated tools for the analysis of 3D single-photon emission computed tomography (SPECT) images. The focus is on the efficient boundary delineation of complex 3D structures that enables accurate measurement of their structural and physiologic properties. We employ intensity based thresholding algorithms for interactive and semi-automated analysis. We also explore fuzzy-connectedness concepts for fully automating the segmentation process. We apply the proposed tools to SPECT image data capturing variation of gastric accommodation and emptying. These image analysis tools were developed within the framework of a noninvasive scintigraphic test to measure simultaneously both gastric emptying and gastric volume after ingestion of a solid or a liquid meal. The clinical focus of the particular analysis was to probe associations between gastric accommodation/emptying and functional dyspepsia. Employing the proposed tools, we outline effectively the complex three dimensional gastric boundaries shown in the 3D SPECT images. We also perform accurate volume calculations in order to quantitatively assess the gastric mass variation. This analysis was performed both with the semi-automated and fully-automated tools. The results were validated against manual segmentation performed by a human expert. We believe that the development of an automated segmentation tool for SPECT imaging of the gastric volume variability will allow for other new applications of SPECT imaging where there is a need to evaluate complex organ function or tumor masses.
In this paper, we introduce a new clustering algorithm, <i>FCC</i>, for intrusion detection based on the concept of fuzzy connectedness. This concept was introduced by Rosenfeld in 1979 and used with success in image segmentation; here we extend this approach to clustering and demonstrate its effectiveness in intrusion detection. Starting with a single or a few seed points in each cluster, all the data points are dynamically assigned to the cluster that has the highest fuzzy connectedness value (strongest connection). With an efficient heuristic algorithm, the time complexity of the clustering process is O(<i>N</i>log<i>N</i>), where <i>N</i> is the number of data points. The value of fuzzy connectedness is calculated using both the Euclidean distance and the statistical properties of clusters. This unsupervised learning method allows the discovery of clusters of any shape. Application of the method in intrusion detection demonstrates that it can detect not only known intrusion types, but also their variants. Experimental results on the KDD-99 intrusion detection data set show the efficiency and accuracy of this method. A detection rate above 94% and a false alarm rate below 4% are achieved, outperforming major competitors by at least 5%.