Objective: The purpose of this study is to propose a complete methodology for automatically registering three-dimensional (3D) pre-operative and post-operative CT scan dental volumes as well as to provide a toolset for quantifying and evaluating their volumetric differences. Methods: The proposed methodology was applied to cone beam CT (CBCT) data from 20 patients in order to assess the volume of augmented bone in the alveolar region. In each case, the pre-operative and post-operative data were registered using a 3D affine-based scheme. The performance of the 3D registration algorithm was evaluated by measuring the average distance between the edges of the registered sets. The differences between the registered sets were assessed through 3D subtraction radiography. The volume of the differences was finally evaluated by defining regions of interest in each slice of the subtracted 3D data and by combining all respective slices to model the desired volume of interest. The effectiveness of the algorithm was verified by applying it to several reference standard-shaped objects with known volumes. Results: Satisfactory alignment was achieved as a low average offset of 1.483 ¡ 1.558 mm was recorded between the edges of the registered sets. Moreover, the estimated volumes closely matched the volumes of the reference objects used for verification, as the recorded volume differences were less than 0.4 mm 3 in all cases. Conclusion: The proposed method allows for automatic registration of 3D CBCT data sets and the volumetric assessment of their differences in particular areas of interest. The proposed approach provides accurate volumetric measurements in three dimensions, requiring minimal user interaction.

No abstract

Abstract-In this paper a computer-aided diagnostic system for the classification of hepatic lesions from Computed Tomography (CT) images is presented. Regions of Interest (ROI's) taken from non-enhanced CT images of normal liver, hepatic cysts, hemangiomas, and hepatocellular carcinomas (a total of 147 samples), have been used as input to the system. The system consists of two levels: the feature extraction and the classification levels. The feature extraction level calculates the average grey scale and 48 texture characteristics, which are derived from the spatial grey-level co-occurrence matrices, obtained from the ROI's. The classifier level consists of three sequentially placed feed-forward Neural Networks (NN's), which are activated sequentially. The first NN classifies into normal or pathological liver regions. The pathological liver regions are classified by the second NN into cysts or "other disease". The third NN classifies "other disease" into hemangiomas and hepatocellular carcinomas. In order to enhance the performance of the classifier and improve the execution time, the dimensionality of the initial feature vector has been reduced using the sequential forward floating selection method for each individual NN input vector. A total classification rate of 98% has been achieved.

Segmentation of biomedical images is of great importance in various studies aiming to both the identification of regions of interests within the image and the performance of quantified measurements. Nevertheless, the segmentation of the biomedical images represents a wide range of medical cases and there is not a unique technique applicable to all kinds of medical images. In this study, three popular techniques for segmenting micro-CT images of bone microstructures are evaluated. Fixed threshold, Otsu's algorithm and a modified version of the Chan-Vese segmentation technique have been applied on micro-CT images and have been compared to higher resolution golden standard, that is histological images. The modification of the Chan-Vese technique is based on the novel implementation of a new initialization process called the Branch Point Initialization. Stereological measurements were performed on all the segmented images and statistically compared to the golden standard. Fixed threshold and the modified Chan-Vese technique have shown comparable results, with a maximum significant error of about 10%. However, Chan-Vese showed an easier, faster and more reliable segmentation procedure for optimal settings identification. The Otsu's method showed a maximum error larger than 20%. Given the limits and advantages of the known segmentation techniques, the proposed modified Chan-Vese active contour technique shows high potential for use in the segmentation of micro-CT images as well as in other high-resolution X-ray images. This potential is augmented by the recent introduction of high-resolution clinical technologies for which standard techniques have already shown to be insufficient.

No abstract