Aleksandrs Glazs

A Surface Smoothing Method for a 3D Model of a Medical Object

This paper describes a method to smoothen the surface of a Medical object’s 3D model. This method is intended to be used on model that was obtained by a triangulation algorithm, but it also can be used on a model that was obtained by a marching cubes algorithm. The basic principle behind this algorithm is that it adjusts the position of the vertices of a 3D model relative to the neighboring vertices, thus evening the rough edges. This method was tested on the model of human head, which was acquired by computer tomography and it showed considerable visual improvement of the model.

Medical Image Region Extraction and 3D Modeling Based on Approximating Curves

This work describes several methods that intend to solve such medical image processing tasks as extraction and 3D visualization of the region of interest (ROI). The proposed methods were tested on the medical images of a brain acquired by computer tomography and proven to be applicable to different types of ROI, resulting in a possible visualization of several ROI at once, i.e. pathology and the head of a patient. The results can be used to provide practical improvements to the reliability of medical diagnostics.

Volume Estimation of Pathology Zones in 3D Medical Images

Medical images of a brain, acquired with computer tomography (CT) or magnetic resonance (MR) are widely used in medicine for patient diagnosis. Therefore, a task of pathology zone detection and its volume estimation develops in medical image analysis. To successfully solve this task several problems have to be considered: 3D visualization of medical images, image segmentation, pathology zone extraction and volume estimation of the extracted zone. Standard software for processing medical CT and MR images in many cases does not allow extraction of the three-dimensional pathology zone and its volume estimation. Often the detection of pathology zone and its volume estimation is so complex, that the physicians prefer to measure only the pathology zone’s maximum axial and coaxial diameters in two-dimensional slices of medical images, although it is clear, that precise volume estimation could be of great assistance to the physicians in patient diagnostics. In addition, the standard medical imaging software is very specific — it is usually installed only on one work station linked to medical hardware and that is not always convenient. The problems described above complicate the diagnosis of the patient for physicians.