The creation of systems for automatic processing of computed tomography (CT) results is associated with the task of recognizing individual areas in the image and building their contours. The paper proposes a method for constructing an external non-self-intersecting contour of a simply-connected two-dimensional region on a cross section of a computer tomogram, and also considers the main problems arising during its implementation.
The method of 2D segmentation of vertebrae based on computer tomography data (DICOM files) in sagittal projection using artificial neural network Mask-RCNNN is considered in this study. The effectiveness of network recognition was compared with manual segmentation performed by a professional physician. The comparison of accuracy between the neural network and manual segmentation was evaluated using the Sørens coefficient. The result of automatic 2D segmentation has been tested by professional physicians. The application of the method makes it possible to significantly speed up the process of modeling bone structures of the spine in 2D mode to solve the problems of biomechanics.
Modeling of biological objects on the basis of computer and magnetic resonance imaging is a common practice today. DICOM source files (CT with contrast agent, heart without pathologies) were obtained at the Saratov cardiology center and correspond to diastole of cardiac cycle. The created geometric model consists of the internal volume of blood, ventricles, atria, heart valves and tendon chords. The resulting model can be studied using various computer systems, in particular, the finite element method.
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.