A Neural Network Approach to Medical Image Segmentation and Three-Dimensional Reconstruction
Medical Image Analysis represents a very important step in clinical diagnosis. It provides image segmentation of the Region of Interest (ROI) and the generation of a three-dimensional model, representing the selected object. In this work, was proposed a neural network segmentation based on Self-Organizing Maps (SOM) and a three-dimensional SOM architecture to create a 3D model, starting from 2D data of extracted contours. The utilized dataset consists of a set of CT images of patients presenting a prosthesis’ implant, in DICOM format. An application was developed in Visual C++, which provides an user interface to visualize DICOM images and relative segmentation. Moreover it generates a three-dimensional model of the segmented region using Direct3D.
KeywordsSegmentation Technique Neural Network Approach Segmented Region Streak Artifact Adaptive Resonance Theory
Unable to display preview. Download preview PDF.
- 2.Kohonen, T.: Self-Organizing Maps: Optimization and Approaches. In: ICANN, Espoo, Finland (1991)Google Scholar
- 3.Digital Imaging and Communications in Medicine (DICOM), National Electrical Manufacturers Association (2004)Google Scholar
- 5.Gelenbe, E., Feng, Y., Krishnan, K.R.R.: Neural Network Methods for Volumetric Magnetic Resonance Imaging of the Human Brain, pp. 1488–1496. IEEE, Los Alamitos (1996)Google Scholar
- 7.Fausett, L.: Fundamentals of Neural Networks – Architectures, Algorithms and ApplicationsGoogle Scholar
- 8.Stănciulescu, V.: 3D Tomography: Computerized Modeling of 2D scanned images. Results. Advantages. General Inspectorate for Communications and Information Technology Timişoara, RomaniaGoogle Scholar
- 9.Galin, E., Akkouche, S.: Fast Surface Reconstruction from Contours using Implicit Surfaces, Laboratoire d’Informatique Graphique Image et ModèlisationGoogle Scholar
- 10.Petzold, C.: Programming Windows. Microsoft Programming Series (1998)Google Scholar