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