Study of 2D MRI Interactive Tools for Cartilage Segmentation

Abstract

Image processing software is important in medical imaging fields. Medical Image segmentation could be achieved through manual, semiautomated and automated methods. However, manual segmentation consumes a lot of time and prone to human error. For automated segmentation tools, it is complicated since it has too many functions that may confuse the users. Furthermore, automated segmentation software does not allow additional improvement. In this paper, 2D interactive tools for knee cartilage segmentation was developed using Graphical User Interface (GUI) in MATLAB (Mathworks, Natick, MA). The purpose of this study was to evaluate the efficiency and intuitiveness of this segmentation software since the software are designed with three essential qualities which is efficient, convenience and intuitiveness. The interactive segmentation method that has been used in this software is Random Walk Algorithm. Further work will extend the software to three-dimensional segmentation and qualitative analysis.