VR Representation of Brain Tumor based on Self Organisation Based Segmentation (SOBS) and 3D Reconstruction (VR-SOBS3DR) model

Abstract

The medical images are visualized using recent techniques like Virtual Reality (VR). This VR representation is a breakthrough for medical experts. The lacking of 3D capabilities is the most important problem in traditional visualization tools. But in VR, the three available dimensions are used. The anatomical areas of interest must be segmented to visualize medical images in 3D. Earlier segmentation methods require huge number of iterations, longer time and a reduced accuracy. Using new technologies, such as Virtual Reality based on the segmentation (SOBS) algorithm for visualization techniques implementation, we designed a complete platform to solve these problems and allow medical professionals to work more frequently with anatomical 3D models obtained from medical imaging. As a result, the medical images are imported and the automatic segmentation of certain anatomical structures is carried out with new algorithm SOBS that improve upon the current research results. Afterwards the isosurface method is used for 3D reconstruction is performed. Feature extraction is performed in the next stage in which five 3D features are extracted from 3D Gray Level Co-occurrence Matrix (GLCM). Then Random Forest Classifier is used for classify MR images into normal, glioma or meningioma. Finally the classified image is visualized using Virtual Reality. This project is unique, as it covers the whole process from uploading MRI brain images to automatic segmentation, 3D reconstruction, 3D feature extraction and classification using virtual reality. There is lot of researches about application of virtual reality for medical image 3D visualization; however, they are not automated platforms. Although some other anatomical structures can be studied, we focused on one case: a brain tumor MRI. Analyzing the application of the platform to more than 1000 dicom images and studying the results with medical specialists, we concluded that the installation of this system in hospitals would provide a considerable improvement as a tool for medical image visualization.