Author:
Hamzah Norhafiza,Alias Norma,Abdul Wahab Syamshiyatul,Ali Omar Z
Abstract
Abstract
The inaccurate prediction of tumour is because of the 2D images do not present the complete natural tumour representation as in 3D visualization. In order to construct the 3D model, the contour of 2D MRI images must be merged together. In this work, the edge detection of brain tumour on 2D images is done using the Geodesic Active Contour (GAC) model based on Additive Operator Splitting (AOS), then 3D model is visualized using Image Manifold (IM) and Volume Estimation (VE) methods. The comparison of performance for both methods is calculated. In conclusion, the execution time for VE method is higher than IM method since more images are used in VE method to calculate the volume of the tumour accurately. In terms of iteration number, Volume Estimation has a higher number of iterations, but for error and root mean square error, both methods have roughly the same value.
Subject
General Physics and Astronomy
Reference18 articles.
1. Efficient and Reliable Schemes for Nonlinear Diffusion Filtering;Weickert;IEEE Transactions on Image Processing,1998
2. Fast Implicit Active Contour Models;Kuhne,2002
3. An Additive Operator Splitting Method for Microscopic Image Segmentation;Han,2010
4. Fast Evolution of Image Manifolds and Application to Filtering and Segmentation in 3D Medical Images;Deschamps;IEEE Transactions on Visualization and Computer Graphics,2004
5. Tangent Bundle Manifold Learning for Image Analysis;Kuleshov;Sixth International Conference on Machine Vision (ICMV 2013), Proc. of SPIE,2013