| Abstrakt: |
Medical image processing plays an important role in recent medication for training simulators, treatment planning systems, and the development of easy diagnosis. Brain tumour surgery and diagnosis requires precise 3D visualisation of the brain. Many researchers are still working on the 3D reconstruction of brain images from different 2D images. However, 3D visualisation and detection of possible brain tumours from MRI is an error-prone and time-consuming task. This paper intends to introduce a 3D reconstruction model along with the solution of the curve fitting problem via the optimisation process. This helps the model to sustain the accurate construction by estimating the boundary, corner points, etc. To make the better adjustment the parameters in the curve fitting process are optimised by a new clan updated grey wolf algorithm (CUGWA), which is the hybrid version of conventional GWO and EHO algorithms. The boundary fitting is precisely done by considering the minimisation of RMSE among original and fitted boundaries. Finally, the performance of the adopted method is validated over other existing schemes with respect to curve fit analysis and convergence analysis. |
