Int J Performability Eng ›› 2021, Vol. 17 ›› Issue (12): 1016-1026.doi: 10.23940/ijpe.21.12.p6.10161026

Previous Articles     Next Articles

LSOA Optimized Curve Fitting-based 3D Reconstruction of Brain Tumor

Sushitha Susan Joseph, and Aju D*   

  1. School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, 632014, India
  • Contact: * E-mail address:

Abstract: Medical image processing encompasses the utilization of three dimensionally reconstructed images from CT or MRI scans to diagnose pathologies, surgical planning, and radiation dose calculation. The 3D reconstructed images help the radiologists and surgeons to better understand the complicated internal anatomy. This paper proposes a novel technique of using the curve fitting process through optimization for the three dimensional reconstruction of a brain tumor. The curve fitting process achieves accurate reconstruction by estimating the boundaries as well as the corner points of the model. The process of optimization in the curve fitting process is carried out using the new Levy Walk Trajectory based Seagull Optimization Algorithm which combines the merits of Levy walk with the metaheuristic Seagull Optimization Algorithm to obtain better accuracy. The boundary fitting is precisely done by considering the minimization of root mean square error among original and fitted boundaries. Finally, performance of the adopted method is validated over other existing schemes with respect to curve fit analysis and convergence analysis.

Key words: MRI, 3D reconstruction, brain tumor, Bezier curve, parameterization