A level set method based on domain transformation and bias correction for MRI brain tumor segmentation

2021 ◽  
Vol 352 ◽  
pp. 109091
Author(s):  
Asieh Khosravanian ◽  
Mohammad Rahmanimanesh ◽  
Parviz Keshavarzi ◽  
Saeed Mozaffari
Keyword(s):  
Brain Tumor ◽  
Level Set Method ◽  
Level Set ◽  
Bias Correction ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Mri Brain ◽  
Domain Transformation

GPU-Based Level Set Method for MRI Brain Tumor Segmentation using Modified Probabilistic Clustering

2016 ◽  
pp. 106-130 ◽  
Author(s):  
Ram Kumar ◽  
Sweta Rani ◽  
Abahan Sarkar ◽  
Fazal Ahmed Talukdar
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Intrinsic Nature ◽  
Probabilistic Clustering ◽  
Mri Brain ◽  
Complex Shapes ◽  
Boltzmann Method ◽  
Robust To Noise

The level set method (LSM) has been widely used in image segmentation due to its intrinsic nature which allows handling complex shapes and topological changes easily. We propose a new level set algorithm, which is based on probabilistic c mean objective function which incorporates intensity inhomogeneity in image and robust to noise. The computational complexity of the proposed LSM is greatly reduced by using highly parallelizable lattice Boltzmann method (LBM). So the proposed algorithm is effective and highly parallelizable. The proposed LSM is implemented using Experimental results demonstrate the performance of the proposed method.

GPU-Based Level Set Method for MRI Brain Tumor Segmentation Using Modified Probabilistic Clustering

2017 ◽  
pp. 1053-1078
Author(s):  
Ram Kumar ◽  
Sweta Rani ◽  
Abahan Sarkar ◽  
Fazal Ahmed Talukdar
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Intrinsic Nature ◽  
Probabilistic Clustering ◽  
Mri Brain ◽  
Complex Shapes ◽  
Boltzmann Method ◽  
Robust To Noise

The level set method (LSM) has been widely used in image segmentation due to its intrinsic nature which allows handling complex shapes and topological changes easily. We propose a new level set algorithm, which is based on probabilistic c mean objective function which incorporates intensity inhomogeneity in image and robust to noise. The computational complexity of the proposed LSM is greatly reduced by using highly parallelizable lattice Boltzmann method (LBM). So the proposed algorithm is effective and highly parallelizable. The proposed LSM is implemented using Experimental results demonstrate the performance of the proposed method.

scholarly journals Segmentation of MRI Brain Tumor Image using Optimization based Deep Convolutional Neural networks (DCNN)

2021 ◽  
Vol 11 (1) ◽  
pp. 380-390
Author(s):  
Pradipta Kumar Mishra ◽  
Suresh Chandra Satapathy ◽  
Minakhi Rout
Keyword(s):  
Brain Tumor ◽  
Tumor Segmentation ◽  
Gray Wolf ◽  
Deep Convolutional Neural Networks ◽  
Brain Tumor Segmentation ◽  
Swarm Optimization ◽  
Brain Image ◽  
Mri Brain ◽  
Whale Optimization ◽  
The Brain

Abstract Segmentation of brain image should be done accurately as it can help to predict deadly brain tumor disease so that it can be possible to control the malicious segments of brain image if known beforehand. The accuracy of the brain tumor analysis can be enhanced through the brain tumor segmentation procedure. Earlier DCNN models do not consider the weights as of learning instances which may decrease accuracy levels of the segmentation procedure. Considering the above point, we have suggested a framework for optimizing the network parameters such as weight and bias vector of DCNN models using swarm intelligent based algorithms like Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Gray Wolf Optimization (GWO) and Whale Optimization Algorithm (WOA). The simulation results reveals that the WOA optimized DCNN segmentation model is outperformed than other three optimization based DCNN models i.e., GA-DCNN, PSO-DCNN, GWO-DCNN.

Sign in / Sign up

Export Citation Format

Share Document