Optimized Shannon and Fuzzy Entropy based Machine Learning Model for Brain MRI Image Segmentation
Abstract
The pre-processing procedures for medical image segmentation are a crucial task in MRI image study. The medical image thresholding approaches are competent for bi level thresholding due to its' easiness, strength, fewer convergence period and accurateness. The efficiency can be maintained using an extensive search which can be employed for choosing the best thresholds. In this scenario, swarm intelligence-based learning algorithms can be suitable to gain the best thresholds. In this paper, we have focused in thresholding algorithm for segmentation of MRI brain image by maximizing fuzzy entropy and Shannon Entropy using machine learning and new evolutionary techniques. We have considered, Whale Optimization algorithm (WOA) in order to find the best outcome as well as compared the obtained results with the Shannon Entropy or fuzzy entropy-based examination that are fundamentally improved by Differential Evolution (DE), Particle Swarm Optimization (PSO), Social group optimization algorithm (SGO). It is discovered that overall operation could be effective by the strategy in features which can be captured through picture similarity matrix along with entropy values. We have observed that the proposed whale optimization model is able to better optimize the Shannon and fuzzy entropy compared to other swarm intelligence algorithms. It is also noticed that the new swarm intelligent algorithm i.e Social Group Optimization algorithm (SGO) is also performing better than the other two optimization algorithms i.e., Differential Evolution (DE), Particle Swarm Optimization (PSO) and providing very closer performance compared to Whale optimization algorithm. However, social group optimization algorithm requires little less CPU time than whale optimization algorithm.
Keyword(s)
Fuzzy entropy, Image segmentation, Image thresholding, Shannon entropy, Swarm intelligent algorithms
Full Text: PDF (downloaded 739 times)
Refbacks
- There are currently no refbacks.