Segmentation and Classification of Brain Tumor from Magnetic Resonance Images Using K-Means Algorithm and Hybrid PSO-WCA Based Radial Basis Function Neural Network Article Swipe
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.30534/ijatcse/2020/128952020
The manual detection and classification of the tumor becomes a rigorous and hectic task for the radiologists from magnetic resonance images.This paper presents a novel Hybrid PSO-WCA (Particle Swarm Optimization-Water Cycle Algorithm) based Radial Basis Function Neural Network (RBFNN) machine learning classification model for brain tumors classification.The K-means algorithm has been employed for segmentation and GLCM (Gray Level Co-occurrence Matrix) technique for feature extraction.The extracted features are aligned as input to the PSO-WCA based radial basis function neural network for the classification of brain tumors.The weights of the RBFNN are updated by the PSO-WCA (Particle Swarm optimization) algorithm and the centers of the RBFNN are chosen by K-means algorithm.Further, the malignant and benign tumors has been classified by Fast fuzzy c-means, KNN (Nearest neighborhood) algorithm, Fuzzy c means algorithm and K-Means algorithm by taking features as input for visual localization and the performance of the clustering classification has been presented.This research work considered the brain tumor MRI (Magnetic Resonance Image) Dataset-255 from Harvard medical school.The result obtained from the proposed hybrid PSO-WCA-RBFNN classification model shows better classification accuracy of 99.62% and comparison results with the PSO-RBFNN, WCA-RBFNN and LMS-RBFNN models are also presented.
Related Topics To Compare & Contrast
- Type
- article
- Language
- en
- Landing Page
- http://doi.org/10.30534/ijatcse/2020/128952020
- https://doi.org/10.30534/ijatcse/2020/128952020
- OA Status
- bronze
- Cited By
- 1
- References
- 22
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4230063083