.png){kind=icon}
返回
Brain tumor MRI image segmentation using an optimized multi-kernel FCM method with a pre-processing stage
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-022-14045-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Because of the variety of shapes, locations, and image intensities, image segmentation is a more difficult endeavor in image processing. The most frequent diseases in the world are brain tumors. Therefore, brain tumor segmentation is essential in the medical field. The objective of this work is to propose image denoising and segmentation algorithms, as image segmentation is highly dependent on image denoising. The proposed image denoising algorithm is included in this article as part of the pre-processing stage. For image denoising, a novel adaptive diffusivity function based on partial differential equations is implemented. The diffusivity function's purpose is to enhance the images of brain tumors using a gradient, a Laplacian, and an adaptive threshold while also preserving image details. For image segmentation, the enhanced image is fed into an improved multi-kernel fuzzy c-means method, which then optimizes the centroid using an elephant herding optimization algorithm. Finally, it differentiates between tumor and non-tumor tissue. Images from the BRATS2020 Database were used to assess the effectiveness of the proposed approaches. When compared to conventional techniques, the proposed method performs well and proves to be an effective technique (PSNR-39.4001dBs, SSIM-99.78%, and MSE-7.4656 for image denoising; Sensitivity-98.45%, specificity-99.87%, and accuracy-99.83% for image segmentation at sigma= 20). The proposed method is developed and demonstrated in the MATLAB environment.
Keyword:
Partial differential equation
Diffusivity function
Multi-kernel fuzzy c-means method
Elephant herding optimization algorithm
Adaptive threshold
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
An improved anisotropic diffusion filter with semi-adaptive threshold for edge preservation.png)
SIGNAL PROCESSING
SIGNAL PROCESSINGIF3.6
PREAI
分享收藏On the choice of the parameters for anisotropic diffusion in image processingPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Impediments to Regulatory Compliance of Requirements in Contractual Systems Engineering Projects合同系统工程项目中要求合规的障碍
PREAI
分享收藏
查看更多内容