Prior Information Guided Fuzzy Clustering with Spatial Neighborhood Information for MRI Image Segmentation

Abstract Clustering algorithms with deep neural network have attracted wide attention of scholars. A deep fuzzy K-means clustering algorithm model with adaptive loss function and entropy regularization (DFKM) is proposed by combining automatic encoder and clustering algorithm. Although it introduces adaptive loss function and entropy regularization to improve the robustness of the model, its segmentation effect is not ideal for high noise; At the same time, its model does not use a convolutional auto-encoder, which is not suitable for high-dimensional images.Therefore, on the basis of DFKM, this paper focus on image segmentation, combine neighborhood median and mean information of current pixel, introduce neighborhood information of membership degree, and extend Euclidean distance to kernel space by using kernel function, propose a dual-neighborhood information constrained deep fuzzy clustering based on kernel function (KDFKMS). A large number of experimental results show that compared with DFKM and classical image segmentation algorithms, this algorithm has stronger anti-noise robustness.

Download Full-text

Bias-corrected intuitionistic fuzzy c-means with spatial neighborhood information approach for human brain MRI image segmentation

IEEE Transactions on Fuzzy Systems ◽

10.1109/tfuzz.2020.3044253 ◽

2020 ◽

pp. 1-1

Author(s):

Dhirendra Kumar ◽

Ramesh Kumar Agrawal ◽

Puneet Kumar

Keyword(s):

Image Segmentation ◽

Human Brain ◽

Brain Mri ◽

Information Approach ◽

Fuzzy C Means ◽

Neighborhood Information ◽

Intuitionistic Fuzzy ◽

Mri Image

Download Full-text

Optimized Fuzzy Clustering Algorithms for Brain MRI Image Segmentation Based on Local Gaussian Probability and Anisotropic Weight Models

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001418570057 ◽

2018 ◽

Vol 32 (09) ◽

pp. 1857005 ◽

Cited By ~ 2

Author(s):

Ting Zhang

Keyword(s):

Image Segmentation ◽

Fuzzy Clustering ◽

Clustering Algorithm ◽

Clinical Medicine ◽

Brain Mri ◽

Brain Magnetic Resonance Imaging ◽

Segmentation Algorithm ◽

Fuzzy C Means ◽

Anisotropic Weight ◽

Mri Image

Brain Magnetic Resonance Imaging (MRI) image segmentation is one of the critical technologies of clinical medicine, and is the basis of three-dimensional reconstruction and downstream analysis between normal tissues and diseased tissues. However, there are various limitations in brain MRI images, such as gray irregularities, noise, and low contrast, reducing the accuracy of the brain MRI images segmentation. In this paper, we propose two optimization solutions for the fuzzy clustering algorithm based on local Gaussian probability fuzzy C-means (LGP-FCM) model and anisotropic weight fuzzy C-means (AW-FCM) model and apply it in brain MRI image segmentation. An FCM clustering algorithm is proposed based on AW-FCM. By introducing the new neighborhood weight calculation method, each point has the weight of anisotropy, effectively overcomes the influence of noise on the image segmentation. In addition, the LGP model is introduced in the objective function of fuzzy clustering, and a fuzzy clustering segmentation algorithm based on LGP-FCM is proposed. A clustering segmentation algorithm of adaptive scale fuzzy LGP model is proposed. The neighborhood scale corresponding to each pixel in the image is automatically estimated, which improves the robustness of the model and achieves the purpose of precise segmentation. Extensive experimental results demonstrate that the proposed LGP-FCM algorithm outperforms comparison algorithms in terms of sensitivity, specificity and accuracy. LGP-FCM can effectively segment the target regions from brain MRI images.

Download Full-text