Related Experiment Video
Updated: Jun 30, 2026
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
A modified FCM algorithm for MRI brain image segmentation using both local and non-local spatial constraints
Jianzhong Wang1, Jun Kong, Yinghua Lu
1School of Mathematics and Statistics, Northeast Normal University, Changchun, China. wangjz019@nenu.edu.cn
Abstract:
Image segmentation is often required as a preliminary and indispensable stage in the computer aided medical image process, particularly during the clinical analysis of magnetic resonance (MR) brain images. In this paper, we present a modified fuzzy c-means (FCM) algorithm for MRI brain image segmentation. In order to reduce the noise effect during segmentation, the proposed method incorporates both the local spatial context and the non-local information into the standard FCM cluster algorithm using a novel dissimilarity index in place of the usual distance metric. The efficiency of the proposed algorithm is demonstrated by extensive segmentation experiments using both simulated and real MR images and by comparison with other state of the art algorithms.
Insights
This study introduces a modified fuzzy c-means algorithm for improved magnetic resonance (MR) brain image segmentation. The new method enhances accuracy by incorporating spatial and non-local information to reduce noise in medical imaging.
Area of Science:
- Medical Imaging
- Computer Vision
- Artificial Intelligence
Background:
- Medical image segmentation is crucial for computer-aided diagnosis, especially for Magnetic Resonance (MR) brain images.
- Standard segmentation algorithms can be affected by noise, impacting diagnostic accuracy.
Purpose of the Study:
- To present a modified fuzzy c-means (FCM) algorithm for enhanced MRI brain image segmentation.
- To improve the robustness of FCM by reducing noise effects.
Main Methods:
- A modified fuzzy c-means (FCM) algorithm was developed for MRI brain image segmentation.
- The algorithm incorporates local spatial context and non-local information.
- A novel dissimilarity index replaced the standard distance metric to mitigate noise.
Main Results:
- The modified FCM algorithm demonstrated efficient segmentation of both simulated and real MR images.
- Experimental results showed improved performance compared to existing state-of-the-art algorithms.
- The method effectively reduced noise interference during the segmentation process.
Conclusions:
- The proposed modified FCM algorithm offers a robust and effective solution for MRI brain image segmentation.
- Incorporating spatial and non-local information significantly enhances segmentation accuracy and noise reduction.
- This approach holds promise for improving computer-aided medical image analysis.
