Related Experiment Video
Updated: Dec 27, 2025
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
Image Segmentation of Brain MRI Based on LTriDP and Superpixels of Improved SLIC
Yu Wang1,2, Qi Qi2, Xuanjing Shen2
1College of Applied Technology, Jilin University, Changchun 130012, China.
Abstract:
Non-uniform gray distribution and blurred edges often result in bias during the superpixel segmentation of medical images of magnetic resonance imaging (MRI). To this end, we propose a novel superpixel segmentation algorithm by integrating texture features and improved simple linear iterative clustering (SLIC). First, a 3D histogram reconstruction model is used to reconstruct the input image, which is further enhanced by gamma transformation. Next, the local tri-directional pattern descriptor is used to extract texture features of the image; this is followed by an improved SLIC superpixel segmentation. Finally, a novel clustering-center updating rule is proposed, using pixels with gray difference with original clustering centers smaller than a predefined threshold. The experiments on the Whole Brain Atlas (WBA) image database showed that, compared to existing state-of-the-art methods, our superpixel segmentation algorithm generated significantly more uniform superpixels, and demonstrated the performance accuracy of the superpixel segmentation in both fuzzy boundaries and fuzzy regions.
Insights
This study introduces an improved superpixel segmentation algorithm for magnetic resonance imaging (MRI) that enhances accuracy in medical image analysis by integrating texture features and advanced clustering techniques.
Area of Science:
- Medical Imaging
- Computer Vision
- Image Processing
Background:
- Superpixel segmentation of medical images, particularly MRI, faces challenges due to non-uniform gray distribution and blurred edges, leading to segmentation bias.
- Existing methods struggle with accurately segmenting regions with fuzzy boundaries and non-uniform textures.
Purpose of the Study:
- To develop a novel superpixel segmentation algorithm for medical MRI images.
- To improve the accuracy and uniformity of superpixels, especially in challenging regions with blurred edges and non-uniform gray levels.
Main Methods:
- Proposed a novel algorithm integrating texture features with an improved Simple Linear Iterative Clustering (SLIC) method.
- Employed a 3D histogram reconstruction model and gamma transformation for image enhancement.
- Utilized a local tri-directional pattern descriptor for texture feature extraction.
- Introduced a new clustering-center updating rule based on gray difference thresholding.
Main Results:
- The proposed algorithm generated significantly more uniform superpixels compared to state-of-the-art methods.
- Demonstrated high performance accuracy in segmenting fuzzy boundaries and fuzzy regions within medical images.
- Experiments on the Whole Brain Atlas (WBA) database validated the algorithm's effectiveness.
Conclusions:
- The novel superpixel segmentation algorithm effectively addresses limitations in MRI analysis.
- The integration of texture features and improved SLIC enhances segmentation accuracy and uniformity.
- This method offers a robust solution for superpixel segmentation in complex medical imaging scenarios.
