Related Experiment Video
Updated: Mar 1, 2026
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
Neural Network-Based Learning Kernel for Automatic Segmentation of Multiple Sclerosis Lesions on Magnetic Resonance
H Khastavaneh1, H Ebrahimpour-Komleh1
1Department of Computer Engineering, Faculty of Computer and Electrical Engineering, University of Kashan, Kashan, Iran.
Background:
Multiple Sclerosis (MS) is a degenerative disease of central nervous system. MS patients have some dead tissues in their brains called MS lesions. MRI is an imaging technique sensitive to soft tissues such as brain that shows MS lesions as hyper-intense or hypo-intense signals. Since manual segmentation of these lesions is a laborious and time consuming task, automatic segmentation is a need.
Materials And Methods:
In order to segment MS lesions, a method based on learning kernels has been proposed. The proposed method has three main steps namely; pre-processing, sub-region extraction and segmentation. The segmentation is performed by a kernel. This kernel is trained using a modified version of a special type of Artificial Neural Networks (ANN) called Massive Training ANN (MTANN). The kernel incorporates surrounding pixel information as features for classification of middle pixel of kernel. The materials of this study include a part of MICCAI 2008 MS lesion segmentation grand challenge data-set.
Results:
Both qualitative and quantitative results show promising results. Similarity index of 70 percent in some cases is considered convincing. These results are obtained from information of only one MRI channel rather than multi-channel MRIs.
Conclusion:
This study shows the potential of surrounding pixel information to be incorporated in segmentation by learning kernels. The performance of proposed method will be improved using a special pre-processing pipeline and also a post-processing step for reducing false positives/negatives. An important advantage of proposed model is that it uses just FLAIR MRI that reduces computational time and brings comfort to patients.
Insights
This study introduces an automated method for segmenting Multiple Sclerosis (MS) brain lesions using a learning kernel and Artificial Neural Networks (ANN). The approach effectively utilizes surrounding pixel information for improved MS lesion segmentation from MRI scans.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Artificial Intelligence in Medicine
Background:
- Multiple Sclerosis (MS) is a central nervous system degenerative disease characterized by brain lesions.
- Magnetic Resonance Imaging (MRI) detects MS lesions as signal abnormalities.
- Manual segmentation of MS lesions is time-intensive, necessitating automated methods.
Purpose of the Study:
- To develop and evaluate an automated method for segmenting MS brain lesions.
- To leverage learning kernels and Artificial Neural Networks (ANN) for enhanced segmentation accuracy.
- To utilize surrounding pixel information for improved lesion detection.
Main Methods:
- A novel segmentation method employing learning kernels trained with a modified Massive Training ANN (MTANN).
- The method incorporates surrounding pixel data as features for classifying central pixels.
- Utilized a dataset from the MICCAI 2008 MS lesion segmentation challenge.
Main Results:
- Promising qualitative and quantitative results were achieved, with similarity indices reaching 70% in some cases.
- Effective segmentation was demonstrated using single-channel FLAIR MRI data.
- The method shows potential for accurate MS lesion segmentation.
Conclusions:
- Surrounding pixel information can be effectively incorporated into segmentation using learning kernels.
- The proposed method shows potential for automated MS lesion segmentation.
- Future improvements include specialized pre-processing and post-processing steps to reduce errors and enhance performance.
