Related Experiment Video
Updated: Jul 7, 2026
Manual Segmentation of the Human Choroid Plexus Using Brain MRI
Published on: December 15, 2023
Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method
Rasoul Khayati1, Mansur Vafadust, Farzad Towhidkhah
1Biomedical Engineering Faculty, Amirkabir University of Technology, Tehran, Iran.
Abstract:
In this paper, an approach is proposed for fully automatic segmentation of MS lesions in fluid attenuated inversion recovery (FLAIR) Magnetic Resonance (MR) images. The proposed approach, based on a Bayesian classifier, utilizes the adaptive mixtures method (AMM) and Markov random field (MRF) model to obtain and upgrade the class conditional probability density function (CCPDF) and the a priori probability of each class. To compare the performance of the proposed approach with those of previous approaches including manual segmentation, the similarity criteria of different slices related to 20 MS patients were calculated. Also, volumetric comparison of lesions volume between the fully automated segmentation and the gold standard was performed using correlation coefficient (CC). The results showed a better performance for the proposed approach, compared to those of previous works.
Insights
This study introduces an automated method for segmenting multiple sclerosis (MS) lesions in MRI scans. The novel approach demonstrates superior accuracy compared to existing methods for MS lesion detection.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neurology
Background:
- Accurate segmentation of multiple sclerosis (MS) lesions in Magnetic Resonance (MR) images is crucial for diagnosis and treatment monitoring.
- Manual segmentation is time-consuming and prone to inter-observer variability.
- Existing automated methods may lack sufficient accuracy and robustness.
Purpose of the Study:
- To develop and evaluate a fully automatic approach for segmenting MS lesions in fluid attenuated inversion recovery (FLAIR) MR images.
- To compare the proposed method's performance against manual segmentation and other existing techniques.
Main Methods:
- A Bayesian classifier-based approach utilizing adaptive mixtures method (AMM) and Markov random field (MRF) model.
- Obtaining and upgrading class conditional probability density function (CCPDF) and a priori probability of each class.
- Validation using similarity criteria and volumetric comparison (correlation coefficient) against manual segmentation in 20 MS patients.
Main Results:
- The proposed fully automatic segmentation approach demonstrated superior performance compared to previous methods.
- High correlation coefficients were observed in volumetric comparisons between automated and manual segmentation.
- The method achieved accurate segmentation of MS lesions across different slices.
Conclusions:
- The developed automated segmentation approach offers a promising, accurate, and efficient tool for MS lesion analysis in FLAIR MR images.
- This method has the potential to improve the clinical workflow for MS patient management.
- The Bayesian classifier with AMM and MRF provides a robust framework for automated medical image segmentation.
