Related Experiment Video
Updated: Aug 17, 2026
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
Published on: April 14, 2014
Automated detection and characterization of multiple sclerosis lesions in brain MR images
D Goldberg-Zimring1, A Achiron, S Miron
1Department of Biomedical Engineering, Technion, Israel Institute of Technology, Haifa.
Abstract:
In the present study an automatic algorithm for detection and contouring of multiple sclerosis (MS) lesions in brain magnetic resonance (MR) images is introduced. This algorithm automatically detects MS lesions in axial proton density, T2-weighted, gadolinium enhanced, and fast fluid attenuated inversion recovery (FLAIR) brain MR images. Automated detection consists of three main stages: (1) detection and contouring of all hyperintense signal regions within the image; (2) partial elimination of false positive segments (defined herein as artifacts) by size, shape index, and anatomical location; (3) the use of an artificial neural paradigm (Back-Propagation) for final removal of artifacts by differentiating them from true MS lesions. The algorithm was applied to 45 images acquired from 14 MS patients. The algorithm's sensitivity was 0.87 and the specificity 0.96. In 34 images, 100% of the lesions were detected. The algorithm potentially may serve as a useful preprocessing tool for quantitative MS monitoring via magnetic resonance imaging.
Insights
This study introduces an automated algorithm for detecting multiple sclerosis (MS) lesions in brain MRI scans. The algorithm shows high accuracy, potentially aiding in quantitative monitoring of MS progression.
Area of Science:
- Medical Imaging
- Neurology
- Artificial Intelligence
Background:
- Multiple sclerosis (MS) diagnosis and monitoring rely heavily on Magnetic Resonance Imaging (MRI).
- Accurate and automated detection of MS lesions in MRI is crucial for objective disease assessment.
- Manual lesion segmentation is time-consuming and subject to inter-observer variability.
Purpose of the Study:
- To develop and evaluate an automated algorithm for detecting and contouring multiple sclerosis lesions in brain MRI.
- To assess the algorithm's performance in terms of sensitivity and specificity.
- To explore the potential of the algorithm as a tool for quantitative MS monitoring.
Main Methods:
- An automatic algorithm was developed for MS lesion detection and contouring in various brain MRI sequences (proton density, T2-weighted, gadolinium-enhanced, FLAIR).
- The algorithm involves three stages: hyperintense region detection, artifact elimination based on size/shape/location, and artificial neural network (Back-Propagation) based final artifact removal.
- The algorithm was tested on 45 MRI images from 14 MS patients.
Main Results:
- The algorithm achieved a sensitivity of 0.87 and a specificity of 0.96.
- 100% of lesions were detected in 34 out of 45 images.
- The automated detection successfully differentiated true MS lesions from artifacts.
Conclusions:
- The developed automatic algorithm demonstrates high accuracy in detecting and contouring MS lesions on brain MRI.
- The algorithm shows potential as an efficient preprocessing tool for quantitative monitoring of multiple sclerosis.
- Automated lesion detection can improve the objectivity and efficiency of MS monitoring through MRI.
