Related Experiment Video
Updated: Aug 10, 2026
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
Unified approach for multiple sclerosis lesion segmentation on brain MRI
Balasrinivasa Rao Sajja1, Sushmita Datta, Renjie He
1Department of Diagnostic and Interventional Imaging, University of Texas Medical School at Houston, 6431 Fannin Street, Houston, TX 77030, USA.
Abstract:
The presence of large number of false lesion classification on segmented brain MR images is a major problem in the accurate determination of lesion volumes in multiple sclerosis (MS) brains. In order to minimize the false lesion classifications, a strategy that combines parametric and nonparametric techniques is developed and implemented. This approach uses the information from the proton density (PD)- and T2-weighted and fluid attenuation inversion recovery (FLAIR) images. This strategy involves CSF and lesion classification using the Parzen window classifier. Image processing, morphological operations, and ratio maps of PD- and T2-weighted images are used for minimizing false positives. Contextual information is exploited for minimizing the false negative lesion classifications using hidden Markov random field-expectation maximization (HMRF-EM) algorithm. Lesions are delineated using fuzzy connectivity. The performance of this algorithm is quantitatively evaluated on 23 MS patients. Similarity index, percentages of over, under, and correct estimations of lesions are computed by spatially comparing the results of present procedure with expert manual segmentation. The automated processing scheme detected 80% of the manually segmented lesions in the case of low lesion load and 93% of the lesions in those cases with high lesion load.
Insights
This study introduces an automated method to accurately segment brain lesions in multiple sclerosis (MS) using MRI. The novel approach improves lesion detection, crucial for monitoring disease progression and treatment effectiveness.
Area of Science:
- Medical Imaging
- Neurology
- Computer Science
Background:
- Accurate segmentation of brain lesions in Multiple Sclerosis (MS) is critical for volume determination.
- High rates of false lesion classifications complicate accurate MS lesion volume assessment on MRI.
Purpose of the Study:
- To develop and implement a combined parametric and nonparametric strategy to minimize false lesion classifications in MS brain MR images.
- To enhance the accuracy of automated lesion detection and delineation in MS patients.
Main Methods:
- Utilized proton density (PD), T2-weighted, and fluid attenuation inversion recovery (FLAIR) MRI sequences.
- Employed Parzen window classifier for CSF and lesion classification.
- Integrated image processing, morphological operations, ratio maps, hidden Markov random field-expectation maximization (HMRF-EM), and fuzzy connectivity for lesion delineation.
Main Results:
- The automated method achieved 80% detection of manually segmented lesions in low lesion load cases.
- Achieved 93% detection of manually segmented lesions in high lesion load cases.
- Quantitative evaluation on 23 MS patients demonstrated improved accuracy compared to manual segmentation.
Conclusions:
- The developed automated processing scheme effectively minimizes false positives and negatives in MS brain lesion segmentation.
- This strategy offers a reliable tool for accurate lesion volume determination in multiple sclerosis patients.
- The approach shows significant potential for improving the clinical assessment and management of MS.
