Automated Detection of Lupus White Matter Lesions in MRI
Eloy Roura1, Nicolae Sarbu2, Arnau Oliver1
1Department of Computer Architecture and Technology, University of Girona Girona, Spain.
Abstract:
Brain magnetic resonance imaging provides detailed information which can be used to detect and segment white matter lesions (WML). In this work we propose an approach to automatically segment WML in Lupus patients by using T1w and fluid-attenuated inversion recovery (FLAIR) images. Lupus WML appear as small focal abnormal tissue observed as hyperintensities in the FLAIR images. The quantification of these WML is a key factor for the stratification of lupus patients and therefore both lesion detection and segmentation play an important role. In our approach, the T1w image is first used to classify the three main tissues of the brain, white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF), while the FLAIR image is then used to detect focal WML as outliers of its GM intensity distribution. A set of post-processing steps based on lesion size, tissue neighborhood, and location are used to refine the lesion candidates. The proposal is evaluated on 20 patients, presenting qualitative, and quantitative results in terms of precision and sensitivity of lesion detection [True Positive Rate (62%) and Positive Prediction Value (80%), respectively] as well as segmentation accuracy [Dice Similarity Coefficient (72%)]. Obtained results illustrate the validity of the approach to automatically detect and segment lupus lesions. Besides, our approach is publicly available as a SPM8/12 toolbox extension with a simple parameter configuration.
Insights
This study presents an automated method for detecting and segmenting white matter lesions (WML) in lupus patients using MRI scans. The approach accurately identifies and quantifies these brain lesions, aiding in patient stratification.
Area of Science:
- Neuroimaging
- Radiology
- Medical Image Analysis
Background:
- Brain magnetic resonance imaging (MRI) is crucial for detecting and segmenting white matter lesions (WML).
- Lupus patients often exhibit WML, appearing as hyperintensities on FLAIR MRI sequences.
- Accurate quantification of WML is vital for lupus patient stratification.
Purpose of the Study:
- To develop an automated approach for segmenting white matter lesions (WML) in lupus patients.
- To utilize both T1-weighted (T1w) and fluid-attenuated inversion recovery (FLAIR) MRI images for lesion detection and segmentation.
Main Methods:
- Tissue classification of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) using T1w images.
- Detection of focal WML as intensity outliers in GM distribution using FLAIR images.
- Refinement of lesion candidates through post-processing steps considering size, tissue neighborhood, and location.
Main Results:
- Lesion detection achieved a True Positive Rate of 62% and a Positive Prediction Value of 80%.
- Segmentation accuracy, measured by the Dice Similarity Coefficient, was 72%.
- Qualitative and quantitative results demonstrate the approach's validity on 20 lupus patients.
Conclusions:
- The proposed automated method effectively detects and segments white matter lesions in lupus patients.
- The approach offers a valuable tool for lesion quantification and patient stratification.
- The method is available as a public SPM8/12 toolbox extension.
