Validation of White-Matter Lesion Change Detection Methods on a Novel Publicly Available MRI Image Database
Žiga Lesjak1, Franjo Pernuš2, Boštjan Likar2,3
1University of Ljubljana, Faculty of Electrical Engineering, Tržaška 25, 1000, Ljubljana, Slovenia. ziga.lesjak@fe.uni-lj.si.
Abstract:
Changes of white-matter lesions (WMLs) are good predictors of the progression of neurodegenerative diseases like multiple sclerosis (MS). Based on longitudinal magnetic resonance (MR) imaging the changes can be monitored, while the need for their accurate and reliable quantification led to the development of several automated MR image analysis methods. However, an objective comparison of the methods is difficult, because publicly unavailable validation datasets with ground truth and different sets of performance metrics were used. In this study, we acquired longitudinal MR datasets of 20 MS patients, in which brain regions were extracted, spatially aligned and intensity normalized. Two expert raters then delineated and jointly revised the WML changes on subtracted baseline and follow-up MR images to obtain ground truth WML segmentations. The main contribution of this paper is an objective, quantitative and systematic evaluation of two unsupervised and one supervised intensity based change detection method on the publicly available datasets with ground truth segmentations, using common pre- and post-processing steps and common evaluation metrics. Besides, different combinations of the two main steps of the studied change detection methods, i.e. dissimilarity map construction and its segmentation, were tested to identify the best performing combination.
Insights
Automated methods for detecting white-matter lesion (WML) changes in multiple sclerosis (MS) were objectively compared using standardized metrics and public datasets. This study provides a reliable evaluation framework for WML quantification in neurodegenerative disease research.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Neurodegenerative Diseases
Background:
- White-matter lesions (WMLs) are key indicators of neurodegenerative disease progression, particularly in multiple sclerosis (MS).
- Longitudinal magnetic resonance (MR) imaging facilitates monitoring of WML changes.
- Accurate quantification of WMLs is crucial but hindered by a lack of standardized validation datasets and metrics for automated analysis methods.
Purpose of the Study:
- To objectively compare the performance of automated WML change detection methods.
- To establish a standardized evaluation framework using publicly available datasets with ground truth.
- To identify optimal combinations of image processing steps for WML quantification.
Main Methods:
- Acquisition of longitudinal MR datasets from 20 MS patients.
- Extraction, spatial alignment, and intensity normalization of brain regions.
- Expert-driven delineation and revision of WML changes to create ground truth segmentations.
- Systematic evaluation of two unsupervised and one supervised intensity-based change detection methods using common metrics.
Main Results:
- An objective, quantitative, and systematic comparison of WML change detection algorithms was performed.
- The study identified the best-performing combinations of dissimilarity map construction and segmentation steps.
- Performance metrics were standardized across different methods for a fair comparison.
Conclusions:
- The developed framework enables objective comparison of automated WML detection methods.
- This research contributes to more reliable quantification of WMLs in neurodegenerative diseases.
- Standardized evaluation is essential for advancing MR image analysis in clinical research.
