Related Experiment Video
Updated: Jul 2, 2025
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
Image harmonization improves consistency of intra-rater delineations of MS lesions in heterogeneous MRI
Aaron Carass1, Danielle Greenman2, Blake E Dewey3
1Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA.
Abstract:
Clinical magnetic resonance images (MRIs) lack a standard intensity scale due to differences in scanner hardware and the pulse sequences used to acquire the images. When MRIs are used for quantification, as in the evaluation of white matter lesions (WMLs) in multiple sclerosis, this lack of intensity standardization becomes a critical problem affecting both the staging and tracking of the disease and its treatment. This paper presents a study of harmonization on WML segmentation consistency, which is evaluated using an object detection classification scheme that incorporates manual delineations from both the original and harmonized MRIs. A cohort of ten people scanned on two different imaging platforms was studied. An expert rater, blinded to the image source, manually delineated WMLs on images from both scanners before and after harmonization. It was found that there is closer agreement in both global and per-lesion WML volume and spatial distribution after harmonization, demonstrating the importance of image harmonization prior to the creation of manual delineations. These results could lead to better truth models in both the development and evaluation of automated lesion segmentation algorithms.
Insights
Image harmonization improves consistency in segmenting white matter lesions (WMLs) in multiple sclerosis. Standardizing magnetic resonance images (MRIs) enhances agreement in lesion volume and spatial distribution, crucial for disease tracking and treatment evaluation.
Area of Science:
- Medical Imaging
- Neurology
- Quantitative MRI
Background:
- Clinical magnetic resonance images (MRIs) lack standardized intensity scales due to variations in hardware and pulse sequences.
- This lack of standardization critically impacts the quantification of white matter lesions (WMLs) in multiple sclerosis (MS), affecting disease staging, tracking, and treatment assessment.
Purpose of the Study:
- To evaluate the impact of image harmonization on the consistency of WML segmentation.
- To assess whether harmonization improves agreement in manual delineations of WMLs.
Main Methods:
- A cohort of ten participants underwent MRI scans on two different platforms.
- An expert rater manually delineated WMLs on both original and harmonized MRIs, blinded to the image source.
- Segmentation consistency was evaluated using an object detection classification scheme comparing manual delineations.
Main Results:
- Harmonization led to closer agreement in both global and per-lesion WML volume.
- Spatial distribution of WMLs also showed improved agreement after harmonization.
- These findings underscore the importance of image harmonization before manual WML delineation.
Conclusions:
- Image harmonization is essential for reliable WML quantification in MS.
- Harmonized MRI data can improve the accuracy of manual delineations.
- This study provides a foundation for developing better truth models for automated WML segmentation algorithms.
