Related Experiment Video
Updated: Oct 16, 2025
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
Automatic quantification of white matter hyperintensities on T2-weighted fluid attenuated inversion recovery magnetic
Kay C Igwe1, Patrick J Lao2, Robert S Vorburger3
1Taub Institute for Research on Alzheimer's Disease and the Aging Brain, Vagelos College of Physicians and Surgeons, Columbia University, 630 West 168th Street, New York, NY 10032, USA; Gertrude H. Sergievsky Center, Vagelos College of Physicians and Surgeons, Columbia University, 630 West 168th Street, New York, NY 10032, USA.
Abstract:
White matter hyperintensities (WMH) are areas of increased signal visualized on T2-weighted fluid attenuated inversion recovery (FLAIR) brain magnetic resonance imaging (MRI) sequences. They are typically attributed to small vessel cerebrovascular disease in the context of aging. Among older adults, WMH are associated with risk of cognitive decline and dementia, stroke, and various other health outcomes. There has been increasing interest in incorporating quantitative WMH measurement as outcomes in clinical trials, observational research, and clinical settings. Here, we present a novel, fully automated, unsupervised detection algorithm for WMH segmentation and quantification. The algorithm uses a robust preprocessing pipeline, including brain extraction and a sample-specific mask that incorporates spatial information for automatic false positive reduction, and a half Gaussian mixture model (HGMM). The method was evaluated in 24 participants with varying degrees of WMH (4.9-78.6 cm3) from a community-based study of aging and dementia with dice coefficient, sensitivity, specificity, correlation, and bias relative to the ground truth manual segmentation approach performed by two expert raters. Results were compared with those derived from commonly used available WMH segmentation packages, including SPM lesion probability algorithm (LPA), SPM lesion growing algorithm (LGA), and Brain Intensity AbNormality Classification Algorithm (BIANCA). The HGMM algorithm derived WMH values that had a dice score of 0.87, sensitivity of 0.89, and specificity of 0.99 compared to ground truth. White matter hyperintensity volumes derived with HGMM were strongly correlated with ground truth values (r = 0.97, p = 3.9e-16), with no observable bias (-1.1 [-2.6, 0.44], p-value = 0.16). Our novel algorithm uniquely uses a robust preprocessing pipeline and a half-Gaussian mixture model to segment WMH with high agreement with ground truth for large scale studies of brain aging.
Insights
We developed a new automated algorithm to accurately measure white matter hyperintensities (WMH) on brain MRI scans. This tool shows high agreement with expert segmentation, aiding aging and dementia research.
Area of Science:
- Neuroimaging
- Medical image analysis
- Cerebrovascular disease research
Background:
- White matter hyperintensities (WMH) are common MRI findings in aging.
- WMH are linked to cognitive decline, dementia, and stroke risk.
- Accurate WMH quantification is crucial for clinical trials and research.
Purpose of the Study:
- To introduce a novel, fully automated, unsupervised algorithm for WMH segmentation and quantification.
- To evaluate the performance of this new algorithm against manual segmentation and existing methods.
Main Methods:
- The algorithm employs a robust preprocessing pipeline with brain extraction and spatial information for false positive reduction.
- A half Gaussian mixture model (HGMM) is utilized for WMH segmentation.
- Performance was assessed using Dice coefficient, sensitivity, specificity, correlation, and bias in 24 participants.
Main Results:
- The HGMM algorithm achieved a Dice score of 0.87, sensitivity of 0.89, and specificity of 0.99 against ground truth.
- WMH volumes derived from HGMM strongly correlated with manual segmentation (r=0.97, p < 0.001) with no significant bias.
- The algorithm demonstrated superior or comparable performance to established methods like SPM LPA, SPM LGA, and BIANCA.
Conclusions:
- The novel HGMM algorithm provides accurate and reliable WMH segmentation and quantification.
- Its high agreement with ground truth makes it suitable for large-scale studies on brain aging and dementia.
- This automated approach facilitates objective WMH measurement in research and clinical settings.
