Alzheimer's and vascular disease classification using regional texture biomarkers in FLAIR MRI
Karissa Chan1, Corinne Fischer2, Pejman Jabehdar Maralani3
1Electrical, Computer and Biomedical Engineering Department, Toronto Metropolitan University, 350 Victoria St., Toronto, ON M5B 2K3, Canada; Institute for Biomedical Engineering, Science Tech (iBEST), A Partnership Between St. Michael's Hospital and Toronto Metropolitan University, 209 Victoria St., Toronto, ON M5B 1T8, Canada.
Abstract:
Interactions between subcortical vascular disease and dementia due to Alzheimer's disease (AD) are unclear, and clinical overlap between the diseases makes diagnosis challenging. Existing studies have shown regional microstructural changes specific to each disease, and that textures in fluid-attenuated inversion recovery (FLAIR) MRI images may characterize abnormalities in tissue microstructure. This work aims to investigate regional FLAIR biomarkers that can differentiate dementia cohorts with and without subcortical vascular disease. FLAIR and diffusion MRI (dMRI) volumes were obtained in 65 mild cognitive impairment (MCI), 21 AD, 44 subcortical vascular MCI (scVMCI), 22 Mixed etiology, and 48 healthy elderly patients. FLAIR texture and intensity biomarkers were extracted from the normal appearing brain matter (NABM), WML penumbra, blood supply territory (BST), and white matter tract regions of each patient. All FLAIR biomarkers were correlated to dMRI metrics in each region and global WML load, and biomarker means between groups were compared using ANOVA. Binary classifications were performed using Random Forest classifiers to investigate the predictive nature of the regional biomarkers, and SHAP feature analysis was performed to further investigate optimal regions of interest for differentiating disease groups. The regional FLAIR biomarkers were strongly correlated to MD, while all biomarker regions but white matter tracts were strongly correlated to WML burden. Classification between Mixed disease and healthy, AD, and scVMCI patients yielded accuracies of 97%, 81%, and 72% respectively using WM tract biomarkers. Classification between scVMCI and healthy, MCI, and AD patients yielded accuracies of 89%, 84%, and 79% respectively using penumbra biomarkers. Only the classification between AD and healthy patients had optimal results using NABM biomarkers. This work presents novel regional FLAIR biomarkers that may quantify white matter degeneration related to subcortical vascular disease, and which indicate that investigating degeneration in specific regions may be more important than assessing global WML burden in vascular disease groups.
Insights
New MRI biomarkers can differentiate dementia subtypes, including Alzheimer's disease and subcortical vascular MCI. These fluid-attenuated inversion recovery (FLAIR) biomarkers highlight specific brain regions, improving diagnostic accuracy for mixed dementia cases.
Area of Science:
- Neuroimaging
- Neurology
- Biomarkers
Background:
- Subcortical vascular disease and Alzheimer's disease (AD) dementia often co-occur, complicating diagnosis due to overlapping clinical symptoms.
- Regional microstructural changes are specific to each disease, and fluid-attenuated inversion recovery (FLAIR) MRI textures may reveal tissue abnormalities.
Purpose of the Study:
- To identify regional FLAIR MRI biomarkers capable of distinguishing dementia patients with and without subcortical vascular disease.
- To explore the predictive power of these biomarkers in classifying different dementia cohorts.
Main Methods:
- Acquired FLAIR and diffusion MRI (dMRI) data from healthy elderly individuals and patients with mild cognitive impairment (MCI), AD, subcortical vascular MCI (scVMCI), and mixed etiology dementia.
- Extracted FLAIR texture and intensity biomarkers from normal-appearing brain matter (NABM), white matter lesion (WML) penumbra, blood supply territory (BST), and white matter tract regions.
- Utilized Random Forest classifiers and SHAP feature analysis for biomarker evaluation and group differentiation.
Main Results:
- Regional FLAIR biomarkers strongly correlated with mean diffusivity (MD) and white matter lesion (WML) burden.
- High classification accuracies were achieved: Mixed vs. healthy (97%), Mixed vs. AD (81%), Mixed vs. scVMCI (72%) using white matter tract biomarkers.
- Penumbra biomarkers effectively differentiated scVMCI from healthy (89%), MCI (84%), and AD (79%) groups.
Conclusions:
- Novel regional FLAIR biomarkers can quantify white matter degeneration associated with subcortical vascular disease.
- Focusing on specific regional degeneration is more informative than assessing global WML burden for vascular disease groups.
- These biomarkers offer potential for improved differential diagnosis in complex dementia cases.
