Performance of three freely available methods for extracting white matter hyperintensities: FreeSurfer, UBO Detector, and BIANCA

White matter hyperintensities (WMH) of presumed vascular origin are frequently found in MRIs of healthy older adults. WMH are also associated with aging and cognitive decline. Here, we compared and validated three algorithms for WMH extraction: FreeSurfer (T1w), UBO Detector (T1w + FLAIR), and FSL&#...

Full description

Saved in:
Bibliographic Details
Published in:Human brain mapping 2022-04, Vol.43 (5), p.1481-1500
Main Authors: Hotz, Isabel, Deschwanden, Pascal Frédéric, Liem, Franziskus, Mérillat, Susan, Malagurski, Brigitta, Kollias, Spyros, Jäncke, Lutz
Format: Article
Language:English
Subjects:
Accuracy
Adults
Age
Aged
Aged, 80 and over
Aging
Algorithms
automated segmentation
Automation
Brain Diseases
Cognitive ability
Datasets
healthy aging
Humans
Image segmentation
Imaging, Three-Dimensional
Leukoaraiosis
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Medical imaging
Methods
Middle Aged
MRI
Older people
Outliers (statistics)
Sensors
Substantia alba
validation
White Matter - diagnostic imaging
white matter hyperintensities
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:White matter hyperintensities (WMH) of presumed vascular origin are frequently found in MRIs of healthy older adults. WMH are also associated with aging and cognitive decline. Here, we compared and validated three algorithms for WMH extraction: FreeSurfer (T1w), UBO Detector (T1w + FLAIR), and FSL's Brain Intensity AbNormality Classification Algorithm (BIANCA; T1w + FLAIR) using a longitudinal dataset comprising MRI data of cognitively healthy older adults (baseline N = 231, age range 64–87 years). As reference we manually segmented WMH in T1w, three‐dimensional (3D) FLAIR, and two‐dimensional (2D) FLAIR images which were used to assess the segmentation accuracy of the different automated algorithms. Further, we assessed the relationships of WMH volumes provided by the algorithms with Fazekas scores and age. FreeSurfer underestimated the WMH volumes and scored worst in Dice Similarity Coefficient (DSC = 0.434) but its WMH volumes strongly correlated with the Fazekas scores (rs = 0.73). BIANCA accomplished the highest DSC (0.602) in 3D FLAIR images. However, the relations with the Fazekas scores were only moderate, especially in the 2D FLAIR images (rs = 0.41), and many outlier WMH volumes were detected when exploring within‐person trajectories (2D FLAIR: ~30%). UBO Detector performed similarly to BIANCA in DSC with both modalities and reached the best DSC in 2D FLAIR (0.531) without requiring a tailored training dataset. In addition, it achieved very high associations with the Fazekas scores (2D FLAIR: rs = 0.80). In summary, our results emphasize the importance of carefully contemplating the choice of the WMH segmentation algorithm and MR‐modality. In this study we validated the performance of three freely available algorithms for WMH extraction: FreeSurfer, UBO Detector, and BIANCA. We used manual WMH segmentations to evaluate the segmentation accuracy of the different automated algorithms, and the relationships of WMH volume estimates provided by the algorithms with Fazekas scores and age. FreeSurfer underestimated the WMH volumes, scored worst in the Dice similarity coefficient (DSC) but correlated strongly with the Fazekas scores, and BIANCA accomplished high segmentation accuracy, but the associations with the Fazekas scores were weak and we identified a significant number of outlier‐WMH volumes whereas UBO Detector performed similarly to BIANCA in DSC and achieved very high associations with the Fazekas scores.
ISSN:1065-9471
1097-0193
1097-0193
DOI:10.1002/hbm.25739