Skip to main content
. Author manuscript; available in PMC: 2023 Jan 1.
Published in final edited form as: Magn Reson Imaging. 2021 Oct 16;85:71–79. doi: 10.1016/j.mri.2021.10.007

Figure 4.

Figure 4.

Agreement between ground truth and fully automated white matter hyperintensity (WMH) segmentation algorithms. Ground truth was manual segmentation, while segmentation algorithms included Lesion Probability Algorithm (LPA); Lesion Growing Algorithm (LGA); spell out Brain Intensity AbNormality Classification Algorithm (BIANCA); and Half-Gaussian Mixture Model (HGMM). Agreement metrics include the (a) dice coefficient, (b) sensitivity, and (c) specificity.