Skip to main content
. Author manuscript; available in PMC: 2024 May 1.
Published in final edited form as: Mayo Clin Proc. 2023 Mar 16;98(5):689–700. doi: 10.1016/j.mayocp.2022.12.019

Figure 3: Overall performance of AI-generated TKV segmentation compared to Medical Image Analyst corrected AI-generated TKV segmentation.

Figure 3:

Panel A shows Bland-Altman plots to evaluate absolute agreement between AI-generated segmentation and medical image analyst corrected AI-generated segmentation. Mean difference between measures (blue dashed line); 95% CI for mean difference (shaded blue band); 95% limits of agreement (orange dashed line; average ± 1.96 standard deviation of difference); 95% CI for limits of agreement (shaded orange band). Panel B is the same as Panel A, but for percent difference between AI-generated TKV and medical image analyst corrected AI-generated TKV. Panel C shows a linear regression of highly correlated AI-generated TKV, and medical image analyst corrected AI-generated TKV (slope=1.00, intercept=−41.08, r2 = 0.99, P <.0001). Panel D shows a scatter plot of medical image analyst corrected AI-generated TKV (cc) by Dice score. Panel E shows box plots with individual case scatter of similarity and dissimilarity metrics including dice, jaccard, hausdorff distance (mm), mean surface distance (mm) and surface distance standard deviation. Panel F shows a non-inferiority plot of the mean percent difference (± 95% CI) between AI TKV and corrected AI TKV (gray dashed line = zero difference between methods; dark blue dashed line represents delta acquired from prior inter-rater agreement study; teal dashed line represents delta acquired from stereology measurements; pink dashed line represents delta acquired from ellipsoid measurements. Mean AI TKV and corrected AI TKV difference is non-inferior to inter-rater, stereology and ellipsoid deltas (One sided t-test; inter-rater P<.0001, stereology P<.0001, ellipsoid P<.0001) 12.