Outlier data in volume calculations of uterine fibroids comparing ellipsoid formula and voxel-based segmentation.

Abstract

Background: The ellipsoidal formula is the most common method used to determine the volume of fibroids on MR images. Labor-intensive manual segmentation provides the opportunity to measure the volume of a given lesion on a voxel basis. The aim of this study is to compare the volume of the uterine fibroid calculated using voxel-based segmentation and the ellipsoid formula.

Methods: In this study, pretreatment MRI scans of patients who underwent uterine artery embolization due to symptomatic fibroids were retrospectively collected between 2016 and 2022. The volume data of the largest fibroids was determined by segmentation (group S) as the reference standard. In addition, the largest diameters of the fibroids in three planes (D1/D2/D3) were also measured and the volumes were also estimated by using the ellipsoidal formula (D1*D2*D3*0.5233) (group E). The interobserver reproducibility of the diameter measurements was tested. The volume values (median, IQR) were compared; in addition, the differences between the segmented and ellipsoidal volumes were recorded. Statistical analysis was performed using the Kruskal-Wallis test, Wilcoxon's two-sided signed rank test, intraclass correlation (ICC) analysis, and Bland-Altman plots.

Results: Pretreatment MRI scans of 113 patients were identified. Fibroids where the interobserver difference of diameter-based ellipsoidal volumes reached 30% were excluded resulting in 99 patients in the final dataset. The volumes of group S and group E showed no significant differences with 134.1 (257.3) cm³ and 133.5 (269.1) cm³, respectively, with an average difference of 3.47 cm³ (0.25%; p = 0.377). The agreement between the two methods was excellent (ICC = 0.979), without difference across fibroid locations. In 46 cases (46.5%), group S values were larger, and in 53 fibroids (53.5%), group E volume values were larger. However, volume difference was outside the ± 20% range in 21 cases (21.2%) and outside the ± 30% range in 10 cases (10.1%); the largest difference was approximately 56.5% (156.5 cm³).

Conclusions: The ellipsoid formula-based and the voxel-based volume calculation showed no significant difference for the group as a whole. However, there was a difference of > 20% in 21.2% of cases and > 30% in 10.1% of cases. In the era of personalized medicine, it is not only the average difference between the two methods that need to be considered but also cases where there is a 20% or 30% difference in results should be highlighted, as these may change the treatment plan in individual cases. This methodology should also be tested for other tumor-type volume calculations.