Accuracy of metabolic volume and total glycolysis among six threshold-based target segmentation algorithms

This study aimed to evaluate the accuracy of six threshold-based segmentation methods with different target-to-background ratios (TBR), images with different voxel sizes and image noise, in measuring metabolic volume (MV) and total glycolysis (TG).

A standard body phantom consisting of six spheres (inner diameters of 37, 28, 22, 17, 13, and 10 mm) was filled with ¹⁸F-FDG solution. The background radioactivity level was 2.65 kBq/mL, and the TBRs were 4 and 8. PET data were acquired for 30 min with list mode. PET data for 30 and 3 min were reconstructed with a three-dimensional ordered subset expectation maximization algorithm plus time-of-flight information with images with 2 and 4 mm isotropic voxels. The six methods examined were absolute standardized uptake value (SUV) of 2.5 (SUV_2.5), 41%, 50%, adaptive 41%, and adaptive 50% thresholds of maximum SUV (Th₄₁, Th₅₀, ThA₄₁, and ThA₅₀, respectively); and the contrast-oriented algorithm (Th_COA). Segmented MV and TG were compared with the actual inner volume and expressed as percentages (%MV_seg and %TG_seg, respectively). In addition, the segmented MV was converted to the diameter, and the differences of it from the reference diameter were compared among six methods.

The Th_COA method yielded the most accurate measurements of %MV_seg and %TG_seg; the difference between %MV_seg or %TG_seg and its reference were smaller than 10% in 30-min and 15% in 3-min images, but the segmented contour was almost the same as the reference diameter. Measurements with Th₅₀ and Th_COA were highly accurate for both %MV_seg and %TG_seg in the large spheres, and the adaptive threshold methods, including ThA₄₁, ThA₅₀, and Th_COA, were also highly accurate in the small spheres. The voxel sizes affected the accuracy of %MV_seg and %TG_seg with a TBR of 4 in any threshold-based methods.

Of the six threshold-based segmentation methods studied, Th_COA was the most accurate method for evaluating MV and TG and had only minor dependence on TBRs and sphere size. The small voxel sizes improved the variation of the accuracy in low TBR.