Bone SPECT-based segmented attenuation correction for quantitative analysis of bone metastasis (B-SAC): comparison with CT-based attenuation correction

Background: Evidence has shown the clinical usefulness of measuring the metastatic tumor burden of bone for prognostic assessment especially in prostate cancer; quantitative evaluation by dedicated SPECT is difficult due to the lack of attenuation correction (AC) method. We developed a novel method for attenuation correction using bone SPECT emission data (bone SPECT-based segmented attenuation correction; B-SAC) where emission data were virtually segmented into three tissues (i.e., bone, soft tissue, and air). Then, the pixel values in SPECT were replaced by 50 for the virtual soft tissue, and - 1000 for the virtual air. The replaced pixel values for the virtual bone were based on the averaged CT values of the normal vertebrae (B-SAC(N)) or the metastatic bones (B-SAC(M)). Subsequently, the processed SPECT data (i.e., SPECT value) were supposed to realize CT data (i.e., CT value) that were used for B-SAC. The standardized uptake values (SUVs) of 112 metastatic bone tumors in 15 patients with prostate cancer were compared between CTAC with scatter correction (SC) and resolution recovery (RR) and the following reconstruction conditions: B-SAC(N) (+)SC(+)RR(+), B-SAC(M) (+)SC(+)RR(+), uniform AC(UAC)(+)SC(+)RR(+), AC(-)SC(+)RR(+), and no correction (NC). Results: The SUVs in the five reconstruction conditions were all correlated with those in CTAC(+)SC(+)RR(+) (p < 0.01), and the correlations between B-SAC(N) or B-SAC(M) and CTAC images were excellent (r > 0.94). Bland-Altman analysis showed that the mean SUV differences between CTAC (+)SC(+)RR(+) and the other five reconstructions were 0.85 +/- 2.25 for B-SAC(N) (+)SC(+)RR(+), 1.61 +/- 2.36 for B-SAC(M) (+)SC(+)RR(+), 1.54 +/- 3.84 for UAC(+)SC(+)RR(+), - 3.12 +/- 4.97 for AC(-)SC(+)RR(+), and - 5.96 +/- 4.59 for NC. Compared to CTAC(+)SC(+)RR(+), B-SAC(N) (+)SC(+)RR(+) showed a slight but constant overestimation (approximately 17%) of the metastatic tumor burden of bone when the same threshold of metabolic tumor volume was used. Conclusions: The results of this preliminary study suggest the potential for B-SAC to improve the quantitation of bone metastases in bone SPECT when X-ray CT or transmission CT data are not available. Considering the small but unignorable differences of lesional SUVs between CTAC and B-SAC, SUVs obtained with the current version of B-SAC seem difficult to be directly compared with those obtained with CTAC.