Comparison of semi-automatic volumetric VX2 hepatic tumor segmentation from cone beam CT and multi-detector CT with histology in rabbit models.

RATIONALE AND
OBJECTIVES: The purpose of this study was to compare tumor volume in a VX2 rabbit model as calculated using semiautomatic tumor segmentation from C-arm cone-beam computed tomography (CBCT) and multidetector computed tomography (MDCT) to the actual tumor volume.
MATERIALS AND METHODS: Twenty VX2 tumors in 20 adult male New Zealand rabbits (one tumor per rabbit) were imaged with CBCT (using an intra-arterial contrast medium injection) and MDCT (using an intravenous contrast injection). All tumor volumes were measured using semiautomatic three-dimensional volumetric segmentation software. The software uses a region-growing method using non-Euclidean radial basis functions. After imaging, the tumors were excised for pathologic volume measurement. The imaging-based tumor volume measurements were compared to the pathologic volumes using linear regression, with Pearson's test, and correlated using Bland-Altman analysis.
RESULTS: Average tumor volumes were 3.5 ± 1.6 cm(3) (range, 1.4-7.2 cm(3)) on pathology, 3.8 ± 1.6 cm(3) (range, 1.3-7.3 cm(3)) on CBCT, and 3.9 ± 1.6 (range, 1.8-7.5 cm(3)) on MDCT (P < .001). A strong correlation between volumes on pathology and CBCT and also with MDCT was observed (Pearson's correlation coefficient = 0.993 and 0.996, P < .001, for CBCT and MDCT, respectively). Bland-Altman analysis showed that MDCT tended to overestimate tumor volume, and there was stronger agreement for tumor volume between CBCT and pathology than with MDCT, possibly because of the intra-arterial contrast injection.
CONCLUSIONS: Tumor volume as measured using semiautomatic tumor segmentation software showed a strong correlation with the "real volume" measured on pathology. The segmentation software on CBCT and MDCT can be a useful tool for volumetric hepatic tumor assessment.